{"ep": "h1-00048", "task": "L1_014", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.1423, "speedup": 4.1423, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 47.3, "calls": 1, "tokens_in": 5875, "tokens_out": 1212, "ctx_chars": 9311, "t_end": 1791527089.4663131, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.1423, "lo95": 4.1314, "mean": 4.2455, "ev_only": 4.1713, "ref_ms": 7.38419, "cand_ms": 1.78264, "n_trials": 170, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9758, "r_wall_s": 34.97, "compile_s": 1.98, "r_error": "", "src_len": 1946, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5875, "tout": 1212, "ts": 1791527054.3387713, "chk": null, "code_len": 1946}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5875, "started": 1791527042.1315892}
{"ep": "h1-00062", "task": "L3_019", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 49.7, "calls": 1, "tokens_in": 2378, "tokens_out": 3614, "ctx_chars": 0, "t_end": 1791527091.866484, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.1203, "r_wall_s": 17.0, "compile_s": 2.09, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 4384, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2378, "tout": 3614, "ts": 1791527074.82705, "chk": null, "code_len": 4384}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2378, "started": 1791527042.1451595}
{"ep": "h1-00010", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1133, "speedup": 1.1133, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 53.5, "calls": 2, "tokens_in": 14379, "tokens_out": 2273, "ctx_chars": 11296, "t_end": 1791527095.6261659, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1133, "lo95": 1.1119, "mean": 1.1132, "ev_only": 1.1134, "ref_ms": 31.40242, "cand_ms": 28.20622, "n_trials": 48, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.046, "r_wall_s": 14.44, "compile_s": 2.0, "r_error": "", "src_len": 1267, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6639, "tout": 1585, "ts": 1791527057.341699, "chk": "ok", "code_len": 1267}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7740, "tout": 688, "ts": 1791527081.1354988, "chk": null, "code_len": 1267}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6639, "started": 1791527042.1146824}
{"ep": "h1-00026", "task": "L3_034", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9764, "speedup": 0.9764, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 57.0, "calls": 3, "tokens_in": 16193, "tokens_out": 2164, "ctx_chars": 6034, "t_end": 1791527099.0753922, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9764, "lo95": 0.9727, "mean": 1.0623, "ev_only": 0.9762, "ref_ms": 27.94104, "cand_ms": 28.6169, "n_trials": 57, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1982, "r_wall_s": 25.19, "compile_s": 1.89, "r_error": "", "src_len": 2101, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4546, "tout": 1147, "ts": 1791527054.0171936, "chk": "ok", "code_len": 2203}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5805, "tout": 13, "ts": 1791527065.349931, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5842, "tout": 1004, "ts": 1791527073.860475, "chk": null, "code_len": 2101}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4546, "started": 1791527042.123894}
{"ep": "h1-00063", "task": "L3_033", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 63.0, "calls": 1, "tokens_in": 2001, "tokens_out": 1438, "ctx_chars": 0, "t_end": 1791527105.1559622, "error": "RuntimeError: Error building extension 'rnn_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=rnn_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 47.11, "compile_s": 47.1, "r_error": "RuntimeError: Error building extension 'rnn_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=rnn_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "src_len": 2478, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2001, "tout": 1438, "ts": 1791527058.021178, "chk": null, "code_len": 2478}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2001, "started": 1791527042.1477258}
{"ep": "h1-00045", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0349, "speedup": 1.0349, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 65.2, "calls": 2, "tokens_in": 4524, "tokens_out": 2171, "ctx_chars": 0, "t_end": 1791527107.3789313, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0349, "lo95": 1.0345, "mean": 1.049, "ev_only": 1.0349, "ref_ms": 8.25713, "cand_ms": 7.97873, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 37.89, "compile_s": 1.89, "r_error": "", "src_len": 1116, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1706, "tout": 1481, "ts": 1791527055.8995166, "chk": "ok", "code_len": 1116}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2818, "tout": 690, "ts": 1791527069.418648, "chk": null, "code_len": 1116}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1706, "started": 1791527042.1301703}
{"ep": "h1-00039", "task": "L2_051", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 29.3715, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.0, "calls": 3, "tokens_in": 21095, "tokens_out": 3358, "ctx_chars": 8570, "t_end": 1791527115.111832, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 29.3715, "lo95": 29.1868, "mean": 28.9672, "ev_only": 30.1281, "ref_ms": 15.91786, "cand_ms": 0.54195, "n_trials": 106, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.3779, "r_wall_s": 23.21, "compile_s": 2.53, "r_error": "", "src_len": 1889, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5370, "tout": 2344, "ts": 1791527064.9415672, "chk": "ok", "code_len": 1949}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7826, "tout": 49, "ts": 1791527083.2932873, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7899, "tout": 965, "ts": 1791527091.7067108, "chk": null, "code_len": 1889}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5370, "started": 1791527042.127407}
{"ep": "h1-00006", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.034, "speedup": 1.034, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 75.3, "calls": 2, "tokens_in": 12220, "tokens_out": 1697, "ctx_chars": 9028, "t_end": 1791527117.4214656, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.034, "lo95": 1.0336, "mean": 1.0336, "ev_only": 1.0328, "ref_ms": 8.2316, "cand_ms": 7.96096, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0058, "r_wall_s": 48.54, "compile_s": 2.73, "r_error": "", "src_len": 1188, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 1032, "ts": 1791527052.1754103, "chk": "ok", "code_len": 1188}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6682, "tout": 665, "ts": 1791527068.7374165, "chk": null, "code_len": 1188}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5538, "started": 1791527042.1131535}
{"ep": "h1-00023", "task": "L3_039", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7949, "speedup": 0.7949, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 76.1, "calls": 2, "tokens_in": 12127, "tokens_out": 1967, "ctx_chars": 8224, "t_end": 1791527118.1847913, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7949, "lo95": 0.7894, "mean": 0.8178, "ev_only": 0.7948, "ref_ms": 31.98475, "cand_ms": 40.23725, "n_trials": 33, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 32.23, "compile_s": 2.04, "r_error": "", "src_len": 926, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 1042, "ts": 1791527056.481407, "chk": "ok", "code_len": 939}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6639, "tout": 925, "ts": 1791527085.8433955, "chk": null, "code_len": 926}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5488, "started": 1791527042.1216433}
{"ep": "h1-00047", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0149, "speedup": 1.0149, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 88.3, "calls": 2, "tokens_in": 5618, "tokens_out": 4788, "ctx_chars": 0, "t_end": 1791527130.4627166, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0149, "lo95": 1.0147, "mean": 1.0145, "ev_only": 1.0154, "ref_ms": 8.21827, "cand_ms": 8.09757, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0123, "r_wall_s": 20.94, "compile_s": 3.01, "r_error": "", "src_len": 3160, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1730, "tout": 3012, "ts": 1791527069.1063888, "chk": "ok", "code_len": 3160}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3888, "tout": 1776, "ts": 1791527109.4402792, "chk": null, "code_len": 3160}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1730, "started": 1791527042.1318715}
{"ep": "h1-00012", "task": "L3_022", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.3078, "speedup": 0.3078, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 88.7, "calls": 3, "tokens_in": 24491, "tokens_out": 5977, "ctx_chars": 6513, "t_end": 1791527130.8318, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.3078, "lo95": 0.2965, "mean": 0.3299, "ev_only": 0.3076, "ref_ms": 6.25328, "cand_ms": 20.31822, "n_trials": 64, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0556, "r_wall_s": 23.9, "compile_s": 2.02, "r_error": "", "src_len": 6053, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6066, "tout": 3000, "ts": 1791527067.1906633, "chk": "ok", "code_len": 6053}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9178, "tout": 45, "ts": 1791527083.859163, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9247, "tout": 2932, "ts": 1791527106.9117398, "chk": null, "code_len": 6053}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6066, "started": 1791527042.1166022}
{"ep": "h1-00061", "task": "L2_057", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1673, "speedup": 2.1673, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 91.0, "calls": 1, "tokens_in": 5844, "tokens_out": 479, "ctx_chars": 9855, "t_end": 1791527133.1721754, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.1673, "lo95": 2.166, "mean": 2.1645, "ev_only": 2.1798, "ref_ms": 6.28579, "cand_ms": 2.90027, "n_trials": 224, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2346, "r_wall_s": 84.42, "compile_s": 1.88, "r_error": "", "src_len": 908, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5844, "tout": 479, "ts": 1791527047.9070668, "chk": null, "code_len": 908}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5844, "started": 1791527042.145126}
{"ep": "h1-00032", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 37.2401, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 95.9, "calls": 2, "tokens_in": 12555, "tokens_out": 4008, "ctx_chars": 8570, "t_end": 1791527138.0673916, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 37.2401, "lo95": 37.1292, "mean": 36.956, "ev_only": 37.3425, "ref_ms": 15.95069, "cand_ms": 0.42832, "n_trials": 85, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.9608, "r_wall_s": 30.54, "compile_s": 2.09, "r_error": "", "src_len": 2309, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5372, "tout": 2769, "ts": 1791527068.4093547, "chk": "ok", "code_len": 2309}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7183, "tout": 1239, "ts": 1791527107.2995927, "chk": null, "code_len": 2309}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5372, "started": 1791527042.1263897}
{"ep": "h1-00034", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 30.1791, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 99.3, "calls": 2, "tokens_in": 13020, "tokens_out": 5230, "ctx_chars": 8570, "t_end": 1791527141.4629304, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 30.1791, "lo95": 28.075, "mean": 26.5088, "ev_only": 30.2859, "ref_ms": 16.07799, "cand_ms": 0.53275, "n_trials": 90, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.951, "r_wall_s": 34.83, "compile_s": 1.98, "r_error": "", "src_len": 3178, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5372, "tout": 3520, "ts": 1791527075.3337882, "chk": "ok", "code_len": 3178}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7648, "tout": 1710, "ts": 1791527106.4670992, "chk": null, "code_len": 3178}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5372, "started": 1791527042.1255732}
{"ep": "h1-00054", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9176, "speedup": 0.9176, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 102.4, "calls": 2, "tokens_in": 14187, "tokens_out": 4575, "ctx_chars": 10384, "t_end": 1791527144.5798361, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9176, "lo95": 0.9174, "mean": 0.9174, "ev_only": 0.9163, "ref_ms": 7.27943, "cand_ms": 7.9335, "n_trials": 216, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 39.67, "compile_s": 2.03, "r_error": "", "src_len": 2491, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6176, "tout": 2829, "ts": 1791527067.5814164, "chk": "ok", "code_len": 2491}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8011, "tout": 1746, "ts": 1791527104.6952868, "chk": null, "code_len": 2491}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6176, "started": 1791527042.1350045}
{"ep": "h1-00043", "task": "L2_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5444, "speedup": 1.5444, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 103.2, "calls": 1, "tokens_in": 1915, "tokens_out": 2458, "ctx_chars": 0, "t_end": 1791527145.318286, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.5444, "lo95": 1.5421, "mean": 1.5424, "ev_only": 1.5444, "ref_ms": 4.73155, "cand_ms": 3.06371, "n_trials": 163, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.2889, "r_wall_s": 80.51, "compile_s": 42.99, "r_error": "", "src_len": 5009, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1915, "tout": 2458, "ts": 1791527064.6574636, "chk": null, "code_len": 5009}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1915, "started": 1791527042.129588}
{"ep": "h1-00014", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0686, "speedup": 1.0686, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 108.7, "calls": 2, "tokens_in": 14827, "tokens_out": 3384, "ctx_chars": 11062, "t_end": 1791527150.817329, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0686, "lo95": 1.067, "mean": 1.0657, "ev_only": 1.07, "ref_ms": 12.76853, "cand_ms": 11.94903, "n_trials": 128, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0269, "r_wall_s": 60.68, "compile_s": 2.15, "r_error": "", "src_len": 1996, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6695, "tout": 2345, "ts": 1791527065.5328395, "chk": "ok", "code_len": 1996}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8132, "tout": 1039, "ts": 1791527090.0890064, "chk": null, "code_len": 1996}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6695, "started": 1791527042.1173227}
{"ep": "h1-00016", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3674, "speedup": 1.3674, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.0, "calls": 2, "tokens_in": 14165, "tokens_out": 3963, "ctx_chars": 10384, "t_end": 1791527159.1115384, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3674, "lo95": 1.3668, "mean": 1.3673, "ev_only": 1.3667, "ref_ms": 7.32525, "cand_ms": 5.3569, "n_trials": 211, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 65.39, "compile_s": 1.91, "r_error": "", "src_len": 2343, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6176, "tout": 2639, "ts": 1791527065.8589509, "chk": "ok", "code_len": 2343}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7989, "tout": 1324, "ts": 1791527093.5438592, "chk": null, "code_len": 2343}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6176, "started": 1791527042.1191397}
{"ep": "h1-00022", "task": "L2_037", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1604, "speedup": 1.1604, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 129.2, "calls": 3, "tokens_in": 7411, "tokens_out": 1885, "ctx_chars": 0, "t_end": 1791527171.3587906, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1604, "lo95": 1.1597, "mean": 1.1593, "ev_only": 1.1605, "ref_ms": 19.76111, "cand_ms": 17.02972, "n_trials": 75, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1465, "r_wall_s": 75.99, "compile_s": 2.44, "r_error": "", "src_len": 1782, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1707, "tout": 991, "ts": 1791527053.0451465, "chk": "ok", "code_len": 1836}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2810, "tout": 60, "ts": 1791527086.8750343, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 2894, "tout": 834, "ts": 1791527093.9508455, "chk": null, "code_len": 1782}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1707, "started": 1791527042.1213982}
{"ep": "h1-00058", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4781, "speedup": 1.4781, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 137.7, "calls": 2, "tokens_in": 4944, "tokens_out": 4295, "ctx_chars": 0, "t_end": 1791527179.830161, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4781, "lo95": 1.4748, "mean": 1.4658, "ev_only": 1.4799, "ref_ms": 7.78328, "cand_ms": 5.2656, "n_trials": 198, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 78.13, "compile_s": 3.36, "r_error": "", "src_len": 2496, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 2672, "ts": 1791527066.203798, "chk": "ok", "code_len": 2496}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3379, "tout": 1623, "ts": 1791527101.5877225, "chk": null, "code_len": 2496}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791527042.135956}
{"ep": "h1-00055", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3958, "speedup": 1.3958, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 143.7, "calls": 2, "tokens_in": 13573, "tokens_out": 2636, "ctx_chars": 10210, "t_end": 1791527185.850451, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3958, "lo95": 1.3918, "mean": 1.3964, "ev_only": 1.3987, "ref_ms": 19.38446, "cand_ms": 13.88789, "n_trials": 76, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0691, "r_wall_s": 98.18, "compile_s": 1.95, "r_error": "", "src_len": 1711, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 1741, "ts": 1791527059.5993311, "chk": "ok", "code_len": 1711}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7438, "tout": 895, "ts": 1791527086.919307, "chk": null, "code_len": 1711}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791527042.1347811}
{"ep": "h1-00051", "task": "L1_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.3195, "speedup": 2.3195, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.5, "calls": 3, "tokens_in": 23919, "tokens_out": 2121, "ctx_chars": 11582, "t_end": 1791527186.6446927, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.3195, "lo95": 2.3173, "mean": 2.3249, "ev_only": 2.3207, "ref_ms": 35.89785, "cand_ms": 15.47634, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 98.88, "compile_s": 2.52, "r_error": "", "src_len": 1890, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7117, "tout": 1128, "ts": 1791527053.956141, "chk": "ok", "code_len": 1890}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8357, "tout": 64, "ts": 1791527078.9186769, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8445, "tout": 929, "ts": 1791527086.8891332, "chk": null, "code_len": 1890}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7117, "started": 1791527042.132235}
{"ep": "h1-00003", "task": "L3_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9324, "speedup": 0.9324, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 146.9, "calls": 3, "tokens_in": 15358, "tokens_out": 1731, "ctx_chars": 6513, "t_end": 1791527188.9957874, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9324, "lo95": 0.932, "mean": 0.9323, "ev_only": 0.9323, "ref_ms": 33.61315, "cand_ms": 36.05085, "n_trials": 36, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0009, "r_wall_s": 79.42, "compile_s": 3.2, "r_error": "", "src_len": 1761, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4416, "tout": 913, "ts": 1791527051.7790797, "chk": "ok", "code_len": 1797}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5441, "tout": 36, "ts": 1791527102.6520107, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5501, "tout": 782, "ts": 1791527109.5433095, "chk": null, "code_len": 1761}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4416, "started": 1791527042.1105695}
{"ep": "h1-00046", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5403, "speedup": 1.5403, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 149.3, "calls": 2, "tokens_in": 15749, "tokens_out": 3967, "ctx_chars": 11288, "t_end": 1791527191.4157395, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.5403, "lo95": 1.5333, "mean": 1.5372, "ev_only": 1.54, "ref_ms": 29.27923, "cand_ms": 19.00894, "n_trials": 29, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0463, "r_wall_s": 100.94, "compile_s": 2.33, "r_error": "", "src_len": 2563, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6972, "tout": 2663, "ts": 1791527067.4893577, "chk": "ok", "code_len": 2563}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8777, "tout": 1304, "ts": 1791527090.2328196, "chk": null, "code_len": 2563}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6972, "started": 1791527042.1312823}
{"ep": "h1-00001", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7339, "speedup": 0.7339, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 154.1, "calls": 2, "tokens_in": 15181, "tokens_out": 2588, "ctx_chars": 11175, "t_end": 1791527196.1998758, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7339, "lo95": 0.733, "mean": 0.7366, "ev_only": 0.734, "ref_ms": 3.32311, "cand_ms": 4.52818, "n_trials": 225, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0006, "r_wall_s": 91.89, "compile_s": 2.86, "r_error": "", "src_len": 2294, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6880, "tout": 1549, "ts": 1791527055.783851, "chk": "ok", "code_len": 2294}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8301, "tout": 1039, "ts": 1791527102.8455157, "chk": null, "code_len": 2294}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6880, "started": 1791527042.1101499}
{"ep": "h1-00020", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.28, "speedup": 1.28, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 156.8, "calls": 2, "tokens_in": 4913, "tokens_out": 2939, "ctx_chars": 0, "t_end": 1791527198.903522, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.28, "lo95": 1.2792, "mean": 1.2693, "ev_only": 1.2814, "ref_ms": 19.82116, "cand_ms": 15.48572, "n_trials": 58, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0401, "r_wall_s": 96.23, "compile_s": 1.91, "r_error": "", "src_len": 1849, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1709, "tout": 1996, "ts": 1791527060.9940364, "chk": "ok", "code_len": 1849}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3204, "tout": 943, "ts": 1791527101.7078505, "chk": null, "code_len": 1849}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1709, "started": 1791527042.1200812}
{"ep": "h1-00009", "task": "L3_047", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9687, "speedup": 0.9687, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 159.1, "calls": 2, "tokens_in": 17520, "tokens_out": 3934, "ctx_chars": 10384, "t_end": 1791527201.2372794, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9687, "lo95": 0.9686, "mean": 0.9719, "ev_only": 0.9688, "ref_ms": 3.62352, "cand_ms": 3.74051, "n_trials": 219, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0436, "r_wall_s": 90.69, "compile_s": 3.2, "r_error": "", "src_len": 2343, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7295, "tout": 2818, "ts": 1791527069.5185332, "chk": "ok", "code_len": 2343}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10225, "tout": 1116, "ts": 1791527110.3171937, "chk": null, "code_len": 2343}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7295, "started": 1791527042.1159182}
{"ep": "h1-00021", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0342, "speedup": 1.0342, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 165.8, "calls": 2, "tokens_in": 12965, "tokens_out": 5345, "ctx_chars": 8449, "t_end": 1791527207.952184, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0342, "lo95": 1.0338, "mean": 1.0707, "ev_only": 1.0323, "ref_ms": 8.2474, "cand_ms": 7.97479, "n_trials": 168, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0091, "r_wall_s": 76.57, "compile_s": 1.89, "r_error": "", "src_len": 3637, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5359, "tout": 3552, "ts": 1791527073.5041761, "chk": "ok", "code_len": 3637}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7606, "tout": 1793, "ts": 1791527131.2973042, "chk": null, "code_len": 3637}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5359, "started": 1791527042.1208928}
{"ep": "h1-00028", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.381, "speedup": 1.381, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 170.0, "calls": 2, "tokens_in": 14537, "tokens_out": 5156, "ctx_chars": 10384, "t_end": 1791527212.1049316, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.381, "lo95": 1.3695, "mean": 1.3667, "ev_only": 1.3826, "ref_ms": 2.89712, "cand_ms": 2.09791, "n_trials": 206, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 62.08, "compile_s": 1.91, "r_error": "", "src_len": 2888, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6193, "tout": 3264, "ts": 1791527071.5272686, "chk": "ok", "code_len": 2888}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8344, "tout": 1892, "ts": 1791527149.9187372, "chk": null, "code_len": 2888}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6193, "started": 1791527042.125112}
{"ep": "h1-00041", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.6908, "speedup": 1.6908, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 173.7, "calls": 2, "tokens_in": 6432, "tokens_out": 6048, "ctx_chars": 0, "t_end": 1791527215.7922778, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.6908, "lo95": 1.6903, "mean": 1.6931, "ev_only": 1.6918, "ref_ms": 28.99472, "cand_ms": 17.14827, "n_trials": 52, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0435, "r_wall_s": 96.22, "compile_s": 12.24, "r_error": "", "src_len": 4275, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1902, "tout": 4040, "ts": 1791527079.0853071, "chk": "ok", "code_len": 4361}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4530, "tout": 2008, "ts": 1791527119.3498585, "chk": null, "code_len": 4275}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1902, "started": 1791527042.128725}
{"ep": "h1-00031", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.014, "speedup": 1.014, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 177.7, "calls": 2, "tokens_in": 10667, "tokens_out": 12656, "ctx_chars": 0, "t_end": 1791527219.829146, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.014, "lo95": 0.9962, "mean": 1.0124, "ev_only": 1.0129, "ref_ms": 16.3082, "cand_ms": 16.08281, "n_trials": 64, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1168, "r_wall_s": 35.94, "compile_s": 2.13, "r_error": "", "src_len": 8434, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 8595, "ts": 1791527117.0063508, "chk": "ok", "code_len": 8522}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7643, "tout": 4061, "ts": 1791527183.7864, "chk": null, "code_len": 8434}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791527042.1256223}
{"ep": "h1-00007", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.153, "speedup": 2.153, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 180.7, "calls": 2, "tokens_in": 15075, "tokens_out": 2224, "ctx_chars": 11175, "t_end": 1791527222.7952354, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.153, "lo95": 2.1504, "mean": 2.1217, "ev_only": 2.1594, "ref_ms": 43.96973, "cand_ms": 20.42248, "n_trials": 31, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 131.32, "compile_s": 1.98, "r_error": "", "src_len": 2274, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6888, "tout": 1187, "ts": 1791527052.8791177, "chk": "ok", "code_len": 2274}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8187, "tout": 1037, "ts": 1791527090.6250117, "chk": null, "code_len": 2274}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6888, "started": 1791527042.1136136}
{"ep": "h1-00059", "task": "L1_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 194.2, "calls": 1, "tokens_in": 1562, "tokens_out": 831, "ctx_chars": 0, "t_end": 1791527236.3231268, "error": "RuntimeError: Error building extension 'gelu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 49.05, "compile_s": 49.04, "r_error": "RuntimeError: Error building extension 'gelu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "src_len": 1719, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1562, "tout": 831, "ts": 1791527051.2613444, "chk": null, "code_len": 1719}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1562, "started": 1791527042.136603}
{"ep": "h1-00057", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0896, "speedup": 1.0896, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 194.5, "calls": 2, "tokens_in": 5181, "tokens_out": 5657, "ctx_chars": 0, "t_end": 1791527236.6201584, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0896, "lo95": 1.0886, "mean": 1.0897, "ev_only": 1.0892, "ref_ms": 72.86257, "cand_ms": 66.87342, "n_trials": 22, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0092, "r_wall_s": 106.74, "compile_s": 2.36, "r_error": "", "src_len": 2226, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1699, "tout": 4511, "ts": 1791527086.4986982, "chk": "ok", "code_len": 2274}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3482, "tout": 1146, "ts": 1791527129.855572, "chk": null, "code_len": 2226}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1699, "started": 1791527042.1355822}
{"ep": "h1-00073", "task": "L1_014", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.0029, "speedup": 4.0029, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.7, "calls": 1, "tokens_in": 5875, "tokens_out": 1190, "ctx_chars": 9311, "t_end": 1791527247.1309817, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.0029, "lo95": 3.9802, "mean": 4.0245, "ev_only": 4.0629, "ref_ms": 7.37329, "cand_ms": 1.84199, "n_trials": 220, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9798, "r_wall_s": 95.39, "compile_s": 1.97, "r_error": "", "src_len": 1941, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5875, "tout": 1190, "ts": 1791527151.6154914, "chk": null, "code_len": 1941}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5875, "started": 1791527130.4629886}
{"ep": "h1-00029", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2411, "speedup": 1.2411, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 221.9, "calls": 2, "tokens_in": 10682, "tokens_out": 4797, "ctx_chars": 6513, "t_end": 1791527263.9868164, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2411, "lo95": 1.2398, "mean": 1.2616, "ev_only": 1.2423, "ref_ms": 33.7825, "cand_ms": 27.22013, "n_trials": 22, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 103.3, "compile_s": 2.02, "r_error": "", "src_len": 2623, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4418, "tout": 3396, "ts": 1791527072.7970278, "chk": "ok", "code_len": 2623}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6264, "tout": 1401, "ts": 1791527160.6500955, "chk": null, "code_len": 2623}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4418, "started": 1791527042.1251996}
{"ep": "h1-00000", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8746, "speedup": 0.8746, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 223.3, "calls": 2, "tokens_in": 5712, "tokens_out": 6445, "ctx_chars": 0, "t_end": 1791527265.3766525, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8746, "lo95": 0.8737, "mean": 0.8765, "ev_only": 0.8738, "ref_ms": 10.7313, "cand_ms": 12.27058, "n_trials": 45, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 104.77, "compile_s": 2.17, "r_error": "", "src_len": 3378, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1686, "tout": 4640, "ts": 1791527103.0682669, "chk": "ok", "code_len": 3412}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4026, "tout": 1805, "ts": 1791527160.5720694, "chk": null, "code_len": 3378}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1686, "started": 1791527062.4673953}
{"ep": "h1-00017", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0186, "speedup": 1.0186, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 223.5, "calls": 2, "tokens_in": 6167, "tokens_out": 4725, "ctx_chars": 0, "t_end": 1791527265.587712, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0186, "lo95": 1.0184, "mean": 1.0151, "ev_only": 1.0204, "ref_ms": 2.35328, "cand_ms": 2.3104, "n_trials": 185, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 125.87, "compile_s": 12.34, "r_error": "", "src_len": 3613, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1921, "tout": 2849, "ts": 1791527067.8430974, "chk": "ok", "code_len": 3613}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4246, "tout": 1876, "ts": 1791527138.859541, "chk": null, "code_len": 3613}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1921, "started": 1791527042.1194813}
{"ep": "h1-00085", "task": "L2_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 82.3, "calls": 1, "tokens_in": 1727, "tokens_out": 1334, "ctx_chars": 0, "t_end": 1791527268.906217, "error": "RuntimeError: Error building extension 'fuse_046': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_046 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 53.65, "compile_s": 53.64, "r_error": "RuntimeError: Error building extension 'fuse_046': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_046 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "src_len": 2834, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1727, "tout": 1334, "ts": 1791527215.1507914, "chk": null, "code_len": 2834}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1727, "started": 1791527186.6449444}
{"ep": "h1-00052", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7237, "speedup": 0.7237, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 228.2, "calls": 2, "tokens_in": 18518, "tokens_out": 21773, "ctx_chars": 6513, "t_end": 1791527270.3255537, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7237, "lo95": 0.7054, "mean": 0.795, "ev_only": 0.7236, "ref_ms": 40.13139, "cand_ms": 55.45095, "n_trials": 38, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.059, "r_wall_s": 31.1, "compile_s": 1.98, "r_error": "", "src_len": 13175, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 15330, "ts": 1791527174.0426702, "chk": "ok", "code_len": 13175}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12791, "tout": 6443, "ts": 1791527239.1601427, "chk": null, "code_len": 13175}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791527042.1338773}
{"ep": "h1-00011", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 8.1271, "speedup": 8.1271, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 228.3, "calls": 3, "tokens_in": 17878, "tokens_out": 13580, "ctx_chars": 0, "t_end": 1791527270.4505863, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 8.1271, "lo95": 8.1143, "mean": 8.0648, "ev_only": 8.1253, "ref_ms": 12.04747, "cand_ms": 1.48238, "n_trials": 141, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8007, "r_wall_s": 30.2, "compile_s": 12.14, "r_error": "", "src_len": 5632, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2677, "tout": 5244, "ts": 1791527089.9851656, "chk": "incorrect", "code_len": 5541}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6012, "tout": 5344, "ts": 1791527160.491976, "chk": "ok", "code_len": 5632}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9189, "tout": 2992, "ts": 1791527239.9502704, "chk": null, "code_len": 5632}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2677, "started": 1791527042.1172516}
{"ep": "h1-00065", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0077, "speedup": 1.0077, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.1, "calls": 2, "tokens_in": 7477, "tokens_out": 8915, "ctx_chars": 0, "t_end": 1791527278.9703603, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0077, "lo95": 1.0069, "mean": 1.0086, "ev_only": 1.0125, "ref_ms": 8.10104, "cand_ms": 8.03928, "n_trials": 126, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0079, "r_wall_s": 77.55, "compile_s": 12.94, "r_error": "", "src_len": 6951, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1771, "tout": 5540, "ts": 1791527137.3983917, "chk": "ok", "code_len": 6973}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5706, "tout": 3375, "ts": 1791527201.2376356, "chk": null, "code_len": 6951}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1771, "started": 1791527091.8666992}
{"ep": "h1-00093", "task": "L2_095", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 64.3, "calls": 1, "tokens_in": 1668, "tokens_out": 884, "ctx_chars": 0, "t_end": 1791527280.068269, "error": "RuntimeError: Error building extension 'fused_act_m095': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_m095 -DTORCH_API_INCLUDE_EXTENSION_H -I/us", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 55.2, "compile_s": 55.19, "r_error": "RuntimeError: Error building extension 'fused_act_m095': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_m095 -DTORCH_API_INCLUDE_EXTENSION_H -I/us", "src_len": 1764, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1668, "tout": 884, "ts": 1791527224.7635658, "chk": null, "code_len": 1764}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1668, "started": 1791527215.7925043}
{"ep": "h1-00081", "task": "L3_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0, "speedup": 1.0, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.9, "calls": 3, "tokens_in": 15325, "tokens_out": 1752, "ctx_chars": 6513, "t_end": 1791527302.0091608, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0, "lo95": 0.9993, "mean": 1.0254, "ev_only": 0.9992, "ref_ms": 10.72403, "cand_ms": 10.72402, "n_trials": 99, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0018, "r_wall_s": 28.91, "compile_s": 2.11, "r_error": "", "src_len": 1730, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4387, "tout": 931, "ts": 1791527168.7650087, "chk": "ok", "code_len": 1766}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5427, "tout": 60, "ts": 1791527266.3731616, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5511, "tout": 761, "ts": 1791527273.0493448, "chk": null, "code_len": 1730}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4387, "started": 1791527159.111751}
{"ep": "h1-00038", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1136, "speedup": 1.1136, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.5, "calls": 2, "tokens_in": 14371, "tokens_out": 2151, "ctx_chars": 11296, "t_end": 1791527303.6359143, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1136, "lo95": 1.1123, "mean": 1.1325, "ev_only": 1.1135, "ref_ms": 31.44692, "cand_ms": 28.23887, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0517, "r_wall_s": 212.95, "compile_s": 1.98, "r_error": "", "src_len": 1235, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6639, "tout": 1490, "ts": 1791527056.9984715, "chk": "ok", "code_len": 1235}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7732, "tout": 661, "ts": 1791527090.6236792, "chk": null, "code_len": 1235}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6639, "started": 1791527042.1275642}
{"ep": "h1-00064", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0826, "speedup": 1.0826, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.1, "calls": 3, "tokens_in": 25685, "tokens_out": 8091, "ctx_chars": 11023, "t_end": 1791527304.5733635, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0826, "lo95": 1.0816, "mean": 1.0849, "ev_only": 1.084, "ref_ms": 12.91845, "cand_ms": 11.93233, "n_trials": 88, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9994, "r_wall_s": 50.97, "compile_s": 2.02, "r_error": "", "src_len": 2853, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6480, "tout": 4594, "ts": 1791527132.4622254, "chk": "runtime_error", "code_len": 2846}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8704, "tout": 1915, "ts": 1791527209.281106, "chk": "ok", "code_len": 2853}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10501, "tout": 1582, "ts": 1791527253.5557702, "chk": null, "code_len": 2853}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 6480, "started": 1791527089.4665506}
{"ep": "h1-00083", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2273, "speedup": 1.2273, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 125.9, "calls": 2, "tokens_in": 4733, "tokens_out": 2353, "ctx_chars": 0, "t_end": 1791527305.7705615, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2273, "lo95": 1.2268, "mean": 1.2271, "ev_only": 1.2261, "ref_ms": 11.96823, "cand_ms": 9.75171, "n_trials": 131, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0689, "r_wall_s": 82.41, "compile_s": 3.14, "r_error": "", "src_len": 1359, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1778, "tout": 1611, "ts": 1791527194.528632, "chk": "ok", "code_len": 1359}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2955, "tout": 742, "ts": 1791527222.4944172, "chk": null, "code_len": 1359}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1778, "started": 1791527179.830399}
{"ep": "h1-00013", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0641, "speedup": 1.0641, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 266.9, "calls": 2, "tokens_in": 5040, "tokens_out": 2871, "ctx_chars": 0, "t_end": 1791527309.0295606, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0641, "lo95": 1.0634, "mean": 1.0656, "ev_only": 1.0641, "ref_ms": 8.44221, "cand_ms": 7.93363, "n_trials": 163, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 234.21, "compile_s": 2.3, "r_error": "", "src_len": 1975, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1791, "tout": 1789, "ts": 1791527058.173812, "chk": "ok", "code_len": 1995}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3249, "tout": 1082, "ts": 1791527074.7213397, "chk": null, "code_len": 1975}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1791, "started": 1791527042.1181152}
{"ep": "h1-00078", "task": "L1_010", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8378, "speedup": 0.8378, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 172.5, "calls": 2, "tokens_in": 4760, "tokens_out": 3470, "ctx_chars": 0, "t_end": 1791527317.0841722, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8378, "lo95": 0.8375, "mean": 0.8375, "ev_only": 0.8371, "ref_ms": 2.8748, "cand_ms": 3.43119, "n_trials": 191, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 119.46, "compile_s": 2.78, "r_error": "", "src_len": 3306, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1587, "tout": 1477, "ts": 1791527157.9270651, "chk": "ok", "code_len": 2443}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3173, "tout": 1993, "ts": 1791527197.1484709, "chk": null, "code_len": 3306}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1587, "started": 1791527144.580148}
{"ep": "h1-00070", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.431, "speedup": 0.431, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 202.0, "calls": 2, "tokens_in": 25400, "tokens_out": 12753, "ctx_chars": 6513, "t_end": 1791527317.0868955, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.431, "lo95": 0.4296, "mean": 0.4756, "ev_only": 0.4312, "ref_ms": 8.53683, "cand_ms": 19.8055, "n_trials": 84, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.7101, "r_wall_s": 87.58, "compile_s": 3.03, "r_error": "", "src_len": 9782, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 10321, "tout": 8535, "ts": 1791527184.7199626, "chk": "ok", "code_len": 9782}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 15079, "tout": 4218, "ts": 1791527229.401875, "chk": null, "code_len": 9782}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 10321, "started": 1791527115.1120794}
{"ep": "h1-00042", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.9737, "speedup": 3.9737, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 277.6, "calls": 2, "tokens_in": 8895, "tokens_out": 20262, "ctx_chars": 0, "t_end": 1791527319.7484741, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.9737, "lo95": 3.964, "mean": 3.9821, "ev_only": 3.9811, "ref_ms": 32.19117, "cand_ms": 8.10102, "n_trials": 29, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9906, "r_wall_s": 57.47, "compile_s": 11.82, "r_error": "", "src_len": 8926, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1966, "tout": 15971, "ts": 1791527186.59811, "chk": "ok", "code_len": 8926}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6929, "tout": 4291, "ts": 1791527262.249366, "chk": null, "code_len": 8926}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1966, "started": 1791527042.13052}
{"ep": "h1-00089", "task": "L3_042", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7935, "speedup": 0.7935, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 126.2, "calls": 2, "tokens_in": 11848, "tokens_out": 1409, "ctx_chars": 8224, "t_end": 1791527325.1016204, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7935, "lo95": 0.7906, "mean": 0.7947, "ev_only": 0.7934, "ref_ms": 60.16243, "cand_ms": 75.82088, "n_trials": 16, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 30.0, "compile_s": 1.98, "r_error": "", "src_len": 915, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5501, "tout": 737, "ts": 1791527207.5013306, "chk": "ok", "code_len": 915}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6347, "tout": 672, "ts": 1791527295.0585632, "chk": null, "code_len": 915}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5501, "started": 1791527198.903812}
{"ep": "h1-00104", "task": "L1_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 67.8, "calls": 1, "tokens_in": 2001, "tokens_out": 1100, "ctx_chars": 0, "t_end": 1791527338.2938557, "error": "RuntimeError: Error building extension 'passmod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=passmod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 54.57, "compile_s": 54.57, "r_error": "RuntimeError: Error building extension 'passmod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=passmod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch", "src_len": 1389, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2001, "tout": 1100, "ts": 1791527283.6984334, "chk": null, "code_len": 1389}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2001, "started": 1791527270.450831}
{"ep": "h1-00102", "task": "L2_059", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0024, "speedup": 1.0024, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 90.3, "calls": 1, "tokens_in": 6426, "tokens_out": 454, "ctx_chars": 10909, "t_end": 1791527359.2546036, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0024, "lo95": 1.002, "mean": 1.0222, "ev_only": 1.0022, "ref_ms": 16.05579, "cand_ms": 16.01691, "n_trials": 65, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0009, "r_wall_s": 85.85, "compile_s": 1.98, "r_error": "", "src_len": 922, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6426, "tout": 454, "ts": 1791527273.3525753, "chk": null, "code_len": 922}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6426, "started": 1791527268.9064753}
{"ep": "h1-00044", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.5434, "speedup": 3.5434, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 319.2, "calls": 4, "tokens_in": 29614, "tokens_out": 17810, "ctx_chars": 0, "t_end": 1791527361.3345096, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 3.5434, "lo95": 3.5362, "mean": 3.5454, "ev_only": 3.6153, "ref_ms": 2.2991, "cand_ms": 0.64884, "n_trials": 190, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8193, "r_wall_s": 59.2, "compile_s": 11.87, "r_error": "", "src_len": 6275, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 7576, "ts": 1791527109.85541, "chk": "no_custom_kernel", "code_len": 6332}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5776, "tout": 3403, "ts": 1791527169.1575992, "chk": "runtime_error", "code_len": 6254}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9243, "tout": 3669, "ts": 1791527245.7000546, "chk": "ok", "code_len": 6275}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 12580, "tout": 3162, "ts": 1791527302.0872672, "chk": null, "code_len": 6275}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "runtime_error", "ok", null], "first_tin": 2015, "started": 1791527042.1301854}
{"ep": "h1-00040", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.3323, "speedup": 3.3323, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 320.8, "calls": 2, "tokens_in": 8370, "tokens_out": 14781, "ctx_chars": 0, "t_end": 1791527362.9363723, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.3323, "lo95": 3.3296, "mean": 3.3369, "ev_only": 3.3792, "ref_ms": 4.73201, "cand_ms": 1.42004, "n_trials": 221, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.996, "r_wall_s": 79.85, "compile_s": 14.94, "r_error": "", "src_len": 7840, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1917, "tout": 11022, "ts": 1791527142.2979536, "chk": "ok", "code_len": 7840}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6453, "tout": 3759, "ts": 1791527283.0199068, "chk": null, "code_len": 7840}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1917, "started": 1791527042.1283126}
{"ep": "h1-00076", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9205, "speedup": 0.9205, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 225.3, "calls": 2, "tokens_in": 5619, "tokens_out": 4826, "ctx_chars": 0, "t_end": 1791527363.3941443, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9205, "lo95": 0.9203, "mean": 0.9206, "ev_only": 0.921, "ref_ms": 15.93701, "cand_ms": 17.31321, "n_trials": 92, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 88.52, "compile_s": 2.12, "r_error": "", "src_len": 2968, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1671, "tout": 3219, "ts": 1791527166.5530202, "chk": "ok", "code_len": 2968}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3948, "tout": 1607, "ts": 1791527274.7210593, "chk": null, "code_len": 2968}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1671, "started": 1791527138.067615}
{"ep": "h1-00030", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.855, "speedup": 0.855, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 325.1, "calls": 2, "tokens_in": 4826, "tokens_out": 4081, "ctx_chars": 0, "t_end": 1791527367.179914, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.855, "lo95": 0.8544, "mean": 0.8751, "ev_only": 0.8565, "ref_ms": 7.71022, "cand_ms": 9.01752, "n_trials": 194, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 266.04, "compile_s": 2.86, "r_error": "", "src_len": 2057, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 2748, "ts": 1791527068.5581038, "chk": "ok", "code_len": 2057}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3261, "tout": 1333, "ts": 1791527101.041028, "chk": null, "code_len": 2057}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791527042.1247447}
{"ep": "h1-00088", "task": "L1_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9631, "speedup": 0.9631, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 176.0, "calls": 3, "tokens_in": 24507, "tokens_out": 2474, "ctx_chars": 11175, "t_end": 1791527372.2272122, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9631, "lo95": 0.9625, "mean": 0.9663, "ev_only": 0.9627, "ref_ms": 4.38249, "cand_ms": 4.55038, "n_trials": 208, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0118, "r_wall_s": 71.08, "compile_s": 2.1, "r_error": "", "src_len": 1917, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7065, "tout": 1477, "ts": 1791527213.2385697, "chk": "ok", "code_len": 1991}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8654, "tout": 110, "ts": 1791527293.218795, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8788, "tout": 887, "ts": 1791527300.9625392, "chk": null, "code_len": 1917}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7065, "started": 1791527196.200109}
{"ep": "h1-00002", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5447, "speedup": 1.5447, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 338.9, "calls": 2, "tokens_in": 5612, "tokens_out": 4552, "ctx_chars": 0, "t_end": 1791527380.9807036, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.5447, "lo95": 1.5428, "mean": 1.5462, "ev_only": 1.5441, "ref_ms": 28.72989, "cand_ms": 18.59892, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0481, "r_wall_s": 168.74, "compile_s": 2.48, "r_error": "", "src_len": 2298, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1902, "tout": 3244, "ts": 1791527072.7535813, "chk": "ok", "code_len": 2366}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3710, "tout": 1308, "ts": 1791527211.589889, "chk": null, "code_len": 2298}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1902, "started": 1791527042.1101284}
{"ep": "h1-00092", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6593, "speedup": 1.6593, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 169.0, "calls": 2, "tokens_in": 8900, "tokens_out": 8266, "ctx_chars": 3355, "t_end": 1791527381.097147, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.6593, "lo95": 1.6587, "mean": 1.6591, "ev_only": 1.6606, "ref_ms": 20.43225, "cand_ms": 12.31413, "n_trials": 73, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 49.44, "compile_s": 1.98, "r_error": "", "src_len": 3475, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3296, "tout": 6390, "ts": 1791527268.4654956, "chk": "ok", "code_len": 3475}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5604, "tout": 1876, "ts": 1791527331.6137745, "chk": null, "code_len": 3475}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3296, "started": 1791527212.1051908}
{"ep": "h1-00099", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1189, "speedup": 1.1189, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.7, "calls": 2, "tokens_in": 5038, "tokens_out": 4536, "ctx_chars": 0, "t_end": 1791527386.7060835, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1189, "lo95": 1.1182, "mean": 1.1223, "ev_only": 1.1201, "ref_ms": 7.51601, "cand_ms": 6.71735, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 54.18, "compile_s": 2.29, "r_error": "", "src_len": 2471, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 3134, "ts": 1791527291.2247531, "chk": "ok", "code_len": 2471}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3471, "tout": 1402, "ts": 1791527332.446398, "chk": null, "code_len": 2471}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791527263.987053}
{"ep": "h1-00075", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.415, "speedup": 3.415, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.0, "calls": 2, "tokens_in": 13190, "tokens_out": 2827, "ctx_chars": 9311, "t_end": 1791527391.1746984, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.415, "lo95": 3.4064, "mean": 3.3965, "ev_only": 3.4357, "ref_ms": 7.39407, "cand_ms": 2.1652, "n_trials": 92, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 57.95, "compile_s": 2.44, "r_error": "", "src_len": 1841, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5877, "tout": 1747, "ts": 1791527157.2143114, "chk": "ok", "code_len": 1841}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7313, "tout": 1080, "ts": 1791527333.1059551, "chk": null, "code_len": 1841}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5877, "started": 1791527133.1724093}
{"ep": "h1-00035", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4729, "speedup": 0.4729, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 360.4, "calls": 2, "tokens_in": 7621, "tokens_out": 11978, "ctx_chars": 0, "t_end": 1791527402.4878361, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.4729, "lo95": 0.4523, "mean": 0.4505, "ev_only": 0.4754, "ref_ms": 3.32447, "cand_ms": 7.03011, "n_trials": 87, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 95.83, "compile_s": 11.22, "r_error": "", "src_len": 6197, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2031, "tout": 8940, "ts": 1791527122.8348002, "chk": "ok", "code_len": 6197}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5590, "tout": 3038, "ts": 1791527305.8555498, "chk": null, "code_len": 6197}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2031, "started": 1791527042.1271958}
{"ep": "h1-00025", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.011, "speedup": 4.011, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 370.3, "calls": 2, "tokens_in": 7599, "tokens_out": 13239, "ctx_chars": 0, "t_end": 1791527412.4336793, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.011, "lo95": 4.0027, "mean": 4.0047, "ev_only": 4.0139, "ref_ms": 79.78242, "cand_ms": 19.89105, "n_trials": 17, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8347, "r_wall_s": 73.73, "compile_s": 12.59, "r_error": "", "src_len": 6366, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1972, "tout": 10081, "ts": 1791527132.006484, "chk": "ok", "code_len": 6366}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5627, "tout": 3158, "ts": 1791527338.6748447, "chk": null, "code_len": 6366}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1972, "started": 1791527042.1246538}
{"ep": "h1-00056", "task": "L1_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.3213, "speedup": 2.3213, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 372.1, "calls": 2, "tokens_in": 6039, "tokens_out": 2854, "ctx_chars": 0, "t_end": 1791527414.2356267, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.3213, "lo95": 2.3136, "mean": 2.3197, "ev_only": 2.3226, "ref_ms": 35.72319, "cand_ms": 15.3894, "n_trials": 38, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 321.6, "compile_s": 1.93, "r_error": "", "src_len": 1735, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1960, "tout": 2007, "ts": 1791527062.6304467, "chk": "ok", "code_len": 1735}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4079, "tout": 847, "ts": 1791527091.8399785, "chk": null, "code_len": 1735}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1960, "started": 1791527042.1345913}
{"ep": "h1-00004", "task": "L2_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1682, "speedup": 1.1682, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 372.6, "calls": 3, "tokens_in": 23506, "tokens_out": 1600, "ctx_chars": 12155, "t_end": 1791527414.7112162, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1682, "lo95": 1.1677, "mean": 1.1678, "ev_only": 1.1668, "ref_ms": 12.14122, "cand_ms": 10.39347, "n_trials": 127, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1501, "r_wall_s": 202.5, "compile_s": 2.43, "r_error": "", "src_len": 1558, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7201, "tout": 821, "ts": 1791527050.6295195, "chk": "ok", "code_len": 1558}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8134, "tout": 13, "ts": 1791527204.0217211, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8171, "tout": 766, "ts": 1791527210.5480525, "chk": null, "code_len": 1558}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7201, "started": 1791527042.1110117}
{"ep": "h1-00037", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6628, "speedup": 0.6628, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 382.9, "calls": 2, "tokens_in": 16363, "tokens_out": 10583, "ctx_chars": 6513, "t_end": 1791527425.0013459, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.6628, "lo95": 0.5257, "mean": 0.6263, "ev_only": 0.6638, "ref_ms": 8.54634, "cand_ms": 12.89397, "n_trials": 77, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4059, "r_wall_s": 278.76, "compile_s": 1.89, "r_error": "", "src_len": 7495, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6068, "tout": 6791, "ts": 1791527101.6866837, "chk": "ok", "code_len": 7495}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10295, "tout": 3792, "ts": 1791527146.1914148, "chk": null, "code_len": 7495}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6068, "started": 1791527042.127786}
{"ep": "h1-00049", "task": "L2_063", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0068, "speedup": 1.0068, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 383.7, "calls": 1, "tokens_in": 1518, "tokens_out": 597, "ctx_chars": 0, "t_end": 1791527425.856834, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0068, "lo95": 1.006, "mean": 1.0064, "ev_only": 1.0056, "ref_ms": 8.00897, "cand_ms": 7.95474, "n_trials": 156, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0051, "r_wall_s": 376.4, "compile_s": 44.0, "r_error": "", "src_len": 1213, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1518, "tout": 597, "ts": 1791527049.3588274, "chk": null, "code_len": 1213}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1518, "started": 1791527042.131244}
{"ep": "h1-00087", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6454, "speedup": 0.6454, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.3, "calls": 2, "tokens_in": 5465, "tokens_out": 11422, "ctx_chars": 0, "t_end": 1791527434.7499397, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.6454, "lo95": 0.645, "mean": 0.6573, "ev_only": 0.6454, "ref_ms": 5.29145, "cand_ms": 8.19935, "n_trials": 195, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 74.32, "compile_s": 11.3, "r_error": "", "src_len": 4436, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1476, "tout": 9304, "ts": 1791527289.8137817, "chk": "ok", "code_len": 4436}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3989, "tout": 2118, "ts": 1791527359.6804519, "chk": null, "code_len": 4436}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1476, "started": 1791527191.416006}
{"ep": "h1-00053", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7711, "speedup": 0.7711, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 392.7, "calls": 3, "tokens_in": 19380, "tokens_out": 19157, "ctx_chars": 0, "t_end": 1791527434.8730774, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7711, "lo95": 0.7683, "mean": 0.7792, "ev_only": 0.7744, "ref_ms": 5.63919, "cand_ms": 7.31341, "n_trials": 186, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.1075, "r_wall_s": 204.19, "compile_s": 17.78, "r_error": "", "src_len": 9743, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 10124, "ts": 1791527133.8645415, "chk": "forbidden", "code_len": 9735}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6590, "tout": 4597, "ts": 1791527172.5104513, "chk": "ok", "code_len": 9743}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11180, "tout": 4436, "ts": 1791527229.813685, "chk": null, "code_len": 9743}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", null], "first_tin": 1610, "started": 1791527042.133168}
{"ep": "h1-00067", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2831, "speedup": 1.2831, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.2, "calls": 2, "tokens_in": 13445, "tokens_out": 2839, "ctx_chars": 9893, "t_end": 1791527448.311043, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2831, "lo95": 1.2821, "mean": 1.2834, "ev_only": 1.282, "ref_ms": 19.70771, "cand_ms": 15.35894, "n_trials": 66, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0406, "r_wall_s": 286.91, "compile_s": 1.91, "r_error": "", "src_len": 1904, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5991, "tout": 1837, "ts": 1791527118.3090436, "chk": "ok", "code_len": 1904}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7454, "tout": 1002, "ts": 1791527160.59036, "chk": null, "code_len": 1904}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5991, "started": 1791527099.0756087}
{"ep": "h1-00111", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6155, "speedup": 1.6155, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.5, "calls": 2, "tokens_in": 16874, "tokens_out": 4991, "ctx_chars": 11886, "t_end": 1791527451.5065563, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.6155, "lo95": 1.6146, "mean": 1.6431, "ev_only": 1.6157, "ref_ms": 4.72163, "cand_ms": 2.92262, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2793, "r_wall_s": 39.77, "compile_s": 2.96, "r_error": "", "src_len": 3856, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7269, "tout": 3041, "ts": 1791527343.898322, "chk": "ok", "code_len": 3856}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9605, "tout": 1950, "ts": 1791527411.6657052, "chk": null, "code_len": 3856}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7269, "started": 1791527309.0298107}
{"ep": "h1-00110", "task": "L2_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0694, "speedup": 1.0694, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.7, "calls": 3, "tokens_in": 26060, "tokens_out": 3934, "ctx_chars": 11062, "t_end": 1791527470.4890723, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0694, "lo95": 1.0672, "mean": 1.0678, "ev_only": 1.0718, "ref_ms": 12.7893, "cand_ms": 11.95932, "n_trials": 130, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.023, "r_wall_s": 107.9, "compile_s": 2.0, "r_error": "", "src_len": 2148, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6693, "tout": 2843, "ts": 1791527340.8694534, "chk": "ok", "code_len": 2148}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9648, "tout": 47, "ts": 1791527353.432512, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9719, "tout": 1044, "ts": 1791527362.562522, "chk": null, "code_len": 2148}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6693, "started": 1791527305.770822}
{"ep": "h1-00118", "task": "L3_043", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "runtime_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 113.6, "calls": 1, "tokens_in": 2406, "tokens_out": 5378, "ctx_chars": 0, "t_end": 1791527474.94218, "error": "OutOfResources: out of resource: shared memory, Required: 180480, Hardware limit: 166912. Reducing block sizes or `num_stages` may help.", "f_status": "runtime_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": null, "r_wall_s": 67.09, "compile_s": 2.05, "r_error": "OutOfResources: out of resource: shared memory, Required: 180480, Hardware limit: 166912. Reducing block sizes or `num_stages` may help.", "src_len": 3369, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2406, "tout": 5378, "ts": 1791527407.764418, "chk": null, "code_len": 3369}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2406, "started": 1791527361.3347383}
{"ep": "h1-00117", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0282, "speedup": 1.0282, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 120.6, "calls": 2, "tokens_in": 4292, "tokens_out": 2008, "ctx_chars": 0, "t_end": 1791527479.8698552, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0282, "lo95": 1.028, "mean": 1.0284, "ev_only": 1.0282, "ref_ms": 30.40228, "cand_ms": 29.56989, "n_trials": 41, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0103, "r_wall_s": 88.88, "compile_s": 2.05, "r_error": "", "src_len": 1103, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1696, "tout": 1393, "ts": 1791527372.5645547, "chk": "ok", "code_len": 1103}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2596, "tout": 615, "ts": 1791527389.7814953, "chk": null, "code_len": 1103}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1696, "started": 1791527359.2548668}
{"ep": "h1-00095", "task": "L2_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5832, "speedup": 0.5832, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 257.1, "calls": 2, "tokens_in": 13427, "tokens_out": 1948, "ctx_chars": 10177, "t_end": 1791527479.8856692, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.5832, "lo95": 0.5822, "mean": 0.6086, "ev_only": 0.5859, "ref_ms": 2.41088, "cand_ms": 4.13423, "n_trials": 217, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4906, "r_wall_s": 65.29, "compile_s": 1.98, "r_error": "", "src_len": 1585, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6103, "tout": 1109, "ts": 1791527233.7344534, "chk": "ok", "code_len": 1630}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7324, "tout": 839, "ts": 1791527414.5349686, "chk": null, "code_len": 1585}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6103, "started": 1791527222.79546}
{"ep": "h1-00069", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5323, "speedup": 0.5323, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 378.3, "calls": 2, "tokens_in": 15708, "tokens_out": 5595, "ctx_chars": 10864, "t_end": 1791527485.6594324, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.5323, "lo95": 0.532, "mean": 0.5324, "ev_only": 0.5321, "ref_ms": 20.2171, "cand_ms": 37.97805, "n_trials": 43, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9999, "r_wall_s": 109.86, "compile_s": 2.03, "r_error": "", "src_len": 3848, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6632, "tout": 3569, "ts": 1791527138.6496518, "chk": "ok", "code_len": 3848}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9076, "tout": 2026, "ts": 1791527375.0256855, "chk": null, "code_len": 3848}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6632, "started": 1791527107.3791475}
{"ep": "h1-00060", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.7193, "speedup": 3.7193, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 444.3, "calls": 2, "tokens_in": 9243, "tokens_out": 17373, "ctx_chars": 0, "t_end": 1791527486.4466548, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.7193, "lo95": 3.7162, "mean": 3.9566, "ev_only": 3.718, "ref_ms": 43.70504, "cand_ms": 11.75082, "n_trials": 29, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0005, "r_wall_s": 253.24, "compile_s": 17.08, "r_error": "", "src_len": 8867, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2039, "tout": 12940, "ts": 1791527158.3387377, "chk": "ok", "code_len": 8920}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7204, "tout": 4433, "ts": 1791527231.4512615, "chk": null, "code_len": 8867}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2039, "started": 1791527042.1373663}
{"ep": "h1-00106", "task": "L2_073", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1556, "speedup": 1.1556, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 214.5, "calls": 2, "tokens_in": 13071, "tokens_out": 2958, "ctx_chars": 9590, "t_end": 1791527494.614382, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1556, "lo95": 1.1553, "mean": 1.1552, "ev_only": 1.1575, "ref_ms": 5.58931, "cand_ms": 4.83655, "n_trials": 217, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.565, "r_wall_s": 136.63, "compile_s": 1.92, "r_error": "", "src_len": 2925, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5715, "tout": 1529, "ts": 1791527299.1671834, "chk": "ok", "code_len": 2987}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7356, "tout": 1429, "ts": 1791527357.1203134, "chk": null, "code_len": 2925}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5715, "started": 1791527280.0684955}
{"ep": "h1-00008", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4223, "speedup": 1.4223, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 454.5, "calls": 2, "tokens_in": 4520, "tokens_out": 2013, "ctx_chars": 0, "t_end": 1791527496.590168, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4223, "lo95": 1.4219, "mean": 1.4202, "ev_only": 1.4249, "ref_ms": 13.9979, "cand_ms": 9.84152, "n_trials": 100, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0824, "r_wall_s": 93.54, "compile_s": 1.9, "r_error": "", "src_len": 1276, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 1348, "ts": 1791527055.6795003, "chk": "ok", "code_len": 1276}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2769, "tout": 665, "ts": 1791527402.2223935, "chk": null, "code_len": 1276}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1751, "started": 1791527042.1146343}
{"ep": "h1-00066", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.6727, "speedup": 3.6727, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 409.0, "calls": 3, "tokens_in": 17187, "tokens_out": 11236, "ctx_chars": 0, "t_end": 1791527504.6346443, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.6727, "lo95": 3.6657, "mean": 3.7447, "ev_only": 3.6744, "ref_ms": 3.73913, "cand_ms": 1.01808, "n_trials": 223, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 141.61, "compile_s": 11.73, "r_error": "", "src_len": 5921, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2325, "tout": 4903, "ts": 1791527134.9662843, "chk": "no_custom_kernel", "code_len": 5844}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5835, "tout": 3294, "ts": 1791527231.4453323, "chk": "ok", "code_len": 5921}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9027, "tout": 3039, "ts": 1791527362.2169163, "chk": null, "code_len": 5921}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2325, "started": 1791527095.6264007}
{"ep": "h1-00005", "task": "L1_010", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9231, "speedup": 0.9231, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 464.1, "calls": 3, "tokens_in": 8790, "tokens_out": 3697, "ctx_chars": 0, "t_end": 1791527506.1643922, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9231, "lo95": 0.9224, "mean": 0.9226, "ev_only": 0.92, "ref_ms": 2.87469, "cand_ms": 3.11419, "n_trials": 220, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 39.74, "compile_s": 4.0, "r_error": "", "src_len": 3097, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1587, "tout": 1887, "ts": 1791527059.6388617, "chk": "ok", "code_len": 3113}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3583, "tout": 13, "ts": 1791527451.839745, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3620, "tout": 1797, "ts": 1791527466.2097375, "chk": null, "code_len": 3097}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1587, "started": 1791527042.1125615}
{"ep": "h1-00036", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0094, "speedup": 1.0094, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 467.1, "calls": 4, "tokens_in": 33871, "tokens_out": 9397, "ctx_chars": 9898, "t_end": 1791527509.2615774, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0094, "lo95": 1.0076, "mean": 1.0079, "ev_only": 1.0091, "ref_ms": 8.0381, "cand_ms": 7.96336, "n_trials": 198, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 83.44, "compile_s": 3.24, "r_error": "", "src_len": 859, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6120, "tout": 2360, "ts": 1791527064.0387218, "chk": "incorrect", "code_len": 1725}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7597, "tout": 2676, "ts": 1791527100.8713431, "chk": "incorrect", "code_len": 2796}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9554, "tout": 3293, "ts": 1791527198.524908, "chk": "ok", "code_len": 859}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10600, "tout": 1068, "ts": 1791527425.7919796, "chk": null, "code_len": 859}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6120, "started": 1791527042.1263278}
{"ep": "h1-00096", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2726, "speedup": 1.2726, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 279.0, "calls": 2, "tokens_in": 13321, "tokens_out": 2813, "ctx_chars": 9835, "t_end": 1791527515.341884, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2726, "lo95": 1.2688, "mean": 1.2719, "ev_only": 1.2729, "ref_ms": 17.58913, "cand_ms": 13.82161, "n_trials": 85, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0611, "r_wall_s": 73.72, "compile_s": 2.07, "r_error": "", "src_len": 1998, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5910, "tout": 1696, "ts": 1791527270.469437, "chk": "ok", "code_len": 1998}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7411, "tout": 1117, "ts": 1791527307.4422872, "chk": null, "code_len": 1998}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5910, "started": 1791527256.6675408}
{"ep": "h1-00033", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 6.4729, "speedup": 6.4729, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 473.7, "calls": 3, "tokens_in": 16957, "tokens_out": 16954, "ctx_chars": 0, "t_end": 1791527515.8220475, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.4729, "lo95": 6.4449, "mean": 6.8313, "ev_only": 6.4751, "ref_ms": 33.49914, "cand_ms": 5.1753, "n_trials": 49, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9866, "r_wall_s": 107.53, "compile_s": 12.3, "r_error": "", "src_len": 6347, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1966, "tout": 10210, "ts": 1791527134.2050257, "chk": "no_custom_kernel", "code_len": 6350}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5802, "tout": 3629, "ts": 1791527222.6150901, "chk": "ok", "code_len": 6347}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9189, "tout": 3115, "ts": 1791527408.248119, "chk": null, "code_len": 6347}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1966, "started": 1791527042.129571}
{"ep": "h1-00077", "task": "L2_003", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2538, "speedup": 1.2538, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 379.6, "calls": 2, "tokens_in": 6044, "tokens_out": 2927, "ctx_chars": 0, "t_end": 1791527521.0287132, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2538, "lo95": 1.25, "mean": 1.253, "ev_only": 1.2539, "ref_ms": 28.90109, "cand_ms": 23.05171, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1822, "r_wall_s": 71.42, "compile_s": 2.84, "r_error": "", "src_len": 1541, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1900, "tout": 2132, "ts": 1791527165.8600597, "chk": "ok", "code_len": 1541}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4144, "tout": 795, "ts": 1791527448.9826539, "chk": null, "code_len": 1541}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1900, "started": 1791527141.4631557}
{"ep": "h1-00123", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3083, "speedup": 1.3083, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 140.1, "calls": 2, "tokens_in": 14212, "tokens_out": 4373, "ctx_chars": 10384, "t_end": 1791527521.038584, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3083, "lo95": 1.3073, "mean": 1.3043, "ev_only": 1.3052, "ref_ms": 7.30537, "cand_ms": 5.58365, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 60.79, "compile_s": 3.9, "r_error": "", "src_len": 2483, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6176, "tout": 2787, "ts": 1791527406.9453614, "chk": "ok", "code_len": 2483}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8036, "tout": 1586, "ts": 1791527459.9566631, "chk": null, "code_len": 2483}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6176, "started": 1791527380.9811459}
{"ep": "h1-00050", "task": "L2_032", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1063, "speedup": 1.1063, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 493.1, "calls": 1, "tokens_in": 1681, "tokens_out": 654, "ctx_chars": 0, "t_end": 1791527535.1847434, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1063, "lo95": 1.1047, "mean": 1.1068, "ev_only": 1.107, "ref_ms": 31.61374, "cand_ms": 28.57612, "n_trials": 40, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0577, "r_wall_s": 216.81, "compile_s": 2.46, "r_error": "", "src_len": 1265, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1681, "tout": 654, "ts": 1791527050.5516472, "chk": null, "code_len": 1265}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1681, "started": 1791527042.131442}
{"ep": "h1-00074", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.8738, "speedup": 1.8738, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 406.4, "calls": 2, "tokens_in": 5997, "tokens_out": 7544, "ctx_chars": 0, "t_end": 1791527537.2212439, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.8738, "lo95": 1.8719, "mean": 1.9149, "ev_only": 1.8761, "ref_ms": 3.64213, "cand_ms": 1.94368, "n_trials": 186, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9983, "r_wall_s": 107.96, "compile_s": 17.92, "r_error": "", "src_len": 4476, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1631, "tout": 5302, "ts": 1791527184.8010814, "chk": "ok", "code_len": 4476}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4366, "tout": 2242, "ts": 1791527428.4691386, "chk": null, "code_len": 4476}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1631, "started": 1791527130.8320143}
{"ep": "h1-00018", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.4284, "speedup": 7.4284, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 498.5, "calls": 3, "tokens_in": 28594, "tokens_out": 24773, "ctx_chars": 8224, "t_end": 1791527540.6611514, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 7.4284, "lo95": 7.3791, "mean": 7.9754, "ev_only": 7.4669, "ref_ms": 31.97456, "cand_ms": 4.30439, "n_trials": 31, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 99.43, "compile_s": 12.81, "r_error": "", "src_len": 7177, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5510, "tout": 17304, "ts": 1791527200.825338, "chk": "no_custom_kernel", "code_len": 7181}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9682, "tout": 3999, "ts": 1791527256.9565506, "chk": "ok", "code_len": 7177}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13402, "tout": 3470, "ts": 1791527307.490978, "chk": null, "code_len": 7177}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5510, "started": 1791527042.1199074}
{"ep": "h1-00084", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4549, "speedup": 1.4549, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 354.9, "calls": 2, "tokens_in": 4621, "tokens_out": 2101, "ctx_chars": 0, "t_end": 1791527540.7839918, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4549, "lo95": 1.4539, "mean": 1.4547, "ev_only": 1.4537, "ref_ms": 14.08655, "cand_ms": 9.68225, "n_trials": 112, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0807, "r_wall_s": 116.36, "compile_s": 2.05, "r_error": "", "src_len": 1273, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 1430, "ts": 1791527203.0981033, "chk": "ok", "code_len": 1273}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2870, "tout": 671, "ts": 1791527423.5576744, "chk": null, "code_len": 1273}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1751, "started": 1791527185.8506806}
{"ep": "h1-00079", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0048, "speedup": 1.0048, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 396.0, "calls": 2, "tokens_in": 3906, "tokens_out": 2070, "ctx_chars": 0, "t_end": 1791527541.3472233, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0048, "lo95": 1.0045, "mean": 1.0304, "ev_only": 1.0052, "ref_ms": 7.98907, "cand_ms": 7.95059, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0025, "r_wall_s": 100.83, "compile_s": 2.48, "r_error": "", "src_len": 863, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1520, "tout": 1499, "ts": 1791527159.617183, "chk": "ok", "code_len": 863}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2386, "tout": 571, "ts": 1791527440.4486425, "chk": null, "code_len": 863}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1520, "started": 1791527145.3185086}
{"ep": "h1-00116", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.6458, "speedup": 3.6458, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 203.2, "calls": 2, "tokens_in": 7279, "tokens_out": 12254, "ctx_chars": 0, "t_end": 1791527541.5244393, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.6458, "lo95": 3.6441, "mean": 3.6427, "ev_only": 3.6439, "ref_ms": 19.45943, "cand_ms": 5.33753, "n_trials": 74, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 48.68, "compile_s": 15.19, "r_error": "", "src_len": 6279, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1782, "tout": 9204, "ts": 1791527419.266369, "chk": "ok", "code_len": 6279}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5497, "tout": 3050, "ts": 1791527492.3073454, "chk": null, "code_len": 6279}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1782, "started": 1791527338.294093}
{"ep": "h1-00082", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.6457, "speedup": 2.6457, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 371.0, "calls": 3, "tokens_in": 30195, "tokens_out": 11039, "ctx_chars": 10384, "t_end": 1791527542.3249938, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.6457, "lo95": 2.6418, "mean": 2.6066, "ev_only": 2.6681, "ref_ms": 3.65121, "cand_ms": 1.38003, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5581, "r_wall_s": 233.52, "compile_s": 1.86, "r_error": "", "src_len": 4367, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 6408, "ts": 1791527259.2440155, "chk": "forbidden", "code_len": 4351}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10243, "tout": 2407, "ts": 1791527277.230962, "chk": "ok", "code_len": 4367}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12655, "tout": 2224, "ts": 1791527308.4918168, "chk": null, "code_len": 4367}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", null], "first_tin": 7297, "started": 1791527191.7222424}
{"ep": "h1-00126", "task": "L2_011", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.6383, "speedup": 3.6383, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 151.6, "calls": 3, "tokens_in": 36763, "tokens_out": 10346, "ctx_chars": 12352, "t_end": 1791527542.8131642, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.6383, "lo95": 3.6334, "mean": 3.5196, "ev_only": 3.6474, "ref_ms": 27.93161, "cand_ms": 7.67712, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2117, "r_wall_s": 44.12, "compile_s": 2.56, "r_error": "", "src_len": 6311, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7392, "tout": 7157, "ts": 1791527450.5886118, "chk": "ok", "code_len": 6311}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 14661, "tout": 25, "ts": 1791527473.3787487, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14710, "tout": 3164, "ts": 1791527498.4396555, "chk": null, "code_len": 6311}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7392, "started": 1791527391.1749725}
{"ep": "h1-00127", "task": "L2_011", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.0385, "speedup": 4.0385, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 154.2, "calls": 2, "tokens_in": 19859, "tokens_out": 7010, "ctx_chars": 12352, "t_end": 1791527556.6728501, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.0385, "lo95": 4.0344, "mean": 4.0258, "ev_only": 4.0421, "ref_ms": 27.87702, "cand_ms": 6.90285, "n_trials": 55, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.076, "r_wall_s": 76.97, "compile_s": 3.3, "r_error": "", "src_len": 3973, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7392, "tout": 4963, "ts": 1791527445.546498, "chk": "ok", "code_len": 3973}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12467, "tout": 2047, "ts": 1791527479.3981245, "chk": null, "code_len": 3973}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7392, "started": 1791527402.4880717}
{"ep": "h1-00091", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.8703, "speedup": 3.8703, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.3, "calls": 4, "tokens_in": 27650, "tokens_out": 18163, "ctx_chars": 0, "t_end": 1791527557.210273, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.8703, "lo95": 3.8675, "mean": 3.8604, "ev_only": 3.8886, "ref_ms": 11.9623, "cand_ms": 3.0908, "n_trials": 114, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.092, "r_wall_s": 124.18, "compile_s": 15.4, "r_error": "", "src_len": 3956, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2677, "tout": 5376, "ts": 1791527255.9203284, "chk": "incorrect", "code_len": 4507}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5552, "tout": 4530, "ts": 1791527318.1076143, "chk": "incorrect", "code_len": 4798}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8357, "tout": 6228, "ts": 1791527393.5242803, "chk": "ok", "code_len": 4146}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11064, "tout": 2029, "ts": 1791527432.90678, "chk": null, "code_len": 3956}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2677, "started": 1791527207.9524202}
{"ep": "h1-00122", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9345, "speedup": 0.9345, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.8, "calls": 2, "tokens_in": 7771, "tokens_out": 7067, "ctx_chars": 0, "t_end": 1791527560.0388277, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9345, "lo95": 0.9343, "mean": 0.9345, "ev_only": 0.9346, "ref_ms": 30.76675, "cand_ms": 32.92369, "n_trials": 40, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.5097, "r_wall_s": 95.63, "compile_s": 4.07, "r_error": "", "src_len": 4386, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2408, "tout": 4654, "ts": 1791527414.2479434, "chk": "ok", "code_len": 4386}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5363, "tout": 2413, "ts": 1791527463.6832736, "chk": null, "code_len": 4386}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2408, "started": 1791527372.2274582}
{"ep": "h1-00027", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7294, "speedup": 0.7294, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 518.0, "calls": 2, "tokens_in": 15943, "tokens_out": 6194, "ctx_chars": 10864, "t_end": 1791527560.1628127, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7294, "lo95": 0.7262, "mean": 0.7275, "ev_only": 0.7293, "ref_ms": 20.27587, "cand_ms": 27.79714, "n_trials": 47, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 245.35, "compile_s": 1.89, "r_error": "", "src_len": 4087, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6632, "tout": 4043, "ts": 1791527076.8216994, "chk": "ok", "code_len": 4087}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9311, "tout": 2151, "ts": 1791527313.9251645, "chk": null, "code_len": 4087}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6632, "started": 1791527042.123325}
{"ep": "h1-00130", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.0411, "speedup": 4.0411, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 145.8, "calls": 2, "tokens_in": 13241, "tokens_out": 2932, "ctx_chars": 9311, "t_end": 1791527560.4703455, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.0411, "lo95": 4.0093, "mean": 4.0308, "ev_only": 4.0503, "ref_ms": 7.42314, "cand_ms": 1.8369, "n_trials": 211, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 75.71, "compile_s": 3.27, "r_error": "", "src_len": 1880, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5877, "tout": 1778, "ts": 1791527429.4928713, "chk": "ok", "code_len": 1880}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7364, "tout": 1154, "ts": 1791527484.3944817, "chk": null, "code_len": 1880}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5877, "started": 1791527414.7115521}
{"ep": "h1-00101", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3515, "speedup": 1.3515, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 299.2, "calls": 2, "tokens_in": 14030, "tokens_out": 3941, "ctx_chars": 10384, "t_end": 1791527564.809552, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3515, "lo95": 1.3505, "mean": 1.3442, "ev_only": 1.3531, "ref_ms": 7.34322, "cand_ms": 5.43343, "n_trials": 214, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 235.04, "compile_s": 1.95, "r_error": "", "src_len": 2332, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6176, "tout": 2590, "ts": 1791527288.2837825, "chk": "ok", "code_len": 2332}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7854, "tout": 1351, "ts": 1791527329.5942914, "chk": null, "code_len": 2332}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6176, "started": 1791527265.5880346}
{"ep": "h1-00071", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 13.2283, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 451.0, "calls": 2, "tokens_in": 16010, "tokens_out": 7546, "ctx_chars": 11393, "t_end": 1791527568.4253218, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 13.2283, "lo95": 13.1926, "mean": 13.1669, "ev_only": 13.2637, "ref_ms": 25.12238, "cand_ms": 1.89913, "n_trials": 63, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 222.63, "compile_s": 2.1, "r_error": "", "src_len": 3203, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6822, "tout": 5777, "ts": 1791527169.883701, "chk": "ok", "code_len": 3203}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9188, "tout": 1769, "ts": 1791527345.6110597, "chk": null, "code_len": 3203}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6822, "started": 1791527117.421708}
{"ep": "h1-00121", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3507, "speedup": 1.3507, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 207.7, "calls": 2, "tokens_in": 12767, "tokens_out": 4403, "ctx_chars": 9033, "t_end": 1791527574.9129317, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3507, "lo95": 1.3502, "mean": 1.3505, "ev_only": 1.3489, "ref_ms": 7.51623, "cand_ms": 5.56468, "n_trials": 174, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 90.19, "compile_s": 3.37, "r_error": "", "src_len": 2271, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 3123, "ts": 1791527412.2358086, "chk": "ok", "code_len": 2318}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7277, "tout": 1280, "ts": 1791527484.4141798, "chk": null, "code_len": 2271}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791527367.1801538}
{"ep": "h1-00114", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 30.6509, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.5, "calls": 3, "tokens_in": 22329, "tokens_out": 11563, "ctx_chars": 6034, "t_end": 1791527575.2985039, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 30.6509, "lo95": 28.7672, "mean": 33.3072, "ev_only": 31.6256, "ref_ms": 28.725, "cand_ms": 0.93717, "n_trials": 62, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.8316, "r_wall_s": 118.24, "compile_s": 20.43, "r_error": "", "src_len": 4881, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 6643, "ts": 1791527377.763917, "chk": "no_custom_kernel", "code_len": 5002}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7630, "tout": 2549, "ts": 1791527412.0301654, "chk": "ok", "code_len": 4881}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10151, "tout": 2371, "ts": 1791527456.9506102, "chk": null, "code_len": 4881}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 4548, "started": 1791527319.7487073}
{"ep": "h1-00100", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.1168, "speedup": 4.1168, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 324.5, "calls": 3, "tokens_in": 16959, "tokens_out": 15652, "ctx_chars": 0, "t_end": 1791527589.8429768, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.1168, "lo95": 3.4761, "mean": 4.0107, "ev_only": 4.1319, "ref_ms": 85.57963, "cand_ms": 20.78765, "n_trials": 17, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8749, "r_wall_s": 96.88, "compile_s": 16.83, "r_error": "", "src_len": 6470, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1959, "tout": 8847, "ts": 1791527344.7463942, "chk": "no_custom_kernel", "code_len": 6547}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5795, "tout": 3589, "ts": 1791527445.8800159, "chk": "ok", "code_len": 6470}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9205, "tout": 3216, "ts": 1791527492.915098, "chk": null, "code_len": 6470}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1959, "started": 1791527265.3770826}
{"ep": "h1-00138", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0117, "speedup": 1.0117, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 118.5, "calls": 2, "tokens_in": 13669, "tokens_out": 1442, "ctx_chars": 10749, "t_end": 1791527593.486371, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0117, "lo95": 1.0113, "mean": 1.0115, "ev_only": 1.0121, "ref_ms": 15.9126, "cand_ms": 15.72843, "n_trials": 80, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 59.93, "compile_s": 3.69, "r_error": "", "src_len": 1128, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6387, "tout": 786, "ts": 1791527482.7168353, "chk": "ok", "code_len": 1128}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7282, "tout": 656, "ts": 1791527533.4062047, "chk": null, "code_len": 1128}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6387, "started": 1791527474.942433}
{"ep": "h1-00125", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 13.7145, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 208.1, "calls": 2, "tokens_in": 16035, "tokens_out": 7102, "ctx_chars": 11393, "t_end": 1791527594.7633314, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 13.7145, "lo95": 13.6743, "mean": 13.6346, "ev_only": 13.8315, "ref_ms": 25.04637, "cand_ms": 1.82627, "n_trials": 63, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 108.9, "compile_s": 3.23, "r_error": "", "src_len": 3425, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6822, "tout": 5246, "ts": 1791527433.3261921, "chk": "ok", "code_len": 3425}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9213, "tout": 1856, "ts": 1791527485.6611328, "chk": null, "code_len": 3425}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6822, "started": 1791527386.7063153}
{"ep": "h1-00086", "task": "L1_017", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6592, "speedup": 0.6592, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 408.8, "calls": 2, "tokens_in": 12912, "tokens_out": 3223, "ctx_chars": 9033, "t_end": 1791527597.8315198, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6592, "lo95": 0.6588, "mean": 0.6936, "ev_only": 0.6585, "ref_ms": 7.76994, "cand_ms": 11.78739, "n_trials": 142, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 267.63, "compile_s": 2.01, "r_error": "", "src_len": 2542, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 1831, "ts": 1791527216.5970967, "chk": "ok", "code_len": 2542}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7426, "tout": 1392, "ts": 1791527330.1256008, "chk": null, "code_len": 2542}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5486, "started": 1791527188.9960246}
{"ep": "h1-00109", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0688, "speedup": 1.0688, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 296.9, "calls": 2, "tokens_in": 12042, "tokens_out": 2026, "ctx_chars": 8462, "t_end": 1791527601.429071, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0688, "lo95": 1.0683, "mean": 1.0724, "ev_only": 1.0668, "ref_ms": 8.55203, "cand_ms": 8.00157, "n_trials": 133, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 18.86, "compile_s": 2.23, "r_error": "", "src_len": 1555, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1126, "ts": 1791527331.3811684, "chk": "ok", "code_len": 1555}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6640, "tout": 900, "ts": 1791527582.4719691, "chk": null, "code_len": 1555}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791527304.5735905}
{"ep": "h1-00019", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4229, "speedup": 1.4229, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 561.6, "calls": 2, "tokens_in": 14230, "tokens_out": 4376, "ctx_chars": 10384, "t_end": 1791527603.6859274, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4229, "lo95": 1.4221, "mean": 1.4258, "ev_only": 1.4205, "ref_ms": 7.33136, "cand_ms": 5.15226, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 245.52, "compile_s": 1.91, "r_error": "", "src_len": 2487, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6176, "tout": 2974, "ts": 1791527069.9955776, "chk": "ok", "code_len": 2487}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8054, "tout": 1402, "ts": 1791527358.0182917, "chk": null, "code_len": 2487}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6176, "started": 1791527042.1201859}
{"ep": "h1-00112", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9422, "speedup": 1.9422, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 288.5, "calls": 2, "tokens_in": 8886, "tokens_out": 4568, "ctx_chars": 2425, "t_end": 1791527605.6294515, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.9422, "lo95": 1.9408, "mean": 1.9895, "ev_only": 1.9451, "ref_ms": 12.64247, "cand_ms": 6.50923, "n_trials": 125, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5199, "r_wall_s": 37.69, "compile_s": 1.9, "r_error": "", "src_len": 2865, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3400, "tout": 3048, "ts": 1791527344.859142, "chk": "ok", "code_len": 2865}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5486, "tout": 1520, "ts": 1791527567.8400118, "chk": null, "code_len": 2865}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3400, "started": 1791527317.0843885}
{"ep": "h1-00132", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.109, "speedup": 1.109, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.4, "calls": 2, "tokens_in": 14405, "tokens_out": 2202, "ctx_chars": 11296, "t_end": 1791527608.2454782, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.109, "lo95": 1.1067, "mean": 1.1094, "ev_only": 1.1092, "ref_ms": 31.53556, "cand_ms": 28.43622, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0583, "r_wall_s": 35.96, "compile_s": 1.89, "r_error": "", "src_len": 1281, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6639, "tout": 1479, "ts": 1791527439.952312, "chk": "ok", "code_len": 1281}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7766, "tout": 723, "ts": 1791527572.2252479, "chk": null, "code_len": 1281}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6639, "started": 1791527425.8570874}
{"ep": "h1-00166", "task": "L2_032", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1119, "speedup": 1.1119, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 54.4, "calls": 1, "tokens_in": 1681, "tokens_out": 734, "ctx_chars": 0, "t_end": 1791527622.871124, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1119, "lo95": 1.1106, "mean": 1.112, "ev_only": 1.1117, "ref_ms": 31.40984, "cand_ms": 28.24957, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0471, "r_wall_s": 46.35, "compile_s": 2.1, "r_error": "", "src_len": 1363, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1681, "tout": 734, "ts": 1791527576.4750988, "chk": null, "code_len": 1363}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1681, "started": 1791527568.4255672}
{"ep": "h1-00140", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2719, "speedup": 1.2719, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 143.5, "calls": 2, "tokens_in": 13406, "tokens_out": 2645, "ctx_chars": 9835, "t_end": 1791527623.3526218, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2719, "lo95": 1.266, "mean": 1.2718, "ev_only": 1.2691, "ref_ms": 17.63187, "cand_ms": 13.86255, "n_trials": 47, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0492, "r_wall_s": 103.38, "compile_s": 2.64, "r_error": "", "src_len": 2014, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5910, "tout": 1474, "ts": 1791527492.0698225, "chk": "ok", "code_len": 2014}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7496, "tout": 1171, "ts": 1791527519.4088073, "chk": null, "code_len": 2014}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5910, "started": 1791527479.8858979}
{"ep": "h1-00094", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.934, "speedup": 2.934, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 404.5, "calls": 3, "tokens_in": 13155, "tokens_out": 9576, "ctx_chars": 0, "t_end": 1791527624.2887084, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.934, "lo95": 2.9155, "mean": 2.9085, "ev_only": 2.9356, "ref_ms": 2.4003, "cand_ms": 0.81811, "n_trials": 180, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 47.49, "compile_s": 13.44, "r_error": "", "src_len": 4661, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 4707, "ts": 1791527259.1559396, "chk": "no_custom_kernel", "code_len": 4683}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4467, "tout": 2519, "ts": 1791527307.0400577, "chk": "ok", "code_len": 4661}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6937, "tout": 2350, "ts": 1791527576.756079, "chk": null, "code_len": 4661}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1751, "started": 1791527219.8293707}
{"ep": "h1-00135", "task": "L2_073", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0042, "speedup": 1.0042, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 177.1, "calls": 3, "tokens_in": 20584, "tokens_out": 3086, "ctx_chars": 9590, "t_end": 1791527625.4060016, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0042, "lo95": 1.0034, "mean": 1.0038, "ev_only": 1.0022, "ref_ms": 5.60512, "cand_ms": 5.58182, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.6191, "r_wall_s": 108.56, "compile_s": 2.7, "r_error": "", "src_len": 3033, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5715, "tout": 1585, "ts": 1791527462.985682, "chk": "ok", "code_len": 3068}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7410, "tout": 25, "ts": 1791527503.8479993, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7459, "tout": 1476, "ts": 1791527516.0099368, "chk": null, "code_len": 3033}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5715, "started": 1791527448.3113005}
{"ep": "h1-00103", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.758, "speedup": 3.758, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 355.5, "calls": 3, "tokens_in": 16654, "tokens_out": 16408, "ctx_chars": 0, "t_end": 1791527625.8425438, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.758, "lo95": 3.6982, "mean": 4.1037, "ev_only": 3.7558, "ref_ms": 60.61342, "cand_ms": 16.12906, "n_trials": 15, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8432, "r_wall_s": 83.23, "compile_s": 19.24, "r_error": "", "src_len": 6438, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1959, "tout": 9630, "ts": 1791527354.9000592, "chk": "no_custom_kernel", "code_len": 6523}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5662, "tout": 3541, "ts": 1791527420.970484, "chk": "ok", "code_len": 6438}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9033, "tout": 3237, "ts": 1791527542.5713315, "chk": null, "code_len": 6438}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1959, "started": 1791527270.325845}
{"ep": "h1-00115", "task": "L1_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.1694, "speedup": 0.1694, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 302.5, "calls": 1, "tokens_in": 1474, "tokens_out": 1832, "ctx_chars": 0, "t_end": 1791527627.6129878, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.1694, "lo95": 0.1691, "mean": 0.1701, "ev_only": 0.169, "ref_ms": 5.33612, "cand_ms": 31.50697, "n_trials": 37, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 284.57, "compile_s": 11.15, "r_error": "", "src_len": 3547, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1474, "tout": 1832, "ts": 1791527342.435147, "chk": null, "code_len": 3547}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1474, "started": 1791527325.1018627}
{"ep": "h1-00090", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.025, "speedup": 2.025, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 427.6, "calls": 3, "tokens_in": 14226, "tokens_out": 12535, "ctx_chars": 0, "t_end": 1791527628.8654342, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.025, "lo95": 2.0242, "mean": 2.0249, "ev_only": 2.0266, "ref_ms": 19.13765, "cand_ms": 9.45057, "n_trials": 80, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 49.8, "compile_s": 13.32, "r_error": "", "src_len": 5341, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1586, "tout": 6551, "ts": 1791527258.0986564, "chk": "no_custom_kernel", "code_len": 5345}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4810, "tout": 3294, "ts": 1791527342.764443, "chk": "ok", "code_len": 5341}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7830, "tout": 2690, "ts": 1791527578.989572, "chk": null, "code_len": 5341}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1586, "started": 1791527201.2381217}
{"ep": "h1-00108", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 48.9781, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 326.8, "calls": 3, "tokens_in": 20063, "tokens_out": 19589, "ctx_chars": 0, "t_end": 1791527630.3915539, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 48.9781, "lo95": 44.0685, "mean": 45.0871, "ev_only": 49.1708, "ref_ms": 36.34427, "cand_ms": 0.74205, "n_trials": 44, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9466, "r_wall_s": 47.16, "compile_s": 13.29, "r_error": "", "src_len": 9199, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1765, "tout": 10599, "ts": 1791527413.222753, "chk": "no_custom_kernel", "code_len": 9244}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6879, "tout": 4617, "ts": 1791527499.6100986, "chk": "ok", "code_len": 9199}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11419, "tout": 4373, "ts": 1791527583.173507, "chk": null, "code_len": 9199}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1765, "started": 1791527303.6361523}
{"ep": "h1-00128", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2823, "speedup": 1.2823, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 218.7, "calls": 3, "tokens_in": 22063, "tokens_out": 7357, "ctx_chars": 9033, "t_end": 1791527631.1659877, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2823, "lo95": 1.2798, "mean": 1.2809, "ev_only": 1.2857, "ref_ms": 7.96622, "cand_ms": 6.21249, "n_trials": 140, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 110.8, "compile_s": 2.44, "r_error": "", "src_len": 2348, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 4098, "ts": 1791527449.953588, "chk": "incorrect", "code_len": 2439}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7423, "tout": 1905, "ts": 1791527487.6271648, "chk": "ok", "code_len": 2348}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9152, "tout": 1354, "ts": 1791527520.2704566, "chk": null, "code_len": 2348}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5488, "started": 1791527412.4339373}
{"ep": "h1-00162", "task": "L3_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1553, "speedup": 1.1553, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 74.6, "calls": 2, "tokens_in": 11369, "tokens_out": 3774, "ctx_chars": 6513, "t_end": 1791527634.6226745, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1553, "lo95": 1.1536, "mean": 1.1569, "ev_only": 1.153, "ref_ms": 5.27103, "cand_ms": 4.56259, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0726, "r_wall_s": 29.99, "compile_s": 2.14, "r_error": "", "src_len": 3764, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4675, "tout": 1907, "ts": 1791527575.82887, "chk": "ok", "code_len": 3764}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6694, "tout": 1867, "ts": 1791527604.38188, "chk": null, "code_len": 3764}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4675, "started": 1791527560.0390599}
{"ep": "h1-00131", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8746, "speedup": 0.8746, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 221.6, "calls": 2, "tokens_in": 17530, "tokens_out": 18804, "ctx_chars": 6513, "t_end": 1791527646.5824895, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8746, "lo95": 0.8732, "mean": 0.8959, "ev_only": 0.8745, "ref_ms": 15.45336, "cand_ms": 17.66943, "n_trials": 77, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0947, "r_wall_s": 36.27, "compile_s": 1.94, "r_error": "", "src_len": 10892, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 13343, "ts": 1791527561.3746386, "chk": "ok", "code_len": 10892}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11803, "tout": 5461, "ts": 1791527610.2898624, "chk": null, "code_len": 10892}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791527445.3530746}
{"ep": "h1-00098", "task": "L2_003", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2589, "speedup": 1.2589, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 403.0, "calls": 3, "tokens_in": 27102, "tokens_out": 4610, "ctx_chars": 11288, "t_end": 1791527650.1048198, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2589, "lo95": 1.2585, "mean": 1.2594, "ev_only": 1.259, "ref_ms": 29.1045, "cand_ms": 23.11852, "n_trials": 58, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2277, "r_wall_s": 315.34, "compile_s": 1.94, "r_error": "", "src_len": 3186, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6970, "tout": 2959, "ts": 1791527279.3458679, "chk": "ok", "code_len": 3186}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10041, "tout": 26, "ts": 1791527321.1621544, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10091, "tout": 1625, "ts": 1791527334.5436654, "chk": null, "code_len": 3186}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6970, "started": 1791527247.1312182}
{"ep": "h1-00159", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3942, "speedup": 1.3942, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 126.7, "calls": 2, "tokens_in": 14840, "tokens_out": 5258, "ctx_chars": 10508, "t_end": 1791527669.4753668, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3942, "lo95": 1.3813, "mean": 1.4064, "ev_only": 1.4338, "ref_ms": 2.19446, "cand_ms": 1.57395, "n_trials": 199, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1288, "r_wall_s": 66.94, "compile_s": 2.75, "r_error": "", "src_len": 2842, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6405, "tout": 3765, "ts": 1791527576.1110244, "chk": "ok", "code_len": 2842}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8435, "tout": 1493, "ts": 1791527602.5077438, "chk": null, "code_len": 2842}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6405, "started": 1791527542.8133912}
{"ep": "h1-00137", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0138, "speedup": 1.0138, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 202.4, "calls": 2, "tokens_in": 13540, "tokens_out": 1266, "ctx_chars": 10749, "t_end": 1791527672.84813, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0138, "lo95": 1.0132, "mean": 1.0139, "ev_only": 1.013, "ref_ms": 15.91271, "cand_ms": 15.69648, "n_trials": 81, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0056, "r_wall_s": 85.07, "compile_s": 2.69, "r_error": "", "src_len": 1075, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6387, "tout": 657, "ts": 1791527476.3611739, "chk": "ok", "code_len": 1075}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7153, "tout": 609, "ts": 1791527587.6492774, "chk": null, "code_len": 1075}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6387, "started": 1791527470.4893153}
{"ep": "h1-00172", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0123, "speedup": 1.0123, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.9, "calls": 2, "tokens_in": 13731, "tokens_out": 1481, "ctx_chars": 10749, "t_end": 1791527679.7036102, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0123, "lo95": 1.0115, "mean": 1.0161, "ev_only": 1.0129, "ref_ms": 16.06611, "cand_ms": 15.87098, "n_trials": 87, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 54.67, "compile_s": 1.83, "r_error": "", "src_len": 1127, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6387, "tout": 848, "ts": 1791527604.884302, "chk": "ok", "code_len": 1127}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7344, "tout": 633, "ts": 1791527624.6746247, "chk": null, "code_len": 1127}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6387, "started": 1791527597.8317738}
{"ep": "h1-00105", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1928, "speedup": 0.1928, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 402.8, "calls": 2, "tokens_in": 15878, "tokens_out": 10000, "ctx_chars": 11132, "t_end": 1791527681.7220705, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.1928, "lo95": 0.1925, "mean": 0.1975, "ev_only": 0.1924, "ref_ms": 3.67887, "cand_ms": 19.07892, "n_trials": 80, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 72.17, "compile_s": 13.51, "r_error": "", "src_len": 5133, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 7521, "ts": 1791527346.551773, "chk": "ok", "code_len": 5133}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9452, "tout": 2479, "ts": 1791527608.7635636, "chk": null, "code_len": 5133}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6426, "started": 1791527278.9705997}
{"ep": "h1-00161", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1123, "speedup": 0.1123, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 137.0, "calls": 2, "tokens_in": 8851, "tokens_out": 5167, "ctx_chars": 2425, "t_end": 1791527694.2044196, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.1123, "lo95": 0.1123, "mean": 0.1124, "ev_only": 0.1123, "ref_ms": 30.79218, "cand_ms": 274.1366, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9404, "r_wall_s": 60.05, "compile_s": 2.3, "r_error": "", "src_len": 3178, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3324, "tout": 3425, "ts": 1791527586.782118, "chk": "ok", "code_len": 3178}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5527, "tout": 1742, "ts": 1791527633.8171918, "chk": null, "code_len": 3178}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3324, "started": 1791527557.2105186}
{"ep": "h1-00151", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3778, "speedup": 1.3778, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 175.6, "calls": 2, "tokens_in": 6301, "tokens_out": 6929, "ctx_chars": 0, "t_end": 1791527696.629527, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3778, "lo95": 1.3757, "mean": 1.3775, "ev_only": 1.3792, "ref_ms": 11.0511, "cand_ms": 8.02107, "n_trials": 132, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1702, "r_wall_s": 89.31, "compile_s": 14.08, "r_error": "", "src_len": 4970, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1619, "tout": 4490, "ts": 1791527559.050242, "chk": "ok", "code_len": 4970}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4682, "tout": 2439, "ts": 1791527605.9108946, "chk": null, "code_len": 4970}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1619, "started": 1791527521.038803}
{"ep": "h1-00068", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.4545, "speedup": 2.4545, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 603.9, "calls": 4, "tokens_in": 23336, "tokens_out": 14986, "ctx_chars": 0, "t_end": 1791527709.0223897, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.4545, "lo95": 2.4517, "mean": 2.4527, "ev_only": 2.4505, "ref_ms": 12.87597, "cand_ms": 5.24595, "n_trials": 95, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 175.82, "compile_s": 20.31, "r_error": "", "src_len": 5017, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1657, "tout": 7288, "ts": 1791527192.1365874, "chk": "forbidden", "code_len": 5062}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4634, "tout": 2441, "ts": 1791527214.6110485, "chk": "no_custom_kernel", "code_len": 5021}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7198, "tout": 2851, "ts": 1791527413.6830304, "chk": "ok", "code_len": 5017}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9847, "tout": 2406, "ts": 1791527533.0854175, "chk": null, "code_len": 5017}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "no_custom_kernel", "ok", null], "first_tin": 1657, "started": 1791527125.5051827}
{"ep": "h1-00170", "task": "L2_082", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9328, "speedup": 1.9328, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.5, "calls": 2, "tokens_in": 14061, "tokens_out": 2017, "ctx_chars": 10743, "t_end": 1791527710.9664688, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.9328, "lo95": 1.9304, "mean": 1.9325, "ev_only": 1.9376, "ref_ms": 19.46472, "cand_ms": 10.07055, "n_trials": 63, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0913, "r_wall_s": 84.34, "compile_s": 2.78, "r_error": "", "src_len": 2035, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6464, "tout": 1024, "ts": 1791527603.539869, "chk": "ok", "code_len": 2035}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7597, "tout": 993, "ts": 1791527626.2997751, "chk": null, "code_len": 2035}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6464, "started": 1791527593.4866061}
{"ep": "h1-00148", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1695, "speedup": 2.1695, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 200.4, "calls": 2, "tokens_in": 12435, "tokens_out": 1174, "ctx_chars": 9855, "t_end": 1791527715.7438498, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.1695, "lo95": 2.1685, "mean": 2.1679, "ev_only": 2.1765, "ref_ms": 6.30847, "cand_ms": 2.90776, "n_trials": 234, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2726, "r_wall_s": 85.32, "compile_s": 1.9, "r_error": "", "src_len": 880, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 634, "ts": 1791527521.2259326, "chk": "ok", "code_len": 880}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6589, "tout": 540, "ts": 1791527629.2065678, "chk": null, "code_len": 880}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791527515.342135}
{"ep": "h1-00144", "task": "L3_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "runtime_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 219.2, "calls": 1, "tokens_in": 5546, "tokens_out": 2368, "ctx_chars": 6513, "t_end": 1791527715.7652736, "error": "AttributeError: 'Conv2d' object has no attribute 'running_mean'", "f_status": "runtime_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": null, "r_wall_s": 199.52, "compile_s": 2.81, "r_error": "AttributeError: 'Conv2d' object has no attribute 'running_mean'", "src_len": 4905, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5546, "tout": 2368, "ts": 1791527516.1974275, "chk": null, "code_len": 4905}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5546, "started": 1791527496.5903993}
{"ep": "h1-00160", "task": "L2_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.6074, "speedup": 1.6074, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 167.1, "calls": 2, "tokens_in": 6003, "tokens_out": 3968, "ctx_chars": 0, "t_end": 1791527723.7989495, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.6074, "lo95": 1.6055, "mean": 1.603, "ev_only": 1.6054, "ref_ms": 4.77652, "cand_ms": 2.9716, "n_trials": 212, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.253, "r_wall_s": 28.56, "compile_s": 1.98, "r_error": "", "src_len": 3955, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1915, "tout": 2061, "ts": 1791527595.6772695, "chk": "ok", "code_len": 4037}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4088, "tout": 1907, "ts": 1791527695.1515021, "chk": null, "code_len": 3955}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1915, "started": 1791527577.0266237}
{"ep": "h1-00015", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.1768, "speedup": 5.1768, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 682.4, "calls": 3, "tokens_in": 12142, "tokens_out": 9646, "ctx_chars": 0, "t_end": 1791527724.5153875, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 5.1768, "lo95": 5.1713, "mean": 5.1699, "ev_only": 5.1784, "ref_ms": 72.73412, "cand_ms": 14.05, "n_trials": 21, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9905, "r_wall_s": 74.94, "compile_s": 2.95, "r_error": "", "src_len": 3450, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1699, "tout": 6093, "ts": 1791527098.9913929, "chk": "runtime_error", "code_len": 3528}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4248, "tout": 1835, "ts": 1791527327.1141865, "chk": "ok", "code_len": 3450}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6195, "tout": 1718, "ts": 1791527649.465621, "chk": null, "code_len": 3450}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 1699, "started": 1791527042.1187303}
{"ep": "h1-00188", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0354, "speedup": 1.0354, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 77.6, "calls": 2, "tokens_in": 4520, "tokens_out": 2233, "ctx_chars": 0, "t_end": 1791527727.7325141, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0354, "lo95": 1.0341, "mean": 1.0344, "ev_only": 1.0343, "ref_ms": 8.30675, "cand_ms": 8.02288, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0048, "r_wall_s": 28.72, "compile_s": 2.31, "r_error": "", "src_len": 1105, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1706, "tout": 1578, "ts": 1791527663.645921, "chk": "ok", "code_len": 1105}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2814, "tout": 655, "ts": 1791527698.890218, "chk": null, "code_len": 1105}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1706, "started": 1791527650.10506}
{"ep": "h1-00113", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.005, "speedup": 1.005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 414.4, "calls": 5, "tokens_in": 46326, "tokens_out": 22003, "ctx_chars": 0, "t_end": 1791527731.4533498, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.005, "lo95": 1.0042, "mean": 1.0062, "ev_only": 1.0062, "ref_ms": 23.42313, "cand_ms": 23.30623, "n_trials": 26, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0144, "r_wall_s": 65.57, "compile_s": 3.26, "r_error": "", "src_len": 4295, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2736, "tout": 5394, "ts": 1791527366.6800487, "chk": "incorrect", "code_len": 4990}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5941, "tout": 3208, "ts": 1791527408.8980708, "chk": "incorrect", "code_len": 4880}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8745, "tout": 6690, "ts": 1791527492.1598036, "chk": "incorrect", "code_len": 7516}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 13065, "tout": 4023, "ts": 1791527554.5573266, "chk": "ok", "code_len": 4295}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 15839, "tout": 2688, "ts": 1791527665.7579608, "chk": null, "code_len": 4295}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 2736, "started": 1791527317.0870738}
{"ep": "h1-00107", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4788, "speedup": 1.4788, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 429.5, "calls": 2, "tokens_in": 12928, "tokens_out": 4671, "ctx_chars": 9033, "t_end": 1791527731.48806, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4788, "lo95": 1.4784, "mean": 1.4782, "ev_only": 1.4788, "ref_ms": 7.70736, "cand_ms": 5.212, "n_trials": 193, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 94.93, "compile_s": 1.89, "r_error": "", "src_len": 2563, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 3055, "ts": 1791527349.031977, "chk": "ok", "code_len": 2563}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7440, "tout": 1616, "ts": 1791527636.3046606, "chk": null, "code_len": 2563}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5488, "started": 1791527322.363248}
{"ep": "h1-00173", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.28, "speedup": 1.28, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 130.2, "calls": 2, "tokens_in": 13246, "tokens_out": 2269, "ctx_chars": 9893, "t_end": 1791527731.613491, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.28, "lo95": 1.2742, "mean": 1.2807, "ev_only": 1.2798, "ref_ms": 19.78172, "cand_ms": 15.45492, "n_trials": 58, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0516, "r_wall_s": 93.87, "compile_s": 1.91, "r_error": "", "src_len": 1550, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5991, "tout": 1483, "ts": 1791527614.0341744, "chk": "ok", "code_len": 1550}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7255, "tout": 786, "ts": 1791527636.5027423, "chk": null, "code_len": 1550}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5991, "started": 1791527601.429446}
{"ep": "h1-00184", "task": "L2_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3938, "speedup": 1.3938, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 101.8, "calls": 1, "tokens_in": 6133, "tokens_out": 948, "ctx_chars": 10210, "t_end": 1791527732.1776118, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3938, "lo95": 1.3892, "mean": 1.3927, "ev_only": 1.3986, "ref_ms": 19.43839, "cand_ms": 13.94601, "n_trials": 70, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0722, "r_wall_s": 92.65, "compile_s": 2.09, "r_error": "", "src_len": 1916, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6133, "tout": 948, "ts": 1791527639.1410005, "chk": null, "code_len": 1916}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6133, "started": 1791527630.3918238}
{"ep": "h1-00169", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.016, "speedup": 1.016, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 148.5, "calls": 2, "tokens_in": 12839, "tokens_out": 2018, "ctx_chars": 10087, "t_end": 1791527738.3371794, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.016, "lo95": 1.0154, "mean": 1.0296, "ev_only": 1.0171, "ref_ms": 19.14592, "cand_ms": 18.84362, "n_trials": 80, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0733, "r_wall_s": 112.7, "compile_s": 2.48, "r_error": "", "src_len": 1193, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5891, "tout": 1356, "ts": 1791527603.1330001, "chk": "ok", "code_len": 1193}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6948, "tout": 662, "ts": 1791527625.5560238, "chk": null, "code_len": 1193}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5891, "started": 1791527589.843195}
{"ep": "h1-00134", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0873, "speedup": 1.0873, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 305.1, "calls": 2, "tokens_in": 5918, "tokens_out": 6712, "ctx_chars": 0, "t_end": 1791527739.9979284, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0873, "lo95": 1.0869, "mean": 1.1185, "ev_only": 1.0878, "ref_ms": 72.87686, "cand_ms": 67.02276, "n_trials": 16, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0102, "r_wall_s": 216.73, "compile_s": 16.23, "r_error": "", "src_len": 3868, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1699, "tout": 4820, "ts": 1791527489.0256028, "chk": "ok", "code_len": 3868}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4219, "tout": 1892, "ts": 1791527523.220743, "chk": null, "code_len": 3868}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1699, "started": 1791527434.873266}
{"ep": "h1-00119", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.8994, "speedup": 1.8994, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 379.8, "calls": 2, "tokens_in": 5955, "tokens_out": 7319, "ctx_chars": 0, "t_end": 1791527742.6965578, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.8994, "lo95": 1.8971, "mean": 1.9705, "ev_only": 1.9078, "ref_ms": 3.64362, "cand_ms": 1.91834, "n_trials": 192, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 191.37, "compile_s": 20.44, "r_error": "", "src_len": 4392, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1631, "tout": 5070, "ts": 1791527427.5031114, "chk": "ok", "code_len": 4392}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4324, "tout": 2249, "ts": 1791527550.5421796, "chk": null, "code_len": 4392}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1631, "started": 1791527383.2803214}
{"ep": "h1-00136", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 29.1197, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 295.3, "calls": 2, "tokens_in": 6491, "tokens_out": 7083, "ctx_chars": 0, "t_end": 1791527746.816082, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 29.1197, "lo95": 28.8142, "mean": 27.9536, "ev_only": 29.1458, "ref_ms": 25.07177, "cand_ms": 0.86099, "n_trials": 54, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 210.05, "compile_s": 20.41, "r_error": "", "src_len": 4856, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1755, "tout": 4689, "ts": 1791527491.2768443, "chk": "ok", "code_len": 4856}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4736, "tout": 2394, "ts": 1791527536.620606, "chk": null, "code_len": 4856}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1755, "started": 1791527451.5068116}
{"ep": "h1-00191", "task": "L2_055", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.001, "speedup": 1.001, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 78.9, "calls": 1, "tokens_in": 1688, "tokens_out": 2722, "ctx_chars": 0, "t_end": 1791527758.6181817, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.001, "lo95": 1.0001, "mean": 1.0134, "ev_only": 1.0002, "ref_ms": 16.14287, "cand_ms": 16.1265, "n_trials": 82, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0024, "r_wall_s": 54.76, "compile_s": 13.59, "r_error": "", "src_len": 1988, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1688, "tout": 2722, "ts": 1791527703.8390923, "chk": null, "code_len": 1988}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1688, "started": 1791527679.703875}
{"ep": "h1-00164", "task": "L2_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.022, "speedup": 1.022, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 218.0, "calls": 3, "tokens_in": 8614, "tokens_out": 3092, "ctx_chars": 0, "t_end": 1791527778.4305215, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.022, "lo95": 1.0204, "mean": 1.0226, "ev_only": 1.0215, "ref_ms": 8.48929, "cand_ms": 8.30644, "n_trials": 150, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0485, "r_wall_s": 129.75, "compile_s": 63.99, "r_error": "", "src_len": 3219, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1713, "tout": 1607, "ts": 1791527575.59557, "chk": "ok", "code_len": 3440}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3432, "tout": 13, "ts": 1791527636.1889238, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3469, "tout": 1472, "ts": 1791527648.5219853, "chk": null, "code_len": 3219}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1713, "started": 1791527560.4705548}
{"ep": "h1-00158", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2048, "speedup": 1.2048, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.4, "calls": 2, "tokens_in": 5595, "tokens_out": 6667, "ctx_chars": 0, "t_end": 1791527783.7375805, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2048, "lo95": 1.2029, "mean": 1.2167, "ev_only": 1.2113, "ref_ms": 10.77715, "cand_ms": 8.94492, "n_trials": 138, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9983, "r_wall_s": 76.57, "compile_s": 2.04, "r_error": "", "src_len": 3079, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1686, "tout": 4976, "ts": 1791527604.1105313, "chk": "ok", "code_len": 3079}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3909, "tout": 1691, "ts": 1791527707.127407, "chk": null, "code_len": 3079}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1686, "started": 1791527542.3252144}
{"ep": "h1-00152", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.1817, "speedup": 2.1817, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 259.8, "calls": 3, "tokens_in": 16336, "tokens_out": 16384, "ctx_chars": 0, "t_end": 1791527795.0130804, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.1817, "lo95": 2.1739, "mean": 2.188, "ev_only": 2.1828, "ref_ms": 59.26789, "cand_ms": 27.16645, "n_trials": 24, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9101, "r_wall_s": 35.38, "compile_s": 11.22, "r_error": "", "src_len": 6249, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1959, "tout": 9916, "ts": 1791527626.3404305, "chk": "no_custom_kernel", "code_len": 6250}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5586, "tout": 3426, "ts": 1791527676.5602496, "chk": "ok", "code_len": 6249}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8791, "tout": 3042, "ts": 1791527759.5869153, "chk": null, "code_len": 6249}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1959, "started": 1791527535.185057}
{"ep": "h1-00200", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.8703, "speedup": 4.8703, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.7, "calls": 2, "tokens_in": 4859, "tokens_out": 4049, "ctx_chars": 0, "t_end": 1791527805.2249866, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.8703, "lo95": 4.8675, "mean": 4.8518, "ev_only": 4.9115, "ref_ms": 7.37222, "cand_ms": 1.51372, "n_trials": 197, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 19.75, "compile_s": 1.98, "r_error": "", "src_len": 2403, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1612, "tout": 2889, "ts": 1791527767.3164172, "chk": "ok", "code_len": 2403}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3247, "tout": 1160, "ts": 1791527785.335386, "chk": null, "code_len": 2403}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1612, "started": 1791527724.5157108}
{"ep": "h1-00201", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.5495, "speedup": 4.5495, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.7, "calls": 2, "tokens_in": 13209, "tokens_out": 2962, "ctx_chars": 9438, "t_end": 1791527809.391716, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.5495, "lo95": 4.5211, "mean": 4.5744, "ev_only": 4.6433, "ref_ms": 7.42092, "cand_ms": 1.63116, "n_trials": 195, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 26.06, "compile_s": 1.88, "r_error": "", "src_len": 1958, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5861, "tout": 1790, "ts": 1791527760.4104307, "chk": "ok", "code_len": 1958}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7348, "tout": 1172, "ts": 1791527783.213582, "chk": null, "code_len": 1958}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5861, "started": 1791527727.7327483}
{"ep": "h1-00153", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6093, "speedup": 1.6093, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 272.7, "calls": 2, "tokens_in": 14142, "tokens_out": 6503, "ctx_chars": 9590, "t_end": 1791527809.9194736, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.6093, "lo95": 1.6085, "mean": 1.6079, "ev_only": 1.6061, "ref_ms": 5.58572, "cand_ms": 3.47098, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3934, "r_wall_s": 162.03, "compile_s": 2.87, "r_error": "", "src_len": 4264, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5717, "tout": 4335, "ts": 1791527575.9523754, "chk": "ok", "code_len": 4264}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8425, "tout": 2168, "ts": 1791527647.0027184, "chk": null, "code_len": 4264}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5717, "started": 1791527537.2214727}
{"ep": "h1-00174", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4481, "speedup": 1.4481, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 212.2, "calls": 2, "tokens_in": 22676, "tokens_out": 19965, "ctx_chars": 0, "t_end": 1791527815.8796244, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4481, "lo95": 1.4451, "mean": 1.4426, "ev_only": 1.4487, "ref_ms": 8.55401, "cand_ms": 5.90713, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.158, "r_wall_s": 22.35, "compile_s": 2.91, "r_error": "", "src_len": 14375, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7618, "tout": 13122, "ts": 1791527727.6051676, "chk": "ok", "code_len": 14375}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 15058, "tout": 6843, "ts": 1791527793.397301, "chk": null, "code_len": 14375}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7618, "started": 1791527603.686164}
{"ep": "h1-00194", "task": "L2_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1434, "speedup": 1.1434, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.7, "calls": 1, "tokens_in": 7201, "tokens_out": 840, "ctx_chars": 12155, "t_end": 1791527819.319299, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1434, "lo95": 1.143, "mean": 1.1459, "ev_only": 1.1455, "ref_ms": 11.98968, "cand_ms": 10.48644, "n_trials": 106, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1524, "r_wall_s": 113.78, "compile_s": 1.95, "r_error": "", "src_len": 1658, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7201, "tout": 840, "ts": 1791527704.6100276, "chk": null, "code_len": 1658}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7201, "started": 1791527696.6297746}
{"ep": "h1-00163", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0061, "speedup": 1.0061, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 265.7, "calls": 2, "tokens_in": 6027, "tokens_out": 5254, "ctx_chars": 0, "t_end": 1791527825.868873, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0061, "lo95": 1.0048, "mean": 1.0027, "ev_only": 1.0078, "ref_ms": 8.16274, "cand_ms": 8.11311, "n_trials": 207, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0153, "r_wall_s": 115.48, "compile_s": 2.23, "r_error": "", "src_len": 3479, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1771, "tout": 3308, "ts": 1791527589.0289314, "chk": "ok", "code_len": 3536}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4256, "tout": 1946, "ts": 1791527710.29412, "chk": null, "code_len": 3479}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1771, "started": 1791527560.1632338}
{"ep": "h1-00171", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7282, "speedup": 0.7282, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 233.9, "calls": 2, "tokens_in": 15274, "tokens_out": 2704, "ctx_chars": 11175, "t_end": 1791527828.675539, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7282, "lo95": 0.7273, "mean": 0.7266, "ev_only": 0.7283, "ref_ms": 3.29392, "cand_ms": 4.52359, "n_trials": 182, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0006, "r_wall_s": 118.99, "compile_s": 2.56, "r_error": "", "src_len": 2314, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6880, "tout": 1618, "ts": 1791527608.2846928, "chk": "ok", "code_len": 2314}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8394, "tout": 1086, "ts": 1791527708.8986385, "chk": null, "code_len": 2314}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6880, "started": 1791527594.763559}
{"ep": "h1-00183", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.475, "speedup": 2.475, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.1, "calls": 2, "tokens_in": 16379, "tokens_out": 11131, "ctx_chars": 11023, "t_end": 1791527841.996617, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.475, "lo95": 2.4623, "mean": 2.4468, "ev_only": 2.4625, "ref_ms": 13.0396, "cand_ms": 5.26859, "n_trials": 122, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 100.63, "compile_s": 11.81, "r_error": "", "src_len": 5693, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6480, "tout": 8278, "ts": 1791527700.6117218, "chk": "ok", "code_len": 5693}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9899, "tout": 2853, "ts": 1791527741.3405836, "chk": null, "code_len": 5693}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6480, "started": 1791527628.865668}
{"ep": "h1-00133", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.4318, "speedup": 4.4318, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 409.0, "calls": 3, "tokens_in": 27078, "tokens_out": 18632, "ctx_chars": 8224, "t_end": 1791527843.7199862, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.4318, "lo95": 3.8961, "mean": 4.6937, "ev_only": 4.432, "ref_ms": 105.70886, "cand_ms": 23.85221, "n_trials": 12, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8624, "r_wall_s": 123.46, "compile_s": 18.4, "r_error": "", "src_len": 6343, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5516, "tout": 12103, "ts": 1791527547.5910568, "chk": "no_custom_kernel", "code_len": 6351}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9145, "tout": 3417, "ts": 1791527661.6228268, "chk": "ok", "code_len": 6343}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12417, "tout": 3112, "ts": 1791527720.2302837, "chk": null, "code_len": 6343}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5516, "started": 1791527434.750194}
{"ep": "h1-00209", "task": "L2_051", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 33.3799, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 101.3, "calls": 3, "tokens_in": 7365, "tokens_out": 1621, "ctx_chars": 0, "t_end": 1791527848.1463206, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 33.3799, "lo95": 32.6839, "mean": 32.5139, "ev_only": 35.5131, "ref_ms": 16.02281, "cand_ms": 0.48001, "n_trials": 95, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.2354, "r_wall_s": 69.87, "compile_s": 1.89, "r_error": "", "src_len": 1255, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1706, "tout": 993, "ts": 1791527759.5553064, "chk": "ok", "code_len": 1255}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2811, "tout": 13, "ts": 1791527772.738549, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 2848, "tout": 615, "ts": 1791527778.1235538, "chk": null, "code_len": 1255}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1706, "started": 1791527746.8164682}
{"ep": "h1-00165", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.635, "speedup": 2.635, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 288.0, "calls": 3, "tokens_in": 29819, "tokens_out": 10907, "ctx_chars": 11175, "t_end": 1791527852.853076, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.635, "lo95": 2.6286, "mean": 2.608, "ev_only": 2.6464, "ref_ms": 4.38413, "cand_ms": 1.66379, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 119.08, "compile_s": 2.88, "r_error": "", "src_len": 4841, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 5961, "ts": 1791527621.068674, "chk": "runtime_error", "code_len": 4883}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10094, "tout": 2588, "ts": 1791527699.4951575, "chk": "ok", "code_len": 4841}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12658, "tout": 2358, "ts": 1791527733.4600534, "chk": null, "code_len": 4841}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 7067, "started": 1791527564.8098092}
{"ep": "h1-00185", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1107, "speedup": 1.1107, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 225.7, "calls": 2, "tokens_in": 14548, "tokens_out": 2572, "ctx_chars": 11296, "t_end": 1791527856.9088607, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1107, "lo95": 1.1096, "mean": 1.1117, "ev_only": 1.1112, "ref_ms": 31.40921, "cand_ms": 28.27977, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.047, "r_wall_s": 169.34, "compile_s": 10.05, "r_error": "", "src_len": 1476, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6639, "tout": 1785, "ts": 1791527647.596333, "chk": "ok", "code_len": 1476}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7909, "tout": 787, "ts": 1791527687.4318597, "chk": null, "code_len": 1476}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6639, "started": 1791527631.1663916}
{"ep": "h1-00142", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.7112, "speedup": 1.7112, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 370.7, "calls": 3, "tokens_in": 10364, "tokens_out": 7138, "ctx_chars": 0, "t_end": 1791527857.1147382, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.7112, "lo95": 1.7042, "mean": 1.6977, "ev_only": 1.7117, "ref_ms": 8.03084, "cand_ms": 4.69298, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 42.91, "compile_s": 2.55, "r_error": "", "src_len": 2076, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 3987, "ts": 1791527532.9850953, "chk": "incorrect", "code_len": 2365}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3633, "tout": 1832, "ts": 1791527754.4703305, "chk": "ok", "code_len": 2076}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5166, "tout": 1319, "ts": 1791527814.0974073, "chk": null, "code_len": 2076}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1565, "started": 1791527486.446912}
{"ep": "h1-00120", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.5663, "speedup": 3.5663, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 495.1, "calls": 2, "tokens_in": 9401, "tokens_out": 19658, "ctx_chars": 0, "t_end": 1791527858.4650755, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.5663, "lo95": 3.5642, "mean": 3.7157, "ev_only": 3.5692, "ref_ms": 44.42383, "cand_ms": 12.45654, "n_trials": 32, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0002, "r_wall_s": 91.42, "compile_s": 11.74, "r_error": "", "src_len": 8461, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2039, "tout": 15053, "ts": 1791527510.5859795, "chk": "ok", "code_len": 8507}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7362, "tout": 4605, "ts": 1791527766.2233987, "chk": null, "code_len": 8461}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2039, "started": 1791527363.3943748}
{"ep": "h1-00204", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1682, "speedup": 1.1682, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 127.4, "calls": 2, "tokens_in": 10710, "tokens_out": 4793, "ctx_chars": 6513, "t_end": 1791527858.9691408, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1682, "lo95": 1.1636, "mean": 1.1676, "ev_only": 1.1731, "ref_ms": 10.79482, "cand_ms": 9.24088, "n_trials": 106, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 52.58, "compile_s": 2.43, "r_error": "", "src_len": 2860, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4389, "tout": 3258, "ts": 1791527764.1973803, "chk": "ok", "code_len": 2860}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6321, "tout": 1535, "ts": 1791527805.3611627, "chk": null, "code_len": 2860}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4389, "started": 1791527731.6136718}
{"ep": "h1-00196", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.3911, "speedup": 2.3911, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 148.2, "calls": 2, "tokens_in": 17654, "tokens_out": 9665, "ctx_chars": 10384, "t_end": 1791527859.1601968, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.3911, "lo95": 2.3884, "mean": 2.3711, "ev_only": 2.3819, "ref_ms": 4.0211, "cand_ms": 1.68173, "n_trials": 238, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4231, "r_wall_s": 34.95, "compile_s": 3.03, "r_error": "", "src_len": 4551, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 7320, "ts": 1791527776.976528, "chk": "ok", "code_len": 4551}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10357, "tout": 2345, "ts": 1791527823.9926262, "chk": null, "code_len": 4551}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791527710.9670196}
{"ep": "h1-00146", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.6834, "speedup": 1.6834, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 361.8, "calls": 2, "tokens_in": 7314, "tokens_out": 9330, "ctx_chars": 0, "t_end": 1791527867.9812512, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.6834, "lo95": 1.68, "mean": 1.6809, "ev_only": 1.6836, "ref_ms": 44.47391, "cand_ms": 26.41883, "n_trials": 30, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 104.93, "compile_s": 11.64, "r_error": "", "src_len": 5595, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2039, "tout": 6655, "ts": 1791527566.0164716, "chk": "ok", "code_len": 5595}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5275, "tout": 2675, "ts": 1791527762.269437, "chk": null, "code_len": 5595}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2039, "started": 1791527506.1646936}
{"ep": "h1-00179", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2176, "speedup": 1.2176, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 248.2, "calls": 2, "tokens_in": 15717, "tokens_out": 2593, "ctx_chars": 12155, "t_end": 1791527872.5370936, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2176, "lo95": 1.217, "mean": 1.2168, "ev_only": 1.2163, "ref_ms": 12.01744, "cand_ms": 9.86964, "n_trials": 113, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0681, "r_wall_s": 128.49, "compile_s": 2.3, "r_error": "", "src_len": 1626, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7203, "tout": 1695, "ts": 1791527638.9354155, "chk": "ok", "code_len": 1626}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8514, "tout": 898, "ts": 1791527743.2064273, "chk": null, "code_len": 1626}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7203, "started": 1791527624.2890074}
{"ep": "h1-00141", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.1454, "speedup": 2.1454, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 387.3, "calls": 2, "tokens_in": 6485, "tokens_out": 6469, "ctx_chars": 0, "t_end": 1791527872.9983904, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.1454, "lo95": 2.1427, "mean": 2.1465, "ev_only": 2.1451, "ref_ms": 44.42111, "cand_ms": 20.70507, "n_trials": 32, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 161.56, "compile_s": 2.13, "r_error": "", "src_len": 3693, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2039, "tout": 4619, "ts": 1791527546.4838421, "chk": "ok", "code_len": 3693}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4446, "tout": 1850, "ts": 1791527710.1675177, "chk": null, "code_len": 3693}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2039, "started": 1791527506.0613966}
{"ep": "h1-00145", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.7457, "speedup": 3.7457, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 371.1, "calls": 2, "tokens_in": 8426, "tokens_out": 14251, "ctx_chars": 0, "t_end": 1791527875.7670224, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 3.7457, "lo95": 3.7287, "mean": 3.841, "ev_only": 3.7478, "ref_ms": 80.16685, "cand_ms": 21.40242, "n_trials": 14, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8587, "r_wall_s": 152.85, "compile_s": 18.51, "r_error": "", "src_len": 8082, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1972, "tout": 10310, "ts": 1791527595.3563313, "chk": "ok", "code_len": 8113}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6454, "tout": 3941, "ts": 1791527722.891125, "chk": null, "code_len": 8082}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1972, "started": 1791527504.6349385}
{"ep": "h1-00154", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4267, "speedup": 1.4267, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 335.1, "calls": 3, "tokens_in": 21815, "tokens_out": 7826, "ctx_chars": 9033, "t_end": 1791527875.8033662, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4267, "lo95": 1.426, "mean": 1.426, "ev_only": 1.4245, "ref_ms": 7.77381, "cand_ms": 5.44881, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 146.84, "compile_s": 3.83, "r_error": "", "src_len": 2033, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 4525, "ts": 1791527586.3531969, "chk": "incorrect", "code_len": 2377}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7442, "tout": 2036, "ts": 1791527700.09034, "chk": "ok", "code_len": 2033}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8885, "tout": 1265, "ts": 1791527728.8626182, "chk": null, "code_len": 2033}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5488, "started": 1791527540.6613977}
{"ep": "h1-00176", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9404, "speedup": 0.9404, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 268.5, "calls": 2, "tokens_in": 15911, "tokens_out": 7370, "ctx_chars": 10864, "t_end": 1791527876.7107341, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9404, "lo95": 0.9396, "mean": 0.9403, "ev_only": 0.9405, "ref_ms": 20.13652, "cand_ms": 21.41203, "n_trials": 67, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 99.69, "compile_s": 1.96, "r_error": "", "src_len": 3901, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6632, "tout": 5159, "ts": 1791527661.3435702, "chk": "ok", "code_len": 3901}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9279, "tout": 2211, "ts": 1791527776.23581, "chk": null, "code_len": 3901}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6632, "started": 1791527608.2457135}
{"ep": "h1-00186", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.0431, "speedup": 2.0431, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 245.7, "calls": 2, "tokens_in": 15622, "tokens_out": 7997, "ctx_chars": 10508, "t_end": 1791527880.297573, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.0431, "lo95": 2.0391, "mean": 2.0362, "ev_only": 2.063, "ref_ms": 2.17234, "cand_ms": 1.06324, "n_trials": 183, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 54.91, "compile_s": 4.48, "r_error": "", "src_len": 4396, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6405, "tout": 5660, "ts": 1791527685.4704328, "chk": "ok", "code_len": 4396}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9217, "tout": 2337, "ts": 1791527825.3530548, "chk": null, "code_len": 4396}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6405, "started": 1791527634.622935}
{"ep": "h1-00177", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0626, "speedup": 1.0626, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.1, "calls": 2, "tokens_in": 4914, "tokens_out": 2661, "ctx_chars": 0, "t_end": 1791527880.9590235, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0626, "lo95": 1.0623, "mean": 1.0626, "ev_only": 1.0647, "ref_ms": 8.47341, "cand_ms": 7.97457, "n_trials": 167, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 50.57, "compile_s": 1.89, "r_error": "", "src_len": 1779, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1791, "tout": 1737, "ts": 1791527659.1386464, "chk": "ok", "code_len": 1779}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3123, "tout": 924, "ts": 1791527695.614129, "chk": null, "code_len": 1779}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1791, "started": 1791527643.3029094}
{"ep": "h1-00143", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.858, "speedup": 3.858, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 386.7, "calls": 3, "tokens_in": 21208, "tokens_out": 17242, "ctx_chars": 0, "t_end": 1791527881.3594167, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.858, "lo95": 3.8433, "mean": 3.7698, "ev_only": 3.9294, "ref_ms": 2.30017, "cand_ms": 0.5962, "n_trials": 207, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 45.85, "compile_s": 13.87, "r_error": "", "src_len": 9409, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 8090, "ts": 1791527563.0917695, "chk": "no_custom_kernel", "code_len": 9636}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7277, "tout": 4696, "ts": 1791527771.960592, "chk": "ok", "code_len": 9409}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11916, "tout": 4456, "ts": 1791527835.4881756, "chk": null, "code_len": 9409}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2015, "started": 1791527494.6146183}
{"ep": "h1-00129", "task": "L3_039", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2324, "speedup": 0.2324, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 477.3, "calls": 5, "tokens_in": 29880, "tokens_out": 8093, "ctx_chars": 0, "t_end": 1791527891.4989297, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.2324, "lo95": 0.1588, "mean": 0.2304, "ev_only": 0.2321, "ref_ms": 45.95485, "cand_ms": 197.7009, "n_trials": 12, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.3476, "r_wall_s": 216.35, "compile_s": 61.05, "r_error": "", "src_len": 4108, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1944, "tout": 2218, "ts": 1791527434.256068, "chk": "forbidden", "code_len": 4567}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4323, "tout": 1981, "ts": 1791527455.6709075, "chk": "ok", "code_len": 4475}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6416, "tout": 2016, "ts": 1791527553.123667, "chk": "ok", "code_len": 4175}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8544, "tout": 62, "ts": 1791527660.2095697, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 8653, "tout": 1816, "ts": 1791527675.026853, "chk": null, "code_len": 4108}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "ok", "no_code", null], "first_tin": 1944, "started": 1791527414.236033}
{"ep": "h1-00150", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 28.428, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 373.7, "calls": 2, "tokens_in": 8119, "tokens_out": 12755, "ctx_chars": 0, "t_end": 1791527894.681444, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 28.428, "lo95": 27.9589, "mean": 23.4207, "ev_only": 29.0816, "ref_ms": 36.42156, "cand_ms": 1.28118, "n_trials": 26, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9541, "r_wall_s": 247.4, "compile_s": 14.16, "r_error": "", "src_len": 8247, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1765, "tout": 8808, "ts": 1791527599.0500546, "chk": "ok", "code_len": 8247}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6354, "tout": 3947, "ts": 1791527647.1450605, "chk": null, "code_len": 8247}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1765, "started": 1791527521.0289912}
{"ep": "h1-00147", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.9175, "speedup": 2.9175, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 391.6, "calls": 2, "tokens_in": 16695, "tokens_out": 6583, "ctx_chars": 10384, "t_end": 1791527900.8208432, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.9175, "lo95": 2.9161, "mean": 2.912, "ev_only": 2.948, "ref_ms": 3.63611, "cand_ms": 1.24631, "n_trials": 224, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5082, "r_wall_s": 131.63, "compile_s": 1.97, "r_error": "", "src_len": 3033, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 5066, "ts": 1791527555.2129588, "chk": "ok", "code_len": 3033}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9398, "tout": 1517, "ts": 1791527632.6673157, "chk": null, "code_len": 3033}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791527509.2621472}
{"ep": "h1-00181", "task": "L2_057", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1804, "speedup": 2.1804, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 275.2, "calls": 1, "tokens_in": 5844, "tokens_out": 479, "ctx_chars": 9855, "t_end": 1791527901.012459, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.1804, "lo95": 2.1791, "mean": 2.191, "ev_only": 2.1831, "ref_ms": 6.29402, "cand_ms": 2.88665, "n_trials": 221, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2354, "r_wall_s": 135.26, "compile_s": 1.91, "r_error": "", "src_len": 908, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5844, "tout": 479, "ts": 1791527630.4314628, "chk": null, "code_len": 908}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5844, "started": 1791527625.8427877}
{"ep": "h1-00155", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.484, "speedup": 0.484, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 366.5, "calls": 3, "tokens_in": 16077, "tokens_out": 13687, "ctx_chars": 0, "t_end": 1791527907.29706, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.484, "lo95": 0.4835, "mean": 0.4835, "ev_only": 0.4835, "ref_ms": 10.09288, "cand_ms": 20.85149, "n_trials": 56, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 87.36, "compile_s": 12.22, "r_error": "", "src_len": 5877, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 7252, "ts": 1791527606.7176456, "chk": "no_custom_kernel", "code_len": 5822}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 3493, "ts": 1791527661.9954104, "chk": "ok", "code_len": 5877}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8588, "tout": 2942, "ts": 1791527819.1119516, "chk": null, "code_len": 5877}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2003, "started": 1791527540.7843657}
{"ep": "h1-00182", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.0546, "speedup": 4.0546, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 282.7, "calls": 3, "tokens_in": 16244, "tokens_out": 15701, "ctx_chars": 0, "t_end": 1791527910.312555, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.0546, "lo95": 4.0377, "mean": 4.1434, "ev_only": 4.0581, "ref_ms": 79.55403, "cand_ms": 19.62088, "n_trials": 17, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8329, "r_wall_s": 25.48, "compile_s": 10.79, "r_error": "", "src_len": 6073, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1972, "tout": 9375, "ts": 1791527709.3394141, "chk": "no_custom_kernel", "code_len": 6095}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5534, "tout": 3313, "ts": 1791527820.6626828, "chk": "ok", "code_len": 6073}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8738, "tout": 3013, "ts": 1791527884.8091807, "chk": null, "code_len": 6073}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1972, "started": 1791527627.6132505}
{"ep": "h1-00231", "task": "L3_026", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9674, "speedup": 0.9674, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 38.0, "calls": 1, "tokens_in": 3591, "tokens_out": 2462, "ctx_chars": 0, "t_end": 1791527910.4970329, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9674, "lo95": 0.966, "mean": 0.9698, "ev_only": 0.9674, "ref_ms": 20.08016, "cand_ms": 20.75785, "n_trials": 57, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0114, "r_wall_s": 14.11, "compile_s": 2.17, "r_error": "", "src_len": 3778, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3591, "tout": 2462, "ts": 1791527896.359274, "chk": null, "code_len": 3778}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3591, "started": 1791527872.5373297}
{"ep": "h1-00237", "task": "L2_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0326, "speedup": 1.0326, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 35.1, "calls": 1, "tokens_in": 1789, "tokens_out": 949, "ctx_chars": 0, "t_end": 1791527916.0878108, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0326, "lo95": 1.0323, "mean": 1.0331, "ev_only": 1.0334, "ref_ms": 8.45826, "cand_ms": 8.19108, "n_trials": 134, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0358, "r_wall_s": 26.4, "compile_s": 1.95, "r_error": "", "src_len": 1846, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1789, "tout": 949, "ts": 1791527889.589849, "chk": null, "code_len": 1846}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1789, "started": 1791527880.9592512}
{"ep": "h1-00239", "task": "L2_067", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2963, "speedup": 1.2963, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 42.3, "calls": 1, "tokens_in": 1655, "tokens_out": 646, "ctx_chars": 0, "t_end": 1791527933.8261409, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2963, "lo95": 1.2955, "mean": 1.3254, "ev_only": 1.2973, "ref_ms": 12.84069, "cand_ms": 9.90563, "n_trials": 78, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1612, "r_wall_s": 35.7, "compile_s": 2.22, "r_error": "", "src_len": 1225, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1655, "tout": 646, "ts": 1791527898.1067135, "chk": null, "code_len": 1225}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1655, "started": 1791527891.499268}
{"ep": "h1-00139", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.0141, "speedup": 3.0141, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 454.0, "calls": 2, "tokens_in": 7597, "tokens_out": 10857, "ctx_chars": 0, "t_end": 1791527933.8686342, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 3.0141, "lo95": 3.0087, "mean": 3.0027, "ev_only": 3.0162, "ref_ms": 35.89481, "cand_ms": 11.90893, "n_trials": 40, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 174.58, "compile_s": 12.09, "r_error": "", "src_len": 6201, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 7819, "ts": 1791527548.0252407, "chk": "ok", "code_len": 6201}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5635, "tout": 3038, "ts": 1791527758.2146554, "chk": null, "code_len": 6201}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791527479.870092}
{"ep": "h1-00224", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.342, "speedup": 1.342, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 82.7, "calls": 2, "tokens_in": 5041, "tokens_out": 4733, "ctx_chars": 0, "t_end": 1791527935.582113, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.342, "lo95": 1.3402, "mean": 1.3561, "ev_only": 1.3439, "ref_ms": 8.00167, "cand_ms": 5.96228, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 27.36, "compile_s": 1.92, "r_error": "", "src_len": 2698, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 3235, "ts": 1791527885.5786748, "chk": "ok", "code_len": 2698}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3476, "tout": 1498, "ts": 1791527908.1469002, "chk": null, "code_len": 2698}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791527852.8533134}
{"ep": "h1-00168", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2712, "speedup": 1.2712, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 362.8, "calls": 2, "tokens_in": 16632, "tokens_out": 6599, "ctx_chars": 13278, "t_end": 1791527938.1027215, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2712, "lo95": 1.2694, "mean": 1.288, "ev_only": 1.2686, "ref_ms": 5.28758, "cand_ms": 4.15965, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9986, "r_wall_s": 280.95, "compile_s": 2.41, "r_error": "", "src_len": 3184, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 4747, "ts": 1791527617.0618086, "chk": "ok", "code_len": 3184}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9470, "tout": 1852, "ts": 1791527656.6034586, "chk": null, "code_len": 3184}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791527575.2987123}
{"ep": "h1-00195", "task": "L1_065", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.191, "speedup": 2.191, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 244.2, "calls": 1, "tokens_in": 6886, "tokens_out": 1038, "ctx_chars": 11175, "t_end": 1791527953.2438176, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.191, "lo95": 2.1877, "mean": 2.1849, "ev_only": 2.1951, "ref_ms": 44.31802, "cand_ms": 20.22747, "n_trials": 31, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 234.16, "compile_s": 2.13, "r_error": "", "src_len": 2120, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6886, "tout": 1038, "ts": 1791527718.1446762, "chk": null, "code_len": 2120}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6886, "started": 1791527709.0226264}
{"ep": "h1-00217", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.795, "speedup": 1.795, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 137.7, "calls": 2, "tokens_in": 6224, "tokens_out": 10177, "ctx_chars": 0, "t_end": 1791527953.545046, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.795, "lo95": 1.7942, "mean": 1.8237, "ev_only": 1.7967, "ref_ms": 19.29776, "cand_ms": 10.75056, "n_trials": 74, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 37.33, "compile_s": 11.94, "r_error": "", "src_len": 5113, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1586, "tout": 7671, "ts": 1791527883.059809, "chk": "ok", "code_len": 5113}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4638, "tout": 2506, "ts": 1791527916.134774, "chk": null, "code_len": 5113}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1586, "started": 1791527815.879894}
{"ep": "h1-00238", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4818, "speedup": 1.4818, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.0, "calls": 2, "tokens_in": 14683, "tokens_out": 3822, "ctx_chars": 10508, "t_end": 1791527954.3578625, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4818, "lo95": 1.4792, "mean": 1.5001, "ev_only": 1.4756, "ref_ms": 2.17145, "cand_ms": 1.46543, "n_trials": 227, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.124, "r_wall_s": 27.99, "compile_s": 2.52, "r_error": "", "src_len": 2750, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6405, "tout": 2370, "ts": 1791527900.9642372, "chk": "ok", "code_len": 2750}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8278, "tout": 1452, "ts": 1791527926.3368149, "chk": null, "code_len": 2750}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6405, "started": 1791527881.359834}
{"ep": "h1-00208", "task": "L1_083", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.2019, "speedup": 2.2019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.0, "calls": 1, "tokens_in": 6377, "tokens_out": 1294, "ctx_chars": 10362, "t_end": 1791527961.698591, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.2019, "lo95": 2.1561, "mean": 2.4889, "ev_only": 2.2403, "ref_ms": 2.42282, "cand_ms": 1.10034, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 206.57, "compile_s": 2.06, "r_error": "", "src_len": 2707, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6377, "tout": 1294, "ts": 1791527754.2014859, "chk": null, "code_len": 2707}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6377, "started": 1791527742.6968246}
{"ep": "h1-00189", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.4301, "speedup": 7.4301, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 293.4, "calls": 2, "tokens_in": 12556, "tokens_out": 2465, "ctx_chars": 9033, "t_end": 1791527962.849248, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.4301, "lo95": 7.2242, "mean": 7.3311, "ev_only": 7.5408, "ref_ms": 8.13622, "cand_ms": 1.09504, "n_trials": 166, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0051, "r_wall_s": 50.17, "compile_s": 1.95, "r_error": "", "src_len": 1466, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5662, "tout": 1726, "ts": 1791527685.0848699, "chk": "ok", "code_len": 1466}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6894, "tout": 739, "ts": 1791527912.653117, "chk": null, "code_len": 1466}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5662, "started": 1791527669.4757993}
{"ep": "h1-00198", "task": "L1_010", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9462, "speedup": 0.9462, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 247.5, "calls": 3, "tokens_in": 7812, "tokens_out": 2695, "ctx_chars": 0, "t_end": 1791527963.2799547, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9462, "lo95": 0.9443, "mean": 0.9358, "ev_only": 0.9468, "ref_ms": 2.88852, "cand_ms": 3.0528, "n_trials": 210, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 89.89, "compile_s": 3.05, "r_error": "", "src_len": 2353, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1587, "tout": 1398, "ts": 1791527729.254272, "chk": "ok", "code_len": 2353}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3094, "tout": 13, "ts": 1791527862.5645173, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3131, "tout": 1284, "ts": 1791527873.2146666, "chk": null, "code_len": 2353}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1587, "started": 1791527715.7655573}
{"ep": "h1-00249", "task": "L2_081", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "runtime_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 29.4, "calls": 1, "tokens_in": 1704, "tokens_out": 543, "ctx_chars": 0, "t_end": 1791527964.95044, "error": "CompilationError: at 9:8:\ndef fused_kernel(x_ptr, out_ptr, n, BLOCK: tl.constexpr):\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    ", "f_status": "runtime_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": null, "r_wall_s": 23.75, "compile_s": 2.48, "r_error": "CompilationError: at 9:8:\ndef fused_kernel(x_ptr, out_ptr, n, BLOCK: tl.constexpr):\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    ", "src_len": 942, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1704, "tout": 543, "ts": 1791527941.160926, "chk": null, "code_len": 942}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1704, "started": 1791527935.5823572}
{"ep": "h1-00221", "task": "L2_012", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0082, "speedup": 1.0082, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 123.0, "calls": 1, "tokens_in": 1586, "tokens_out": 618, "ctx_chars": 0, "t_end": 1791527964.981346, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0082, "lo95": 1.0064, "mean": 1.0092, "ev_only": 1.0094, "ref_ms": 8.03243, "cand_ms": 7.96701, "n_trials": 166, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0042, "r_wall_s": 116.74, "compile_s": 3.71, "r_error": "", "src_len": 1219, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1586, "tout": 618, "ts": 1791527848.1538944, "chk": null, "code_len": 1219}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1586, "started": 1791527841.9968765}
{"ep": "h1-00233", "task": "L3_047", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9674, "speedup": 0.9674, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 90.3, "calls": 2, "tokens_in": 16370, "tokens_out": 2767, "ctx_chars": 10384, "t_end": 1791527966.1151197, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9674, "lo95": 0.967, "mean": 0.969, "ev_only": 0.9685, "ref_ms": 3.63374, "cand_ms": 3.75636, "n_trials": 193, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0437, "r_wall_s": 48.0, "compile_s": 2.1, "r_error": "", "src_len": 2327, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7295, "tout": 1668, "ts": 1791527893.9426053, "chk": "ok", "code_len": 2327}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9075, "tout": 1099, "ts": 1791527917.8927324, "chk": null, "code_len": 2327}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7295, "started": 1791527875.7675643}
{"ep": "h1-00228", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.7022, "speedup": 4.7022, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 108.1, "calls": 2, "tokens_in": 4872, "tokens_out": 4495, "ctx_chars": 0, "t_end": 1791527967.0747256, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.7022, "lo95": 4.6635, "mean": 4.7344, "ev_only": 4.8142, "ref_ms": 7.4272, "cand_ms": 1.57952, "n_trials": 207, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 52.61, "compile_s": 2.08, "r_error": "", "src_len": 2215, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1612, "tout": 3337, "ts": 1791527892.979555, "chk": "ok", "code_len": 2215}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3260, "tout": 1158, "ts": 1791527914.249834, "chk": null, "code_len": 2215}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1612, "started": 1791527858.9695551}
{"ep": "h1-00236", "task": "L2_098", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0012, "speedup": 1.0012, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 92.0, "calls": 3, "tokens_in": 18973, "tokens_out": 1608, "ctx_chars": 9033, "t_end": 1791527972.3137934, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0012, "lo95": 1.001, "mean": 1.0013, "ev_only": 1.0018, "ref_ms": 7.95058, "cand_ms": 7.94069, "n_trials": 169, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0052, "r_wall_s": 35.82, "compile_s": 2.16, "r_error": "", "src_len": 1493, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5660, "tout": 848, "ts": 1791527917.4199417, "chk": "ok", "code_len": 1493}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6617, "tout": 55, "ts": 1791527930.218627, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6696, "tout": 705, "ts": 1791527936.4664886, "chk": null, "code_len": 1493}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5660, "started": 1791527900.7035751}
{"ep": "h1-00235", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.2036, "speedup": 2.2036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.4, "calls": 2, "tokens_in": 15477, "tokens_out": 2941, "ctx_chars": 11175, "t_end": 1791527993.1341665, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.2036, "lo95": 2.2021, "mean": 2.2022, "ev_only": 2.2056, "ref_ms": 44.48363, "cand_ms": 20.18659, "n_trials": 33, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 75.0, "compile_s": 1.95, "r_error": "", "src_len": 2569, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6888, "tout": 1718, "ts": 1791527890.938605, "chk": "ok", "code_len": 2569}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8589, "tout": 1223, "ts": 1791527917.3181348, "chk": null, "code_len": 2569}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6888, "started": 1791527876.7110095}
{"ep": "h1-00243", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0658, "speedup": 1.0658, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 87.7, "calls": 2, "tokens_in": 13754, "tokens_out": 1991, "ctx_chars": 10191, "t_end": 1791527995.0250819, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0658, "lo95": 1.0655, "mean": 1.066, "ev_only": 1.0643, "ref_ms": 8.45435, "cand_ms": 7.9326, "n_trials": 180, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0057, "r_wall_s": 20.45, "compile_s": 2.43, "r_error": "", "src_len": 1638, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6250, "tout": 1142, "ts": 1791527917.252006, "chk": "ok", "code_len": 1638}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7504, "tout": 849, "ts": 1791527974.4175358, "chk": null, "code_len": 1638}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6250, "started": 1791527907.297292}
{"ep": "h1-00192", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.5364, "speedup": 7.5364, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 317.6, "calls": 2, "tokens_in": 12601, "tokens_out": 2607, "ctx_chars": 9033, "t_end": 1791527999.2763932, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 7.5364, "lo95": 7.526, "mean": 7.4547, "ev_only": 7.634, "ref_ms": 7.99186, "cand_ms": 1.06043, "n_trials": 176, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 59.84, "compile_s": 2.73, "r_error": "", "src_len": 1500, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5662, "tout": 1791, "ts": 1791527698.171889, "chk": "ok", "code_len": 1500}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6939, "tout": 816, "ts": 1791527939.4164894, "chk": null, "code_len": 1500}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5662, "started": 1791527681.722315}
{"ep": "h1-00205", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3566, "speedup": 1.3566, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 267.7, "calls": 2, "tokens_in": 22932, "tokens_out": 20665, "ctx_chars": 0, "t_end": 1791527999.8966856, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3566, "lo95": 1.3262, "mean": 1.2736, "ev_only": 1.3568, "ref_ms": 8.61876, "cand_ms": 6.35317, "n_trials": 100, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1572, "r_wall_s": 77.02, "compile_s": 2.8, "r_error": "", "src_len": 14600, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7618, "tout": 13644, "ts": 1791527845.6923506, "chk": "ok", "code_len": 14600}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 15314, "tout": 7021, "ts": 1791527922.837749, "chk": null, "code_len": 14600}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7618, "started": 1791527732.1778727}
{"ep": "h1-00232", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.3557, "speedup": 4.3557, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 128.4, "calls": 2, "tokens_in": 17477, "tokens_out": 7395, "ctx_chars": 12352, "t_end": 1791528001.441074, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.3557, "lo95": 4.323, "mean": 4.3309, "ev_only": 4.3597, "ref_ms": 27.92707, "cand_ms": 6.41164, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1021, "r_wall_s": 34.37, "compile_s": 1.82, "r_error": "", "src_len": 3968, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7394, "tout": 5276, "ts": 1791527920.669615, "chk": "ok", "code_len": 3968}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10083, "tout": 2119, "ts": 1791527966.7822208, "chk": null, "code_len": 3968}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7394, "started": 1791527872.998615}
{"ep": "h1-00234", "task": "L3_026", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6929, "speedup": 0.6929, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 125.9, "calls": 3, "tokens_in": 25948, "tokens_out": 6630, "ctx_chars": 6513, "t_end": 1791528001.7274828, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6929, "lo95": 0.6846, "mean": 0.6583, "ev_only": 0.6923, "ref_ms": 20.27035, "cand_ms": 29.25409, "n_trials": 32, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.111, "r_wall_s": 50.48, "compile_s": 2.03, "r_error": "", "src_len": 6543, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6294, "tout": 3396, "ts": 1791527904.0692906, "chk": "ok", "code_len": 6719}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9802, "tout": 26, "ts": 1791527926.1863368, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9852, "tout": 3208, "ts": 1791527951.220942, "chk": null, "code_len": 6543}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6294, "started": 1791527875.80359}
{"ep": "h1-00210", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7905, "speedup": 0.7905, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.8, "calls": 2, "tokens_in": 12151, "tokens_out": 2930, "ctx_chars": 9033, "t_end": 1791528002.4090164, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7905, "lo95": 0.79, "mean": 0.7909, "ev_only": 0.7917, "ref_ms": 3.72676, "cand_ms": 4.71452, "n_trials": 181, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0035, "r_wall_s": 138.66, "compile_s": 3.53, "r_error": "", "src_len": 1168, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 2049, "ts": 1791527798.7458572, "chk": "ok", "code_len": 1168}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6661, "tout": 881, "ts": 1791527863.7093856, "chk": null, "code_len": 1168}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791527778.9646385}
{"ep": "h1-00178", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1206, "speedup": 0.1206, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 387.0, "calls": 2, "tokens_in": 9069, "tokens_out": 5956, "ctx_chars": 2425, "t_end": 1791528010.3524575, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.1206, "lo95": 0.1205, "mean": 0.1207, "ev_only": 0.1205, "ref_ms": 30.91615, "cand_ms": 256.45635, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.936, "r_wall_s": 66.87, "compile_s": 1.93, "r_error": "", "src_len": 3655, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3324, "tout": 3985, "ts": 1791527656.236108, "chk": "ok", "code_len": 3655}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5745, "tout": 1971, "ts": 1791527943.0130641, "chk": null, "code_len": 3655}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3324, "started": 1791527623.3528728}
{"ep": "h1-00199", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.0805, "speedup": 0.0805, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 288.2, "calls": 2, "tokens_in": 7331, "tokens_out": 6201, "ctx_chars": 0, "t_end": 1791528011.9781241, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0805, "lo95": 0.0804, "mean": 0.0805, "ev_only": 0.0804, "ref_ms": 30.85209, "cand_ms": 383.43734, "n_trials": 14, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9574, "r_wall_s": 138.1, "compile_s": 2.7, "r_error": "", "src_len": 3618, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2408, "tout": 4174, "ts": 1791527758.5769649, "chk": "ok", "code_len": 3618}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4923, "tout": 2027, "ts": 1791527873.495672, "chk": null, "code_len": 3618}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2408, "started": 1791527723.7991734}
{"ep": "h1-00259", "task": "L2_058", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2292, "speedup": 1.2292, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 60.2, "calls": 3, "tokens_in": 22539, "tokens_out": 1746, "ctx_chars": 11393, "t_end": 1791528026.2713833, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2292, "lo95": 1.2287, "mean": 1.2286, "ev_only": 1.2291, "ref_ms": 25.05053, "cand_ms": 20.37908, "n_trials": 34, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0225, "r_wall_s": 31.74, "compile_s": 2.14, "r_error": "", "src_len": 1612, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6820, "tout": 903, "ts": 1791527974.8842053, "chk": "ok", "code_len": 1628}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7835, "tout": 25, "ts": 1791527987.3178904, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7884, "tout": 818, "ts": 1791527994.3348806, "chk": null, "code_len": 1612}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6820, "started": 1791527966.1153455}
{"ep": "h1-00216", "task": "L3_004", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9438, "speedup": 0.9438, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 221.1, "calls": 4, "tokens_in": 16953, "tokens_out": 4887, "ctx_chars": 0, "t_end": 1791528031.06829, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9438, "lo95": 0.9424, "mean": 0.9501, "ev_only": 0.9532, "ref_ms": 2.30945, "cand_ms": 2.44701, "n_trials": 218, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0661, "r_wall_s": 39.32, "compile_s": 2.53, "r_error": "", "src_len": 2891, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2013, "tout": 1658, "ts": 1791527824.409787, "chk": "incorrect", "code_len": 2873}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3805, "tout": 1626, "ts": 1791527878.4717767, "chk": "ok", "code_len": 2891}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5543, "tout": 25, "ts": 1791527978.9525146, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5592, "tout": 1578, "ts": 1791527991.643137, "chk": null, "code_len": 2891}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 2013, "started": 1791527809.9197102}
{"ep": "h1-00240", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 7.7118, "speedup": 7.7118, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 136.4, "calls": 2, "tokens_in": 4550, "tokens_out": 2320, "ctx_chars": 0, "t_end": 1791528031.0942676, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.7118, "lo95": 7.6341, "mean": 7.4593, "ev_only": 7.7567, "ref_ms": 3.58199, "cand_ms": 0.46448, "n_trials": 221, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 91.05, "compile_s": 11.71, "r_error": "", "src_len": 1910, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 1310, "ts": 1791527905.8382769, "chk": "ok", "code_len": 1910}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2986, "tout": 1010, "ts": 1791527939.543782, "chk": null, "code_len": 1910}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791527894.6816812}
{"ep": "h1-00213", "task": "L2_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0043, "speedup": 1.0043, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 238.8, "calls": 4, "tokens_in": 19191, "tokens_out": 4639, "ctx_chars": 0, "t_end": 1791528033.7792776, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0043, "lo95": 1.0031, "mean": 1.004, "ev_only": 1.0041, "ref_ms": 72.86106, "cand_ms": 72.55205, "n_trials": 19, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0135, "r_wall_s": 41.67, "compile_s": 12.47, "r_error": "", "src_len": 2931, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1697, "tout": 1832, "ts": 1791527812.6091743, "chk": "compile_error", "code_len": 2897}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4809, "tout": 1389, "ts": 1791527879.7840176, "chk": "ok", "code_len": 2931}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6310, "tout": 41, "ts": 1791527980.692943, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6375, "tout": 1377, "ts": 1791527992.0022829, "chk": null, "code_len": 2931}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1697, "started": 1791527795.0133016}
{"ep": "h1-00149", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7393, "speedup": 1.7393, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 518.0, "calls": 5, "tokens_in": 38313, "tokens_out": 18321, "ctx_chars": 2425, "t_end": 1791528033.8403811, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.7393, "lo95": 1.7384, "mean": 1.7377, "ev_only": 1.7378, "ref_ms": 15.86738, "cand_ms": 9.12302, "n_trials": 82, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9958, "r_wall_s": 88.37, "compile_s": 2.27, "r_error": "", "src_len": 3274, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3753, "tout": 3651, "ts": 1791527549.2565284, "chk": "incorrect", "code_len": 2951}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5729, "tout": 3847, "ts": 1791527687.8999522, "chk": "incorrect", "code_len": 3064}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7692, "tout": 4870, "ts": 1791527797.8622973, "chk": "incorrect", "code_len": 3083}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9578, "tout": 4221, "ts": 1791527906.4785383, "chk": "ok", "code_len": 3274}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11561, "tout": 1732, "ts": 1791527944.639176, "chk": null, "code_len": 3274}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 3753, "started": 1791527515.8222668}
{"ep": "h1-00080", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6965, "speedup": 0.6965, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 893.1, "calls": 5, "tokens_in": 99393, "tokens_out": 52575, "ctx_chars": 6513, "t_end": 1791528043.9467063, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6965, "lo95": 0.6937, "mean": 0.7713, "ev_only": 0.6998, "ref_ms": 3.52483, "cand_ms": 5.06063, "n_trials": 224, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0192, "r_wall_s": 104.71, "compile_s": 2.37, "r_error": "", "src_len": 3724, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5548, "tout": 17473, "ts": 1791527301.9966612, "chk": "runtime_error", "code_len": 15082}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 13511, "tout": 11640, "ts": 1791527464.2648497, "chk": "incorrect", "code_len": 17604}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 22788, "tout": 13261, "ts": 1791527684.691349, "chk": "incorrect", "code_len": 8883}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 27606, "tout": 8146, "ts": 1791527876.0798156, "chk": "ok", "code_len": 3724}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 29940, "tout": 2055, "ts": 1791527939.212181, "chk": null, "code_len": 3724}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "incorrect", "ok", null], "first_tin": 5548, "started": 1791527150.8175385}
{"ep": "h1-00212", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7042, "speedup": 0.7042, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 263.7, "calls": 2, "tokens_in": 9325, "tokens_out": 20265, "ctx_chars": 0, "t_end": 1791528047.4404657, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7042, "lo95": 0.702, "mean": 0.7208, "ev_only": 0.7031, "ref_ms": 7.53352, "cand_ms": 10.6977, "n_trials": 111, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.031, "r_wall_s": 65.67, "compile_s": 12.58, "r_error": "", "src_len": 10715, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1685, "tout": 14907, "ts": 1791527917.1903632, "chk": "ok", "code_len": 10715}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7640, "tout": 5358, "ts": 1791527981.2953348, "chk": null, "code_len": 10715}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1685, "started": 1791527783.737849}
{"ep": "h1-00097", "task": "L3_048", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9502, "speedup": 0.9502, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 811.7, "calls": 5, "tokens_in": 92437, "tokens_out": 28977, "ctx_chars": 2425, "t_end": 1791528048.307908, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9502, "lo95": 0.9494, "mean": 0.9511, "ev_only": 0.9505, "ref_ms": 15.91157, "cand_ms": 16.74552, "n_trials": 92, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0706, "r_wall_s": 101.7, "compile_s": 2.0, "r_error": "", "src_len": 3192, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3751, "tout": 9704, "ts": 1791527335.159776, "chk": "incorrect", "code_len": 5422}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 13592, "tout": 4970, "ts": 1791527681.2972128, "chk": "incorrect", "code_len": 5404}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 18698, "tout": 5895, "ts": 1791527798.6851714, "chk": "ok", "code_len": 3192}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 24702, "tout": 6831, "ts": 1791527906.7240853, "chk": "incorrect", "code_len": 4073}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 31694, "tout": 1577, "ts": 1791527945.821173, "chk": null, "code_len": 3192}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "incorrect", null], "first_tin": 3751, "started": 1791527236.6203847}
{"ep": "h1-00244", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1211, "speedup": 1.1211, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.6, "calls": 2, "tokens_in": 10749, "tokens_out": 11639, "ctx_chars": 0, "t_end": 1791528054.941011, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1211, "lo95": 0.8528, "mean": 0.9083, "ev_only": 1.1181, "ref_ms": 21.1181, "cand_ms": 18.83696, "n_trials": 71, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1064, "r_wall_s": 43.46, "compile_s": 2.44, "r_error": "", "src_len": 8558, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 7389, "ts": 1791527969.7798421, "chk": "ok", "code_len": 8703}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7725, "tout": 4250, "ts": 1791528011.430963, "chk": null, "code_len": 8558}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791527910.3127947}
{"ep": "h1-00220", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9587, "speedup": 0.9587, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 226.7, "calls": 2, "tokens_in": 4899, "tokens_out": 4837, "ctx_chars": 0, "t_end": 1791528055.3703492, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9587, "lo95": 0.9582, "mean": 0.9943, "ev_only": 0.9564, "ref_ms": 4.46108, "cand_ms": 4.65328, "n_trials": 185, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 94.28, "compile_s": 2.44, "r_error": "", "src_len": 2486, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1532, "tout": 3451, "ts": 1791527857.9263792, "chk": "ok", "code_len": 2486}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3367, "tout": 1386, "ts": 1791527961.0583885, "chk": null, "code_len": 2486}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1532, "started": 1791527828.67579}
{"ep": "h1-00223", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3964, "speedup": 1.3964, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 210.3, "calls": 2, "tokens_in": 13768, "tokens_out": 3033, "ctx_chars": 10210, "t_end": 1791528058.4560218, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3964, "lo95": 1.3926, "mean": 1.398, "ev_only": 1.3961, "ref_ms": 19.31064, "cand_ms": 13.82861, "n_trials": 72, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0688, "r_wall_s": 112.5, "compile_s": 1.97, "r_error": "", "src_len": 2129, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 1939, "ts": 1791527865.2650557, "chk": "ok", "code_len": 2162}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7633, "tout": 1094, "ts": 1791527945.4917245, "chk": null, "code_len": 2129}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791527848.1465647}
{"ep": "h1-00241", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5503, "speedup": 1.5503, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 159.1, "calls": 2, "tokens_in": 15834, "tokens_out": 4424, "ctx_chars": 11288, "t_end": 1791528059.9182508, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.5503, "lo95": 1.5484, "mean": 1.5489, "ev_only": 1.5494, "ref_ms": 28.88004, "cand_ms": 18.62885, "n_trials": 49, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0494, "r_wall_s": 107.94, "compile_s": 1.99, "r_error": "", "src_len": 2406, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6972, "tout": 3107, "ts": 1791527928.6290371, "chk": "ok", "code_len": 2471}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8862, "tout": 1317, "ts": 1791527951.753502, "chk": null, "code_len": 2406}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6972, "started": 1791527900.8210638}
{"ep": "h1-00227", "task": "L2_035", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2687, "speedup": 1.2687, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 202.4, "calls": 1, "tokens_in": 5908, "tokens_out": 969, "ctx_chars": 9835, "t_end": 1791528060.904382, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2687, "lo95": 1.2663, "mean": 1.2682, "ev_only": 1.2688, "ref_ms": 17.44433, "cand_ms": 13.74923, "n_trials": 64, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.064, "r_wall_s": 192.73, "compile_s": 4.03, "r_error": "", "src_len": 1905, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5908, "tout": 969, "ts": 1791527867.5507503, "chk": null, "code_len": 1905}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5908, "started": 1791527858.4653218}
{"ep": "h1-00156", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0029, "speedup": 1.0029, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 522.1, "calls": 4, "tokens_in": 39416, "tokens_out": 14651, "ctx_chars": 6513, "t_end": 1791528063.4008152, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0029, "lo95": 1.0023, "mean": 1.003, "ev_only": 1.0021, "ref_ms": 23.43392, "cand_ms": 23.36701, "n_trials": 67, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0042, "r_wall_s": 132.23, "compile_s": 2.02, "r_error": "", "src_len": 3556, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5439, "tout": 5716, "ts": 1791527607.4791365, "chk": "incorrect", "code_len": 5692}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8740, "tout": 3807, "ts": 1791527671.7039385, "chk": "incorrect", "code_len": 4931}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11556, "tout": 3206, "ts": 1791527908.386729, "chk": "ok", "code_len": 3556}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13681, "tout": 1922, "ts": 1791527931.144404, "chk": null, "code_len": 3556}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5439, "started": 1791527541.3474524}
{"ep": "h1-00255", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 31.9444, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 100.7, "calls": 2, "tokens_in": 12066, "tokens_out": 2792, "ctx_chars": 8570, "t_end": 1791528063.5253425, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 31.9444, "lo95": 31.8874, "mean": 31.2896, "ev_only": 32.6872, "ref_ms": 15.92546, "cand_ms": 0.49854, "n_trials": 91, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.3506, "r_wall_s": 47.22, "compile_s": 1.97, "r_error": "", "src_len": 1499, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5372, "tout": 1969, "ts": 1791527982.0658035, "chk": "ok", "code_len": 1499}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6694, "tout": 823, "ts": 1791528016.0852144, "chk": null, "code_len": 1499}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5372, "started": 1791527962.8494906}
{"ep": "h1-00225", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.9118, "speedup": 1.9118, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 208.3, "calls": 2, "tokens_in": 6417, "tokens_out": 10851, "ctx_chars": 0, "t_end": 1791528065.1604857, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.9118, "lo95": 1.9105, "mean": 1.9095, "ev_only": 1.9094, "ref_ms": 19.24028, "cand_ms": 10.0641, "n_trials": 74, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 86.26, "compile_s": 12.77, "r_error": "", "src_len": 5684, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1586, "tout": 8155, "ts": 1791527929.9449267, "chk": "ok", "code_len": 5684}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4831, "tout": 2696, "ts": 1791527978.7218256, "chk": null, "code_len": 5684}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1586, "started": 1791527856.9091203}
{"ep": "h1-00197", "task": "L3_045", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0003, "speedup": 1.0003, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.6, "calls": 5, "tokens_in": 45350, "tokens_out": 13277, "ctx_chars": 0, "t_end": 1791528065.3419557, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0003, "lo95": 0.9992, "mean": 0.9999, "ev_only": 0.9995, "ref_ms": 23.41715, "cand_ms": 23.40999, "n_trials": 40, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 42.36, "compile_s": 2.65, "r_error": "", "src_len": 3273, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2734, "tout": 2561, "ts": 1791527738.7560532, "chk": "no_custom_kernel", "code_len": 5059}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5434, "tout": 4543, "ts": 1791527893.696533, "chk": "incorrect", "code_len": 4518}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 10110, "tout": 1997, "ts": 1791527923.1099496, "chk": "incorrect", "code_len": 3422}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 12240, "tout": 2460, "ts": 1791527993.0165162, "chk": "ok", "code_len": 3273}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 14832, "tout": 1716, "ts": 1791528022.8729339, "chk": null, "code_len": 3273}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "incorrect", "incorrect", "ok", null], "first_tin": 2734, "started": 1791527715.7440789}
{"ep": "h1-00247", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 16.6689, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.9, "calls": 2, "tokens_in": 6573, "tokens_out": 6590, "ctx_chars": 0, "t_end": 1791528078.6841743, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 16.6689, "lo95": 16.5777, "mean": 16.0078, "ev_only": 16.8623, "ref_ms": 28.67295, "cand_ms": 1.72015, "n_trials": 49, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9206, "r_wall_s": 59.85, "compile_s": 14.72, "r_error": "", "src_len": 4362, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2037, "tout": 4555, "ts": 1791527972.7653136, "chk": "ok", "code_len": 4362}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4536, "tout": 2035, "ts": 1791528018.7882218, "chk": null, "code_len": 4362}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2037, "started": 1791527933.8264148}
{"ep": "h1-00215", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5374, "speedup": 0.5374, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 275.1, "calls": 2, "tokens_in": 13847, "tokens_out": 10105, "ctx_chars": 6513, "t_end": 1791528084.4917393, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.5374, "lo95": 0.5329, "mean": 0.541, "ev_only": 0.5363, "ref_ms": 4.03703, "cand_ms": 7.51158, "n_trials": 33, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2957, "r_wall_s": 47.09, "compile_s": 1.94, "r_error": "", "src_len": 6126, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 6911, "ts": 1791527869.1938045, "chk": "ok", "code_len": 6126}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8764, "tout": 3194, "ts": 1791528037.37725, "chk": null, "code_len": 6126}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791527809.3919911}
{"ep": "h1-00261", "task": "L2_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1496, "speedup": 1.1496, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 112.6, "calls": 1, "tokens_in": 7201, "tokens_out": 799, "ctx_chars": 12155, "t_end": 1791528084.951014, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1496, "lo95": 1.1491, "mean": 1.1494, "ev_only": 1.1517, "ref_ms": 12.14413, "cand_ms": 10.5642, "n_trials": 120, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1276, "r_wall_s": 89.91, "compile_s": 2.0, "r_error": "", "src_len": 1553, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7201, "tout": 799, "ts": 1791527994.213096, "chk": null, "code_len": 1553}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7201, "started": 1791527972.3140442}
{"ep": "h1-00229", "task": "L1_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7302, "speedup": 0.7302, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 231.3, "calls": 1, "tokens_in": 6878, "tokens_out": 978, "ctx_chars": 11175, "t_end": 1791528090.478706, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7302, "lo95": 0.7286, "mean": 0.7314, "ev_only": 0.7301, "ref_ms": 3.31884, "cand_ms": 4.54486, "n_trials": 210, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0006, "r_wall_s": 221.82, "compile_s": 3.78, "r_error": "", "src_len": 2004, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6878, "tout": 978, "ts": 1791527867.7953598, "chk": null, "code_len": 2004}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6878, "started": 1791527859.1606715}
{"ep": "h1-00258", "task": "L3_033", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9365, "speedup": 0.9365, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 125.5, "calls": 3, "tokens_in": 12790, "tokens_out": 2220, "ctx_chars": 3355, "t_end": 1791528090.5125322, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9365, "lo95": 0.9346, "mean": 0.9236, "ev_only": 0.9368, "ref_ms": 20.67328, "cand_ms": 22.07535, "n_trials": 65, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0007, "r_wall_s": 59.29, "compile_s": 1.95, "r_error": "", "src_len": 1776, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3294, "tout": 1292, "ts": 1791527995.4634953, "chk": "ok", "code_len": 1776}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4698, "tout": 76, "ts": 1791528024.0208075, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4798, "tout": 852, "ts": 1791528031.1540549, "chk": null, "code_len": 1776}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3294, "started": 1791527964.9815593}
{"ep": "h1-00187", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1726, "speedup": 1.1726, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 470.6, "calls": 2, "tokens_in": 5332, "tokens_out": 4954, "ctx_chars": 0, "t_end": 1791528117.1540594, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1726, "lo95": 1.1718, "mean": 1.1736, "ev_only": 1.1731, "ref_ms": 33.72304, "cand_ms": 28.75837, "n_trials": 38, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 245.39, "compile_s": 2.99, "r_error": "", "src_len": 2748, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 3512, "ts": 1791527677.9250543, "chk": "ok", "code_len": 2748}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3617, "tout": 1442, "ts": 1791527871.6888793, "chk": null, "code_len": 2748}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791527646.5827274}
{"ep": "h1-00203", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.1282, "speedup": 3.1282, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 386.1, "calls": 3, "tokens_in": 16453, "tokens_out": 16157, "ctx_chars": 0, "t_end": 1791528117.6104531, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.1282, "lo95": 3.1171, "mean": 3.1408, "ev_only": 3.1273, "ref_ms": 60.01906, "cand_ms": 19.18668, "n_trials": 26, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8677, "r_wall_s": 21.01, "compile_s": 10.77, "r_error": "", "src_len": 6175, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1959, "tout": 9852, "ts": 1791527820.7928555, "chk": "no_custom_kernel", "code_len": 6271}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5632, "tout": 3289, "ts": 1791527908.5138993, "chk": "ok", "code_len": 6175}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8862, "tout": 3016, "ts": 1791527962.7424908, "chk": null, "code_len": 6175}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1959, "started": 1791527731.4883018}
{"ep": "h1-00222", "task": "L2_063", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0036, "speedup": 1.0036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 278.1, "calls": 1, "tokens_in": 6275, "tokens_out": 446, "ctx_chars": 10823, "t_end": 1791528121.813787, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0036, "lo95": 1.003, "mean": 1.0056, "ev_only": 1.005, "ref_ms": 7.99848, "cand_ms": 7.9694, "n_trials": 130, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 273.24, "compile_s": 3.54, "r_error": "", "src_len": 896, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6275, "tout": 446, "ts": 1791527848.4724278, "chk": null, "code_len": 896}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6275, "started": 1791527843.7202437}
{"ep": "h1-00180", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.0241, "speedup": 7.0241, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 498.2, "calls": 3, "tokens_in": 29633, "tokens_out": 21010, "ctx_chars": 8224, "t_end": 1791528123.5762439, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.0241, "lo95": 7.0058, "mean": 7.0228, "ev_only": 7.044, "ref_ms": 32.06969, "cand_ms": 4.56564, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 18.66, "compile_s": 1.85, "r_error": "", "src_len": 7706, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 12530, "ts": 1791527737.1796072, "chk": "no_custom_kernel", "code_len": 7730}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10002, "tout": 4398, "ts": 1791528011.4974601, "chk": "ok", "code_len": 7706}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14141, "tout": 4082, "ts": 1791528104.7980278, "chk": null, "code_len": 7706}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791527625.4062378}
{"ep": "h1-00250", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2627, "speedup": 1.2627, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.1, "calls": 2, "tokens_in": 13763, "tokens_out": 1952, "ctx_chars": 11132, "t_end": 1791528126.2155175, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2627, "lo95": 1.2619, "mean": 1.2627, "ev_only": 1.2578, "ref_ms": 3.64336, "cand_ms": 2.88534, "n_trials": 220, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2703, "r_wall_s": 86.21, "compile_s": 2.92, "r_error": "", "src_len": 999, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 1370, "ts": 1791527950.9351225, "chk": "ok", "code_len": 999}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7337, "tout": 582, "ts": 1791528039.10472, "chk": null, "code_len": 999}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6426, "started": 1791527938.102992}
{"ep": "h1-00254", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8059, "speedup": 0.8059, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 166.1, "calls": 2, "tokens_in": 12160, "tokens_out": 2908, "ctx_chars": 9033, "t_end": 1791528127.787825, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8059, "lo95": 0.8046, "mean": 0.8051, "ev_only": 0.8006, "ref_ms": 3.7627, "cand_ms": 4.6687, "n_trials": 183, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0066, "r_wall_s": 74.47, "compile_s": 3.67, "r_error": "", "src_len": 1188, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 1960, "ts": 1791527982.8709886, "chk": "ok", "code_len": 1260}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6670, "tout": 948, "ts": 1791528053.289298, "chk": null, "code_len": 1188}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791527961.6989005}
{"ep": "h1-00266", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2707, "speedup": 1.2707, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 127.9, "calls": 2, "tokens_in": 5126, "tokens_out": 4664, "ctx_chars": 0, "t_end": 1791528129.2912338, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2707, "lo95": 1.2623, "mean": 1.2882, "ev_only": 1.2746, "ref_ms": 2.9125, "cand_ms": 2.29205, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 71.8, "compile_s": 5.05, "r_error": "", "src_len": 2457, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 3111, "ts": 1791528028.7814267, "chk": "ok", "code_len": 2457}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3537, "tout": 1553, "ts": 1791528057.4072888, "chk": null, "code_len": 2457}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791528001.441459}
{"ep": "h1-00242", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0722, "speedup": 1.0722, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 228.4, "calls": 2, "tokens_in": 5036, "tokens_out": 4520, "ctx_chars": 0, "t_end": 1791528129.4581094, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0722, "lo95": 1.0718, "mean": 1.0741, "ev_only": 1.0731, "ref_ms": 7.51979, "cand_ms": 7.01315, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 36.84, "compile_s": 1.95, "r_error": "", "src_len": 2584, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 3054, "ts": 1791527927.2421055, "chk": "ok", "code_len": 2584}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3469, "tout": 1466, "ts": 1791527960.0064652, "chk": null, "code_len": 2584}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791527901.0126672}
{"ep": "h1-00167", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.2418, "speedup": 3.2418, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 573.0, "calls": 3, "tokens_in": 28029, "tokens_out": 15639, "ctx_chars": 8224, "t_end": 1791528147.8834875, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.2418, "lo95": 3.2343, "mean": 3.2424, "ev_only": 3.2448, "ref_ms": 60.1275, "cand_ms": 18.54756, "n_trials": 25, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8681, "r_wall_s": 106.99, "compile_s": 65.14, "r_error": "", "src_len": 6739, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5503, "tout": 8456, "ts": 1791527649.5826478, "chk": "no_custom_kernel", "code_len": 6761}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9478, "tout": 3735, "ts": 1791527929.0410035, "chk": "ok", "code_len": 6739}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13048, "tout": 3448, "ts": 1791528040.8675573, "chk": null, "code_len": 6739}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5503, "started": 1791527574.913207}
{"ep": "h1-00248", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.0038, "speedup": 6.0038, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 216.4, "calls": 3, "tokens_in": 24015, "tokens_out": 15802, "ctx_chars": 6513, "t_end": 1791528150.301749, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 6.0038, "lo95": 5.9578, "mean": 5.4599, "ev_only": 6.1863, "ref_ms": 2.29829, "cand_ms": 0.3828, "n_trials": 239, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.6817, "r_wall_s": 23.28, "compile_s": 11.28, "r_error": "", "src_len": 5740, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4718, "tout": 9845, "ts": 1791528024.5083015, "chk": "no_custom_kernel", "code_len": 5762}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8114, "tout": 3037, "ts": 1791528092.1764977, "chk": "ok", "code_len": 5740}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11183, "tout": 2920, "ts": 1791528126.922493, "chk": null, "code_len": 5740}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 4718, "started": 1791527933.8688633}
{"ep": "h1-00190", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.6213, "speedup": 1.6213, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 477.9, "calls": 2, "tokens_in": 18172, "tokens_out": 41839, "ctx_chars": 0, "t_end": 1791528150.7832608, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.6213, "lo95": 1.6201, "mean": 1.6256, "ev_only": 1.621, "ref_ms": 5.74725, "cand_ms": 3.54491, "n_trials": 203, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4534, "r_wall_s": 103.28, "compile_s": 19.44, "r_error": "", "src_len": 20740, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3365, "tout": 30955, "ts": 1791527944.688724, "chk": "ok", "code_len": 20740}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 14807, "tout": 10884, "ts": 1791528047.465526, "chk": null, "code_len": 20740}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3365, "started": 1791527672.8483703}
{"ep": "h1-00277", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 29.5336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 105.1, "calls": 2, "tokens_in": 12593, "tokens_out": 3978, "ctx_chars": 8570, "t_end": 1791528152.5121083, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 29.5336, "lo95": 29.3182, "mean": 29.1463, "ev_only": 30.4292, "ref_ms": 15.922, "cand_ms": 0.53911, "n_trials": 83, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.9429, "r_wall_s": 37.89, "compile_s": 1.86, "r_error": "", "src_len": 2500, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5372, "tout": 2660, "ts": 1791528071.2297516, "chk": "ok", "code_len": 2500}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7221, "tout": 1318, "ts": 1791528114.4189808, "chk": null, "code_len": 2500}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5372, "started": 1791528047.440698}
{"ep": "h1-00294", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0348, "speedup": 1.0348, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 42.4, "calls": 2, "tokens_in": 14127, "tokens_out": 1774, "ctx_chars": 10901, "t_end": 1791528160.0211163, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0348, "lo95": 1.0345, "mean": 1.0345, "ev_only": 1.0354, "ref_ms": 8.24944, "cand_ms": 7.97237, "n_trials": 172, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 18.64, "compile_s": 2.12, "r_error": "", "src_len": 1004, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6549, "tout": 1198, "ts": 1791528128.3132977, "chk": "ok", "code_len": 1004}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7578, "tout": 576, "ts": 1791528141.3073378, "chk": null, "code_len": 1004}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6549, "started": 1791528117.6106718}
{"ep": "h1-00262", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9504, "speedup": 0.9504, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 184.3, "calls": 2, "tokens_in": 14265, "tokens_out": 4725, "ctx_chars": 10384, "t_end": 1791528177.3930292, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9504, "lo95": 0.9498, "mean": 0.9637, "ev_only": 0.9505, "ref_ms": 7.3292, "cand_ms": 7.71152, "n_trials": 222, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 89.39, "compile_s": 4.72, "r_error": "", "src_len": 2681, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6168, "tout": 3006, "ts": 1791528019.702254, "chk": "ok", "code_len": 2681}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8097, "tout": 1719, "ts": 1791528087.910752, "chk": null, "code_len": 2681}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6168, "started": 1791527993.1344879}
{"ep": "h1-00218", "task": "L2_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5686, "speedup": 1.5686, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 360.5, "calls": 3, "tokens_in": 25799, "tokens_out": 3703, "ctx_chars": 11886, "t_end": 1791528179.833559, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.5686, "lo95": 1.5637, "mean": 1.6108, "ev_only": 1.5868, "ref_ms": 4.77616, "cand_ms": 3.04479, "n_trials": 135, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.283, "r_wall_s": 89.66, "compile_s": 5.68, "r_error": "", "src_len": 3636, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7267, "tout": 1860, "ts": 1791527855.5661511, "chk": "ok", "code_len": 3636}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9239, "tout": 30, "ts": 1791528075.244642, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9293, "tout": 1813, "ts": 1791528090.0994925, "chk": null, "code_len": 3636}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7267, "started": 1791527839.6636987}
{"ep": "h1-00279", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0291, "speedup": 1.0291, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 131.9, "calls": 2, "tokens_in": 5904, "tokens_out": 5611, "ctx_chars": 0, "t_end": 1791528186.8250105, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0291, "lo95": 1.0284, "mean": 1.0525, "ev_only": 1.0289, "ref_ms": 8.27923, "cand_ms": 8.04476, "n_trials": 144, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0066, "r_wall_s": 35.09, "compile_s": 1.96, "r_error": "", "src_len": 4221, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1730, "tout": 3595, "ts": 1791528087.1846564, "chk": "ok", "code_len": 4221}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4174, "tout": 2016, "ts": 1791528151.6499107, "chk": null, "code_len": 4221}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1730, "started": 1791528054.9412463}
{"ep": "h1-00273", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.57, "speedup": 1.57, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 160.6, "calls": 2, "tokens_in": 13470, "tokens_out": 7296, "ctx_chars": 9590, "t_end": 1791528191.6492367, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.57, "lo95": 1.5688, "mean": 1.5664, "ev_only": 1.5684, "ref_ms": 5.61667, "cand_ms": 3.57754, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3482, "r_wall_s": 66.13, "compile_s": 1.87, "r_error": "", "src_len": 3014, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5717, "tout": 5789, "ts": 1791528093.9731522, "chk": "ok", "code_len": 3014}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7753, "tout": 1507, "ts": 1791528124.7858841, "chk": null, "code_len": 3014}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5717, "started": 1791528031.0944698}
{"ep": "h1-00287", "task": "L3_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9676, "speedup": 0.9676, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 130.9, "calls": 1, "tokens_in": 2691, "tokens_out": 1554, "ctx_chars": 0, "t_end": 1791528196.2758899, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9676, "lo95": 0.9662, "mean": 0.9953, "ev_only": 0.9681, "ref_ms": 4.03032, "cand_ms": 4.16537, "n_trials": 194, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0492, "r_wall_s": 114.87, "compile_s": 2.06, "r_error": "", "src_len": 2510, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2691, "tout": 1554, "ts": 1791528080.9914606, "chk": null, "code_len": 2510}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2691, "started": 1791528065.3424528}
{"ep": "h1-00072", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 8.3585, "speedup": 8.3585, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 1081.6, "calls": 5, "tokens_in": 55958, "tokens_out": 35452, "ctx_chars": 0, "t_end": 1791528199.7467828, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 8.3585, "lo95": 8.3505, "mean": 8.5813, "ev_only": 8.4217, "ref_ms": 15.89198, "cand_ms": 1.9013, "n_trials": 76, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.98, "r_wall_s": 89.41, "compile_s": 12.32, "r_error": "", "src_len": 7883, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2837, "tout": 11401, "ts": 1791527217.050533, "chk": "incorrect", "code_len": 7644}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7070, "tout": 9320, "ts": 1791527516.201551, "chk": "incorrect", "code_len": 7849}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11318, "tout": 6876, "ts": 1791527812.525111, "chk": "no_custom_kernel", "code_len": 7906}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 15362, "tout": 4036, "ts": 1791527870.6336238, "chk": "ok", "code_len": 7883}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 19371, "tout": 3819, "ts": 1791528109.0051992, "chk": null, "code_len": 7883}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "no_custom_kernel", "ok", null], "first_tin": 2837, "started": 1791527118.185022}
{"ep": "h1-00124", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1813, "speedup": 1.1813, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 822.0, "calls": 5, "tokens_in": 101393, "tokens_out": 75621, "ctx_chars": 0, "t_end": 1791528203.1159997, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1813, "lo95": 1.0386, "mean": 0.9039, "ev_only": 1.1755, "ref_ms": 5.6044, "cand_ms": 4.74416, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0071, "r_wall_s": 44.32, "compile_s": 2.02, "r_error": "", "src_len": 3953, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2845, "tout": 20460, "ts": 1791527560.3653302, "chk": "runtime_error", "code_len": 15654}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11320, "tout": 9331, "ts": 1791527646.2998612, "chk": "incorrect", "code_len": 16024}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 19505, "tout": 23704, "ts": 1791527888.8196297, "chk": "incorrect", "code_len": 18627}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 29148, "tout": 13178, "ts": 1791528007.488075, "chk": "incorrect", "code_len": 18525}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 38575, "tout": 8948, "ts": 1791528158.7152836, "chk": null, "code_len": 3953}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "incorrect", "incorrect", null], "first_tin": 2845, "started": 1791527381.097331}
{"ep": "h1-00278", "task": "L1_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.1422, "speedup": 4.1422, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.1, "calls": 5, "tokens_in": 20983, "tokens_out": 5012, "ctx_chars": 0, "t_end": 1791528206.4023907, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.1422, "lo95": 4.1373, "mean": 4.1315, "ev_only": 4.1613, "ref_ms": 7.39132, "cand_ms": 1.7844, "n_trials": 218, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9723, "r_wall_s": 40.52, "compile_s": 2.01, "r_error": "", "src_len": 2052, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 1371, "ts": 1791528061.2788029, "chk": "incorrect", "code_len": 2188}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3113, "tout": 1326, "ts": 1791528115.3832788, "chk": "ok", "code_len": 2050}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 1155, "ts": 1791528133.491923, "chk": "ok", "code_len": 2052}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5812, "tout": 41, "ts": 1791528147.0981386, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 5900, "tout": 1119, "ts": 1791528165.7831862, "chk": null, "code_len": 2052}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", "no_code", null], "first_tin": 1610, "started": 1791528048.3081388}
{"ep": "h1-00292", "task": "L1_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8771, "speedup": 1.8771, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 118.8, "calls": 1, "tokens_in": 6947, "tokens_out": 1628, "ctx_chars": 10864, "t_end": 1791528209.2650628, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.8771, "lo95": 1.8708, "mean": 1.931, "ev_only": 1.8873, "ref_ms": 3.73936, "cand_ms": 1.99209, "n_trials": 199, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 95.14, "compile_s": 1.94, "r_error": "", "src_len": 3442, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6947, "tout": 1628, "ts": 1791528113.3140905, "chk": null, "code_len": 3442}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6947, "started": 1791528090.512929}
{"ep": "h1-00246", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1603, "speedup": 1.1603, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 301.9, "calls": 2, "tokens_in": 10970, "tokens_out": 5183, "ctx_chars": 6513, "t_end": 1791528217.9974244, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1603, "lo95": 1.1595, "mean": 1.1862, "ev_only": 1.1595, "ref_ms": 10.67445, "cand_ms": 9.20003, "n_trials": 113, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 160.92, "compile_s": 3.72, "r_error": "", "src_len": 3331, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4389, "tout": 3413, "ts": 1791527948.2171264, "chk": "ok", "code_len": 3331}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6581, "tout": 1770, "ts": 1791528057.0434766, "chk": null, "code_len": 3331}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4389, "started": 1791527916.0880396}
{"ep": "h1-00272", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.0745, "speedup": 2.0745, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 196.2, "calls": 2, "tokens_in": 5519, "tokens_out": 7516, "ctx_chars": 0, "t_end": 1791528227.2623603, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.0745, "lo95": 2.0735, "mean": 2.0715, "ev_only": 2.0836, "ref_ms": 5.59728, "cand_ms": 2.6982, "n_trials": 224, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4332, "r_wall_s": 68.82, "compile_s": 1.99, "r_error": "", "src_len": 3619, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 5760, "ts": 1791528085.3086443, "chk": "ok", "code_len": 3710}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3909, "tout": 1756, "ts": 1791528157.6931024, "chk": null, "code_len": 3619}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1610, "started": 1791528031.0685282}
{"ep": "h1-00193", "task": "L3_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.472, "speedup": 2.472, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 533.2, "calls": 4, "tokens_in": 64168, "tokens_out": 21943, "ctx_chars": 2425, "t_end": 1791528227.445905, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.472, "lo95": 2.4691, "mean": 2.4737, "ev_only": 2.4715, "ref_ms": 11.96341, "cand_ms": 4.83953, "n_trials": 116, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4312, "r_wall_s": 137.38, "compile_s": 55.17, "r_error": "", "src_len": 3171, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3591, "tout": 9840, "ts": 1791527824.6504073, "chk": "incorrect", "code_len": 4300}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 13567, "tout": 8991, "ts": 1791528007.05963, "chk": "forbidden", "code_len": 3082}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 22652, "tout": 1597, "ts": 1791528021.4446745, "chk": "ok", "code_len": 3171}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 24358, "tout": 1515, "ts": 1791528089.8902051, "chk": null, "code_len": 3171}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "forbidden", "ok", null], "first_tin": 3591, "started": 1791527714.662327}
{"ep": "h1-00202", "task": "L3_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.8572, "speedup": 1.8572, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 502.6, "calls": 4, "tokens_in": 25102, "tokens_out": 8060, "ctx_chars": 0, "t_end": 1791528234.1018083, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.8572, "lo95": 1.8375, "mean": 1.8568, "ev_only": 1.8626, "ref_ms": 12.70576, "cand_ms": 6.84117, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4539, "r_wall_s": 55.79, "compile_s": 2.58, "r_error": "", "src_len": 3377, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2482, "tout": 1968, "ts": 1791527754.2909288, "chk": "incorrect", "code_len": 3570}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4583, "tout": 4300, "ts": 1791528050.803196, "chk": "ok", "code_len": 3377}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8992, "tout": 29, "ts": 1791528161.9001048, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9045, "tout": 1763, "ts": 1791528178.1301708, "chk": null, "code_len": 3377}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 2482, "started": 1791527731.4535816}
{"ep": "h1-00256", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.3059, "speedup": 2.3059, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 282.0, "calls": 2, "tokens_in": 8167, "tokens_out": 13490, "ctx_chars": 0, "t_end": 1791528245.2945917, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.3059, "lo95": 2.3028, "mean": 2.3116, "ev_only": 2.3237, "ref_ms": 5.60618, "cand_ms": 2.43124, "n_trials": 207, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9972, "r_wall_s": 104.3, "compile_s": 12.4, "r_error": "", "src_len": 8883, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 9188, "ts": 1791528041.268597, "chk": "ok", "code_len": 8883}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6557, "tout": 4302, "ts": 1791528140.1734233, "chk": null, "code_len": 8883}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1610, "started": 1791527963.2801638}
{"ep": "h1-00290", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3783, "speedup": 1.3783, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.6, "calls": 3, "tokens_in": 11343, "tokens_out": 9204, "ctx_chars": 0, "t_end": 1791528246.5624192, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3783, "lo95": 1.3776, "mean": 1.377, "ev_only": 1.3806, "ref_ms": 7.32201, "cand_ms": 5.31232, "n_trials": 180, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 25.53, "compile_s": 1.85, "r_error": "", "src_len": 2393, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1701, "tout": 5389, "ts": 1791528135.4949236, "chk": "ok", "code_len": 2939}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4002, "tout": 2341, "ts": 1791528175.1644235, "chk": "ok", "code_len": 2393}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5640, "tout": 1474, "ts": 1791528220.9123316, "chk": null, "code_len": 2393}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 1701, "started": 1791528084.9512477}
{"ep": "h1-00310", "task": "L2_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "runtime_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 50.8, "calls": 1, "tokens_in": 1781, "tokens_out": 779, "ctx_chars": 0, "t_end": 1791528247.1103137, "error": "CompilationError: at 12:28:\ndef matvec_kernel(x_ptr, w_ptr, out_ptr, b_sum, N, K,\n                  BLOCK_K: tl.constexpr):\n    row = tl.program_id(0)\n    x_row", "f_status": "runtime_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": null, "r_wall_s": 42.85, "compile_s": 3.39, "r_error": "CompilationError: at 12:28:\ndef matvec_kernel(x_ptr, w_ptr, out_ptr, b_sum, N, K,\n                  BLOCK_K: tl.constexpr):\n    row = tl.program_id(0)\n    x_row", "src_len": 1184, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1781, "tout": 779, "ts": 1791528204.2135305, "chk": null, "code_len": 1184}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1781, "started": 1791528196.2761226}
{"ep": "h1-00219", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6176, "speedup": 1.6176, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 427.7, "calls": 2, "tokens_in": 16991, "tokens_out": 5081, "ctx_chars": 11886, "t_end": 1791528253.5493238, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.6176, "lo95": 1.614, "mean": 1.6076, "ev_only": 1.6166, "ref_ms": 4.73694, "cand_ms": 2.92842, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2791, "r_wall_s": 174.02, "compile_s": 2.0, "r_error": "", "src_len": 3793, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7269, "tout": 3126, "ts": 1791527851.486816, "chk": "ok", "code_len": 3793}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9722, "tout": 1955, "ts": 1791528079.466779, "chk": null, "code_len": 3793}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7269, "started": 1791527825.869105}
{"ep": "h1-00214", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.3661, "speedup": 2.3661, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 451.9, "calls": 2, "tokens_in": 17203, "tokens_out": 8323, "ctx_chars": 10384, "t_end": 1791528257.126325, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.3661, "lo95": 2.3646, "mean": 2.3601, "ev_only": 2.3821, "ref_ms": 4.00867, "cand_ms": 1.6942, "n_trials": 169, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4188, "r_wall_s": 208.64, "compile_s": 3.51, "r_error": "", "src_len": 3920, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 6370, "ts": 1791527861.1300576, "chk": "ok", "code_len": 3920}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9906, "tout": 1953, "ts": 1791528048.1829598, "chk": null, "code_len": 3920}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791527805.2255368}
{"ep": "h1-00271", "task": "L2_063", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0077, "speedup": 1.0077, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 232.5, "calls": 1, "tokens_in": 1518, "tokens_out": 946, "ctx_chars": 0, "t_end": 1791528258.8065176, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0077, "lo95": 1.0037, "mean": 1.0101, "ev_only": 1.0082, "ref_ms": 8.06715, "cand_ms": 8.00546, "n_trials": 185, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0054, "r_wall_s": 202.65, "compile_s": 16.14, "r_error": "", "src_len": 2080, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1518, "tout": 946, "ts": 1791528056.0686815, "chk": null, "code_len": 2080}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1518, "started": 1791528046.654806}
{"ep": "h1-00295", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2722, "speedup": 1.2722, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 140.2, "calls": 2, "tokens_in": 4816, "tokens_out": 2850, "ctx_chars": 0, "t_end": 1791528262.0018158, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2722, "lo95": 1.2714, "mean": 1.2718, "ev_only": 1.2735, "ref_ms": 19.73672, "cand_ms": 15.51427, "n_trials": 57, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0497, "r_wall_s": 98.28, "compile_s": 1.97, "r_error": "", "src_len": 1809, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1709, "tout": 1930, "ts": 1791528140.2175689, "chk": "ok", "code_len": 1809}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3107, "tout": 920, "ts": 1791528162.7141094, "chk": null, "code_len": 1809}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1709, "started": 1791528121.8140419}
{"ep": "h1-00301", "task": "L2_058", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2361, "speedup": 1.2361, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 119.5, "calls": 3, "tokens_in": 22579, "tokens_out": 1770, "ctx_chars": 11393, "t_end": 1791528267.3356721, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2361, "lo95": 1.2356, "mean": 1.2357, "ev_only": 1.2361, "ref_ms": 25.06796, "cand_ms": 20.27919, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0429, "r_wall_s": 19.92, "compile_s": 1.96, "r_error": "", "src_len": 1618, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6820, "tout": 921, "ts": 1791528165.3898056, "chk": "ok", "code_len": 1658}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7853, "tout": 29, "ts": 1791528240.0062728, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7906, "tout": 820, "ts": 1791528247.2716002, "chk": null, "code_len": 1618}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6820, "started": 1791528147.8837063}
{"ep": "h1-00284", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7559, "speedup": 1.7559, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.1, "calls": 2, "tokens_in": 13586, "tokens_out": 4140, "ctx_chars": 10087, "t_end": 1791528280.5208583, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.7559, "lo95": 1.7549, "mean": 1.7536, "ev_only": 1.7576, "ref_ms": 19.15924, "cand_ms": 10.91137, "n_trials": 70, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 26.93, "compile_s": 1.92, "r_error": "", "src_len": 2352, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5891, "tout": 2871, "ts": 1791528089.5651772, "chk": "ok", "code_len": 2352}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7695, "tout": 1269, "ts": 1791528253.519631, "chk": null, "code_len": 2352}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5891, "started": 1791528063.401061}
{"ep": "h1-00311", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6297, "speedup": 0.6297, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.5, "calls": 2, "tokens_in": 12931, "tokens_out": 4817, "ctx_chars": 8224, "t_end": 1791528281.2332666, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6297, "lo95": 0.5581, "mean": 0.7504, "ev_only": 0.6298, "ref_ms": 80.04007, "cand_ms": 127.11171, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0, "r_wall_s": 27.31, "compile_s": 1.92, "r_error": "", "src_len": 2670, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5516, "tout": 3378, "ts": 1791528229.5922174, "chk": "ok", "code_len": 2773}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7415, "tout": 1439, "ts": 1791528253.9043858, "chk": null, "code_len": 2670}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5516, "started": 1791528199.7470653}
{"ep": "h1-00211", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1257, "speedup": 1.1257, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 508.7, "calls": 2, "tokens_in": 6013, "tokens_out": 7801, "ctx_chars": 0, "t_end": 1791528287.1645746, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1257, "lo95": 1.1252, "mean": 1.1584, "ev_only": 1.1258, "ref_ms": 16.03568, "cand_ms": 14.24562, "n_trials": 70, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3368, "r_wall_s": 219.47, "compile_s": 2.32, "r_error": "", "src_len": 3539, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1690, "tout": 5705, "ts": 1791527829.0816944, "chk": "ok", "code_len": 3619}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4323, "tout": 2096, "ts": 1791528067.672054, "chk": null, "code_len": 3539}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1690, "started": 1791527778.4307914}
{"ep": "h1-00267", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0601, "speedup": 1.0601, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 293.8, "calls": 2, "tokens_in": 4947, "tokens_out": 4229, "ctx_chars": 0, "t_end": 1791528295.5754492, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0601, "lo95": 1.0597, "mean": 1.0597, "ev_only": 1.0611, "ref_ms": 7.27807, "cand_ms": 6.86548, "n_trials": 208, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 234.42, "compile_s": 3.82, "r_error": "", "src_len": 2393, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1572, "tout": 2603, "ts": 1791528024.3464172, "chk": "ok", "code_len": 2393}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3375, "tout": 1626, "ts": 1791528061.0350375, "chk": null, "code_len": 2393}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1572, "started": 1791528001.7278256}
{"ep": "h1-00251", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3283, "speedup": 1.3283, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 347.6, "calls": 2, "tokens_in": 16258, "tokens_out": 29572, "ctx_chars": 0, "t_end": 1791528300.8429785, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.3283, "lo95": 1.3276, "mean": 1.3287, "ev_only": 1.329, "ref_ms": 19.91407, "cand_ms": 14.99177, "n_trials": 70, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.2228, "r_wall_s": 31.17, "compile_s": 11.79, "r_error": "", "src_len": 15894, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 21163, "ts": 1791528153.4362402, "chk": "ok", "code_len": 15894}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12665, "tout": 8409, "ts": 1791528269.6068616, "chk": null, "code_len": 15894}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3593, "started": 1791527973.5897892}
{"ep": "h1-00321", "task": "L2_057", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 55.1, "calls": 1, "tokens_in": 1557, "tokens_out": 781, "ctx_chars": 0, "t_end": 1791528302.2371442, "error": "RuntimeError: Error building extension 'fused_act_conv057': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_conv057 -DTORCH_API_INCLUDE_EXTENSION_H", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 46.71, "compile_s": 46.7, "r_error": "RuntimeError: Error building extension 'fused_act_conv057': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_conv057 -DTORCH_API_INCLUDE_EXTENSION_H", "src_len": 1554, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1557, "tout": 781, "ts": 1791528255.4265447, "chk": null, "code_len": 1554}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1557, "started": 1791528247.1105466}
{"ep": "h1-00280", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9999, "speedup": 0.9999, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 248.3, "calls": 2, "tokens_in": 13204, "tokens_out": 1045, "ctx_chars": 10823, "t_end": 1791528303.71901, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9999, "lo95": 0.9982, "mean": 1.0021, "ev_only": 1.0015, "ref_ms": 8.12527, "cand_ms": 8.12612, "n_trials": 123, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 129.04, "compile_s": 2.55, "r_error": "", "src_len": 865, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6277, "tout": 541, "ts": 1791528060.601565, "chk": "ok", "code_len": 865}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6927, "tout": 504, "ts": 1791528174.5677326, "chk": null, "code_len": 865}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6277, "started": 1791528055.3705738}
{"ep": "h1-00226", "task": "L1_017", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.989, "speedup": 0.989, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 449.7, "calls": 3, "tokens_in": 18867, "tokens_out": 1945, "ctx_chars": 9033, "t_end": 1791528306.7874253, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.989, "lo95": 0.9879, "mean": 0.9859, "ev_only": 0.9881, "ref_ms": 7.73078, "cand_ms": 7.8171, "n_trials": 166, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 262.38, "compile_s": 3.24, "r_error": "", "src_len": 500, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 717, "ts": 1791527865.480237, "chk": "ok", "code_len": 709}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6312, "tout": 648, "ts": 1791528028.5311978, "chk": "ok", "code_len": 500}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7069, "tout": 580, "ts": 1791528044.2996762, "chk": null, "code_len": 500}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 5486, "started": 1791527857.1150053}
{"ep": "h1-00317", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.3329, "speedup": 9.3329, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.5, "calls": 2, "tokens_in": 5039, "tokens_out": 3585, "ctx_chars": 0, "t_end": 1791528308.9138737, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 9.3329, "lo95": 9.2857, "mean": 9.1061, "ev_only": 9.5083, "ref_ms": 8.03931, "cand_ms": 0.8614, "n_trials": 200, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2576, "r_wall_s": 40.72, "compile_s": 1.94, "r_error": "", "src_len": 2041, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1739, "tout": 2366, "ts": 1791528248.8717494, "chk": "ok", "code_len": 2041}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3300, "tout": 1219, "ts": 1791528267.9473755, "chk": null, "code_len": 2041}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1739, "started": 1791528227.4461455}
{"ep": "h1-00312", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.966, "speedup": 1.966, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 105.9, "calls": 2, "tokens_in": 7010, "tokens_out": 4681, "ctx_chars": 0, "t_end": 1791528308.9886057, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.966, "lo95": 1.9647, "mean": 1.9656, "ev_only": 1.9692, "ref_ms": 12.6689, "cand_ms": 6.44389, "n_trials": 103, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5107, "r_wall_s": 41.22, "compile_s": 1.98, "r_error": "", "src_len": 2745, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2484, "tout": 3214, "ts": 1791528231.2745602, "chk": "ok", "code_len": 2745}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4526, "tout": 1467, "ts": 1791528267.6702194, "chk": null, "code_len": 2745}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2484, "started": 1791528203.1162596}
{"ep": "h1-00313", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5836, "speedup": 0.5836, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 102.8, "calls": 2, "tokens_in": 14241, "tokens_out": 6370, "ctx_chars": 10177, "t_end": 1791528309.1690779, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.5836, "lo95": 0.5832, "mean": 0.6007, "ev_only": 0.5859, "ref_ms": 2.36943, "cand_ms": 4.05981, "n_trials": 207, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 37.96, "compile_s": 2.85, "r_error": "", "src_len": 2976, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6105, "tout": 4729, "ts": 1791528248.8467278, "chk": "ok", "code_len": 2976}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8136, "tout": 1641, "ts": 1791528271.1416216, "chk": null, "code_len": 2976}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6105, "started": 1791528206.4026327}
{"ep": "h1-00268", "task": "L2_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3399, "speedup": 1.3399, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 317.1, "calls": 3, "tokens_in": 24188, "tokens_out": 3006, "ctx_chars": 11357, "t_end": 1791528319.5391383, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3399, "lo95": 1.3392, "mean": 1.3398, "ev_only": 1.3416, "ref_ms": 7.52322, "cand_ms": 5.61469, "n_trials": 228, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1066, "r_wall_s": 237.29, "compile_s": 2.01, "r_error": "", "src_len": 2300, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6779, "tout": 1781, "ts": 1791528019.6125784, "chk": "ok", "code_len": 2300}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8672, "tout": 41, "ts": 1791528071.6960545, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8737, "tout": 1184, "ts": 1791528081.6883595, "chk": null, "code_len": 2300}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6779, "started": 1791528002.4092402}
{"ep": "h1-00305", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.763, "speedup": 2.763, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 159.8, "calls": 2, "tokens_in": 8724, "tokens_out": 11629, "ctx_chars": 0, "t_end": 1791528319.794679, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.763, "lo95": 2.7563, "mean": 2.7639, "ev_only": 2.7887, "ref_ms": 3.63735, "cand_ms": 1.31644, "n_trials": 174, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9392, "r_wall_s": 48.97, "compile_s": 2.46, "r_error": "", "src_len": 5493, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 8845, "ts": 1791528239.227339, "chk": "ok", "code_len": 5493}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6031, "tout": 2784, "ts": 1791528270.572111, "chk": null, "code_len": 5493}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791528160.0216668}
{"ep": "h1-00324", "task": "L3_019", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 67.3, "calls": 1, "tokens_in": 2378, "tokens_out": 3239, "ctx_chars": 0, "t_end": 1791528326.0916975, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.1019, "r_wall_s": 39.1, "compile_s": 1.97, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 3765, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2378, "tout": 3239, "ts": 1791528286.9662287, "chk": null, "code_len": 3765}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2378, "started": 1791528258.8067765}
{"ep": "h1-00304", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4661, "speedup": 1.4661, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 178.0, "calls": 2, "tokens_in": 4567, "tokens_out": 2285, "ctx_chars": 0, "t_end": 1791528330.5383813, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4661, "lo95": 1.4649, "mean": 1.4656, "ev_only": 1.4648, "ref_ms": 14.16073, "cand_ms": 9.65905, "n_trials": 99, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0673, "r_wall_s": 116.27, "compile_s": 2.13, "r_error": "", "src_len": 1331, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 1580, "ts": 1791528175.0295308, "chk": "ok", "code_len": 1331}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2816, "tout": 705, "ts": 1791528212.998938, "chk": null, "code_len": 1331}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1751, "started": 1791528152.5123372}
{"ep": "h1-00306", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9663, "speedup": 0.9663, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.9, "calls": 2, "tokens_in": 15680, "tokens_out": 5609, "ctx_chars": 11175, "t_end": 1791528333.2955258, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9663, "lo95": 0.9659, "mean": 0.9677, "ev_only": 0.9666, "ref_ms": 8.61511, "cand_ms": 8.91553, "n_trials": 148, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.6288, "r_wall_s": 78.44, "compile_s": 2.06, "r_error": "", "src_len": 2695, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6872, "tout": 4219, "ts": 1791528218.1440701, "chk": "ok", "code_len": 2695}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8808, "tout": 1390, "ts": 1791528253.9175735, "chk": null, "code_len": 2695}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6872, "started": 1791528177.393415}
{"ep": "h1-00206", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.3466, "speedup": 2.3466, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 595.5, "calls": 3, "tokens_in": 15590, "tokens_out": 11902, "ctx_chars": 0, "t_end": 1791528333.845576, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.3466, "lo95": 2.3368, "mean": 2.3996, "ev_only": 2.4321, "ref_ms": 2.19988, "cand_ms": 0.93749, "n_trials": 197, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9974, "r_wall_s": 246.14, "compile_s": 22.86, "r_error": "", "src_len": 6639, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1813, "tout": 5242, "ts": 1791527782.9487524, "chk": "no_custom_kernel", "code_len": 5877}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5197, "tout": 3464, "ts": 1791527879.459302, "chk": "ok", "code_len": 6639}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8580, "tout": 3196, "ts": 1791528087.657048, "chk": null, "code_len": 6639}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1813, "started": 1791527738.3374157}
{"ep": "h1-00316", "task": "L1_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.1148, "speedup": 3.1148, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 110.1, "calls": 2, "tokens_in": 8098, "tokens_out": 1776, "ctx_chars": 4348, "t_end": 1791528337.3191886, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.1148, "lo95": 3.0727, "mean": 3.1042, "ev_only": 3.1388, "ref_ms": 10.15191, "cand_ms": 3.25921, "n_trials": 139, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 77.54, "compile_s": 1.92, "r_error": "", "src_len": 1666, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3529, "tout": 928, "ts": 1791528236.6919453, "chk": "ok", "code_len": 1653}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4569, "tout": 848, "ts": 1791528259.3416965, "chk": null, "code_len": 1666}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3529, "started": 1791528227.2626116}
{"ep": "h1-00300", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2046, "speedup": 1.2046, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 212.3, "calls": 2, "tokens_in": 16153, "tokens_out": 3836, "ctx_chars": 12471, "t_end": 1791528341.7102182, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2046, "lo95": 1.2022, "mean": 1.1958, "ev_only": 1.1992, "ref_ms": 3.67399, "cand_ms": 3.04992, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9988, "r_wall_s": 151.91, "compile_s": 2.7, "r_error": "", "src_len": 2153, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7230, "tout": 2630, "ts": 1791528153.5134778, "chk": "ok", "code_len": 2153}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8923, "tout": 1206, "ts": 1791528189.0119927, "chk": null, "code_len": 2153}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7230, "started": 1791528129.4583182}
{"ep": "h1-00275", "task": "L2_035", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.255, "speedup": 1.255, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 314.2, "calls": 1, "tokens_in": 1691, "tokens_out": 1202, "ctx_chars": 0, "t_end": 1791528347.9952483, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.255, "lo95": 1.2508, "mean": 1.2538, "ev_only": 1.2537, "ref_ms": 17.51757, "cand_ms": 13.95814, "n_trials": 85, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0829, "r_wall_s": 169.12, "compile_s": 49.35, "r_error": "", "src_len": 2443, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1691, "tout": 1202, "ts": 1791528045.5624645, "chk": null, "code_len": 2443}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1691, "started": 1791528033.840579}
{"ep": "h1-00276", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1649, "speedup": 1.1649, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 313.7, "calls": 2, "tokens_in": 4892, "tokens_out": 4646, "ctx_chars": 0, "t_end": 1791528357.659322, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1649, "lo95": 1.1638, "mean": 1.1654, "ev_only": 1.1623, "ref_ms": 4.47087, "cand_ms": 3.83799, "n_trials": 197, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 140.65, "compile_s": 2.05, "r_error": "", "src_len": 2515, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1532, "tout": 3205, "ts": 1791528072.5399294, "chk": "ok", "code_len": 2515}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3360, "tout": 1441, "ts": 1791528216.957028, "chk": null, "code_len": 2515}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1532, "started": 1791528043.946965}
{"ep": "h1-00296", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1735, "speedup": 1.1735, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 236.6, "calls": 2, "tokens_in": 4974, "tokens_out": 4618, "ctx_chars": 0, "t_end": 1791528360.2203684, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1735, "lo95": 1.1727, "mean": 1.1718, "ev_only": 1.1789, "ref_ms": 4.45995, "cand_ms": 3.80057, "n_trials": 220, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 170.47, "compile_s": 2.43, "r_error": "", "src_len": 2438, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1532, "tout": 3288, "ts": 1791528153.9136345, "chk": "ok", "code_len": 2438}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3442, "tout": 1330, "ts": 1791528189.6900582, "chk": null, "code_len": 2438}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1532, "started": 1791528123.5764718}
{"ep": "h1-00263", "task": "L1_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0074, "speedup": 1.0074, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 368.1, "calls": 3, "tokens_in": 20654, "tokens_out": 3480, "ctx_chars": 9033, "t_end": 1791528363.110276, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0074, "lo95": 1.0069, "mean": 1.0038, "ev_only": 1.0062, "ref_ms": 8.01142, "cand_ms": 7.95232, "n_trials": 210, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 308.62, "compile_s": 3.46, "r_error": "", "src_len": 2800, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 1948, "ts": 1791528015.18125, "chk": "ok", "code_len": 2881}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7544, "tout": 56, "ts": 1791528042.3364825, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7624, "tout": 1476, "ts": 1791528054.4186068, "chk": null, "code_len": 2800}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5486, "started": 1791527995.0253184}
{"ep": "h1-00270", "task": "L2_097", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0067, "speedup": 1.0067, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 355.6, "calls": 1, "tokens_in": 1728, "tokens_out": 2358, "ctx_chars": 0, "t_end": 1791528367.5970726, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0067, "lo95": 1.0047, "mean": 1.0016, "ev_only": 1.0068, "ref_ms": 8.21622, "cand_ms": 8.16121, "n_trials": 187, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0157, "r_wall_s": 192.76, "compile_s": 48.86, "r_error": "", "src_len": 4771, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1728, "tout": 2358, "ts": 1791528038.235523, "chk": null, "code_len": 4771}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1728, "started": 1791528011.978373}
{"ep": "h1-00024", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.085, "speedup": 1.085, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 1325.8, "calls": 5, "tokens_in": 111132, "tokens_out": 76919, "ctx_chars": 6513, "t_end": 1791528367.9129758, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.085, "lo95": 1.0779, "mean": 1.0877, "ev_only": 1.0905, "ref_ms": 3.57346, "cand_ms": 3.29349, "n_trials": 186, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0127, "r_wall_s": 279.45, "compile_s": 55.82, "r_error": "", "src_len": 4767, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5548, "tout": 25927, "ts": 1791527273.7234404, "chk": "runtime_error", "code_len": 14235}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 13947, "tout": 12073, "ts": 1791527468.5476046, "chk": "incorrect", "code_len": 16022}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 23248, "tout": 20460, "ts": 1791527741.7436926, "chk": "incorrect", "code_len": 16241}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 32630, "tout": 15861, "ts": 1791527993.8778906, "chk": "ok", "code_len": 4896}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 35759, "tout": 2598, "ts": 1791528088.4366174, "chk": null, "code_len": 4767}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "incorrect", "ok", null], "first_tin": 5548, "started": 1791527042.1227868}
{"ep": "h1-00291", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1261, "speedup": 0.1261, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 281.3, "calls": 2, "tokens_in": 15603, "tokens_out": 8531, "ctx_chars": 11023, "t_end": 1791528371.750645, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.1261, "lo95": 0.1255, "mean": 0.1267, "ev_only": 0.1255, "ref_ms": 13.02068, "cand_ms": 103.27233, "n_trials": 9, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9999, "r_wall_s": 118.52, "compile_s": 63.47, "r_error": "", "src_len": 3788, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6480, "tout": 6415, "ts": 1791528168.5310693, "chk": "ok", "code_len": 3788}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9123, "tout": 2116, "ts": 1791528253.2086136, "chk": null, "code_len": 3788}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6480, "started": 1791528110.7817812}
{"ep": "h1-00264", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.1147, "speedup": 4.1147, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 372.8, "calls": 3, "tokens_in": 15949, "tokens_out": 14072, "ctx_chars": 0, "t_end": 1791528372.095034, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.1147, "lo95": 4.0889, "mean": 4.1197, "ev_only": 4.1171, "ref_ms": 78.56475, "cand_ms": 19.09374, "n_trials": 18, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.824, "r_wall_s": 25.08, "compile_s": 11.42, "r_error": "", "src_len": 5676, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1972, "tout": 7803, "ts": 1791528068.3308556, "chk": "no_custom_kernel", "code_len": 5698}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5440, "tout": 3413, "ts": 1791528285.6833754, "chk": "ok", "code_len": 5676}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8537, "tout": 2856, "ts": 1791528346.9081972, "chk": null, "code_len": 5676}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1972, "started": 1791527999.2766654}
{"ep": "h1-00314", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.304, "speedup": 1.304, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.4, "calls": 2, "tokens_in": 10867, "tokens_out": 4845, "ctx_chars": 6513, "t_end": 1791528372.6494544, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.304, "lo95": 1.3035, "mean": 1.3028, "ev_only": 1.3036, "ref_ms": 33.667, "cand_ms": 25.81822, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 67.77, "compile_s": 2.04, "r_error": "", "src_len": 2857, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4418, "tout": 3257, "ts": 1791528254.2623487, "chk": "ok", "code_len": 2857}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6449, "tout": 1588, "ts": 1791528304.817314, "chk": null, "code_len": 2857}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4418, "started": 1791528209.265288}
{"ep": "h1-00303", "task": "L3_029", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6909, "speedup": 0.6909, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 224.0, "calls": 3, "tokens_in": 41498, "tokens_out": 10210, "ctx_chars": 6513, "t_end": 1791528374.772664, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6909, "lo95": 0.6888, "mean": 0.6869, "ev_only": 0.692, "ref_ms": 8.39049, "cand_ms": 12.14503, "n_trials": 95, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0451, "r_wall_s": 26.8, "compile_s": 1.94, "r_error": "", "src_len": 12038, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 10319, "tout": 5126, "ts": 1791528211.822865, "chk": "ok", "code_len": 12038}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 15557, "tout": 41, "ts": 1791528308.5308459, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15622, "tout": 5043, "ts": 1791528347.8723423, "chk": null, "code_len": 12038}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 10319, "started": 1791528171.1354344}
{"ep": "h1-00323", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.439, "speedup": 1.439, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 120.9, "calls": 2, "tokens_in": 14022, "tokens_out": 4136, "ctx_chars": 10384, "t_end": 1791528378.0136497, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.439, "lo95": 1.4381, "mean": 1.441, "ev_only": 1.4374, "ref_ms": 7.32156, "cand_ms": 5.08789, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 70.0, "compile_s": 2.51, "r_error": "", "src_len": 2161, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6168, "tout": 2763, "ts": 1791528282.9707723, "chk": "ok", "code_len": 2161}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7854, "tout": 1373, "ts": 1791528307.924215, "chk": null, "code_len": 2161}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6168, "started": 1791528257.1266592}
{"ep": "h1-00252", "task": "L2_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4097, "speedup": 1.4097, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 429.7, "calls": 3, "tokens_in": 8962, "tokens_out": 3237, "ctx_chars": 0, "t_end": 1791528383.2939968, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4097, "lo95": 1.4001, "mean": 1.4621, "ev_only": 1.4117, "ref_ms": 19.38166, "cand_ms": 13.74885, "n_trials": 36, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0669, "r_wall_s": 99.77, "compile_s": 2.41, "r_error": "", "src_len": 2100, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1727, "tout": 1056, "ts": 1791527963.4322464, "chk": "runtime_error", "code_len": 1917}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3004, "tout": 1115, "ts": 1791528254.0657208, "chk": "ok", "code_len": 2201}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4231, "tout": 1066, "ts": 1791528283.096062, "chk": null, "code_len": 2100}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 1727, "started": 1791527953.5452769}
{"ep": "h1-00326", "task": "L1_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.7521, "speedup": 3.7521, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.1, "calls": 2, "tokens_in": 4860, "tokens_out": 2906, "ctx_chars": 0, "t_end": 1791528383.410551, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.7521, "lo95": 3.7451, "mean": 3.7022, "ev_only": 3.7564, "ref_ms": 7.36625, "cand_ms": 1.96323, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9754, "r_wall_s": 77.55, "compile_s": 2.15, "r_error": "", "src_len": 2275, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 1531, "ts": 1791528281.957898, "chk": "ok", "code_len": 2522}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3250, "tout": 1375, "ts": 1791528305.7152348, "chk": null, "code_len": 2275}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1610, "started": 1791528267.3359714}
{"ep": "h1-00320", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0632, "speedup": 1.0632, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.0, "calls": 2, "tokens_in": 5838, "tokens_out": 7211, "ctx_chars": 0, "t_end": 1791528390.6075466, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0632, "lo95": 1.0624, "mean": 1.0821, "ev_only": 1.0632, "ref_ms": 72.81321, "cand_ms": 68.48793, "n_trials": 19, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0115, "r_wall_s": 47.75, "compile_s": 10.94, "r_error": "", "src_len": 4072, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1699, "tout": 5176, "ts": 1791528295.3206844, "chk": "ok", "code_len": 4166}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4139, "tout": 2035, "ts": 1791528342.8309658, "chk": null, "code_len": 4072}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1699, "started": 1791528246.5626607}
{"ep": "h1-00274", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.7223, "speedup": 4.7223, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 358.9, "calls": 2, "tokens_in": 5253, "tokens_out": 4508, "ctx_chars": 0, "t_end": 1791528392.6413693, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.7223, "lo95": 4.7196, "mean": 4.9166, "ev_only": 4.7631, "ref_ms": 7.38199, "cand_ms": 1.56323, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 180.09, "compile_s": 2.39, "r_error": "", "src_len": 2510, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1678, "tout": 3277, "ts": 1791528065.0082982, "chk": "ok", "code_len": 2510}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3575, "tout": 1231, "ts": 1791528212.406464, "chk": null, "code_len": 2510}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1678, "started": 1791528033.7795284}
{"ep": "h1-00299", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.763, "speedup": 0.763, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 280.4, "calls": 2, "tokens_in": 5315, "tokens_out": 6978, "ctx_chars": 0, "t_end": 1791528409.6654203, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.763, "lo95": 0.7625, "mean": 0.7631, "ev_only": 0.7624, "ref_ms": 16.04298, "cand_ms": 21.02722, "n_trials": 80, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9999, "r_wall_s": 42.21, "compile_s": 2.05, "r_error": "", "src_len": 2457, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1690, "tout": 5338, "ts": 1791528179.592981, "chk": "ok", "code_len": 2457}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3625, "tout": 1640, "ts": 1791528367.34523, "chk": null, "code_len": 2457}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1690, "started": 1791528129.2914765}
{"ep": "h1-00157", "task": "L1_017", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9937, "speedup": 0.9937, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 868.2, "calls": 2, "tokens_in": 11742, "tokens_out": 1198, "ctx_chars": 9033, "t_end": 1791528409.7533648, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9937, "lo95": 0.9931, "mean": 0.9935, "ev_only": 0.9944, "ref_ms": 7.7326, "cand_ms": 7.78124, "n_trials": 210, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 361.58, "compile_s": 3.32, "r_error": "", "src_len": 663, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 661, "ts": 1791527566.4547687, "chk": "ok", "code_len": 736}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6256, "tout": 537, "ts": 1791528048.0963023, "chk": null, "code_len": 663}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5486, "started": 1791527541.5246546}
{"ep": "h1-00175", "task": "L1_006", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9916, "speedup": 0.9916, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 808.0, "calls": 5, "tokens_in": 20793, "tokens_out": 4651, "ctx_chars": 0, "t_end": 1791528413.606658, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9916, "lo95": 0.9908, "mean": 0.9734, "ev_only": 0.997, "ref_ms": 3.6961, "cand_ms": 3.72742, "n_trials": 189, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0007, "r_wall_s": 53.47, "compile_s": 1.9, "r_error": "", "src_len": 662, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 1196, "ts": 1791527633.030155, "chk": "incorrect", "code_len": 2088}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 2893, "tout": 1568, "ts": 1791527740.2529633, "chk": "incorrect", "code_len": 1780}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4593, "tout": 746, "ts": 1791528035.5219169, "chk": "ok", "code_len": 662}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5448, "tout": 799, "ts": 1791528356.1861923, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 6294, "tout": 342, "ts": 1791528360.0351336, "chk": null, "code_len": 662}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 1565, "started": 1791527605.6298788}
{"ep": "h1-00335", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0158, "speedup": 1.0158, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 105.7, "calls": 2, "tokens_in": 11921, "tokens_out": 1095, "ctx_chars": 9220, "t_end": 1791528414.5662308, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0158, "lo95": 1.015, "mean": 1.0164, "ev_only": 1.0166, "ref_ms": 8.06362, "cand_ms": 7.93828, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0037, "r_wall_s": 80.73, "compile_s": 2.69, "r_error": "", "src_len": 918, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5602, "tout": 605, "ts": 1791528314.3362424, "chk": "ok", "code_len": 918}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6319, "tout": 490, "ts": 1791528333.7509947, "chk": null, "code_len": 918}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5602, "started": 1791528308.9141085}
{"ep": "h1-00260", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 13.307, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 450.3, "calls": 2, "tokens_in": 8993, "tokens_out": 4253, "ctx_chars": 4348, "t_end": 1791528417.3388917, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 13.307, "lo95": 13.2814, "mean": 13.4349, "ev_only": 13.5607, "ref_ms": 10.1096, "cand_ms": 0.75972, "n_trials": 152, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 242.53, "compile_s": 2.48, "r_error": "", "src_len": 2768, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3531, "tout": 2721, "ts": 1791528006.7690046, "chk": "ok", "code_len": 2768}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5462, "tout": 1532, "ts": 1791528037.9483094, "chk": null, "code_len": 2768}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3531, "started": 1791527967.0749755}
{"ep": "h1-00230", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7835, "speedup": 0.7835, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 561.7, "calls": 5, "tokens_in": 93768, "tokens_out": 54810, "ctx_chars": 0, "t_end": 1791528429.6473722, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7835, "lo95": 0.7811, "mean": 0.7903, "ev_only": 0.7834, "ref_ms": 3.52587, "cand_ms": 4.49998, "n_trials": 184, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0011, "r_wall_s": 16.4, "compile_s": 1.96, "r_error": "", "src_len": 3012, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2845, "tout": 19494, "ts": 1791528032.6260688, "chk": "runtime_error", "code_len": 17352}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 12228, "tout": 12189, "ts": 1791528138.6899562, "chk": "incorrect", "code_len": 20222}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 22846, "tout": 15155, "ts": 1791528300.1094954, "chk": "incorrect", "code_len": 9425}, {"turn": 3, "action": "CHECK", "stop": null, "tin": 27897, "tout": 5935, "ts": 1791528392.1634302, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 27952, "tout": 2037, "ts": 1791528413.204552, "chk": null, "code_len": 3012}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn", null], "chk_statuses": ["runtime_error", "incorrect", "incorrect", "no_code", null], "first_tin": 2845, "started": 1791527867.9815102}
{"ep": "h1-00302", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.1307, "speedup": 3.1307, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 289.2, "calls": 2, "tokens_in": 5719, "tokens_out": 3816, "ctx_chars": 0, "t_end": 1791528439.494788, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 3.1307, "lo95": 3.1213, "mean": 2.9961, "ev_only": 3.1733, "ref_ms": 2.93272, "cand_ms": 0.93677, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 87.21, "compile_s": 1.94, "r_error": "", "src_len": 2678, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1921, "tout": 2392, "ts": 1791528178.3443258, "chk": "ok", "code_len": 2678}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3798, "tout": 1424, "ts": 1791528351.4775534, "chk": null, "code_len": 2678}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1921, "started": 1791528150.3020191}
{"ep": "h1-00339", "task": "L2_059", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0024, "speedup": 1.0024, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 124.8, "calls": 1, "tokens_in": 1548, "tokens_out": 544, "ctx_chars": 0, "t_end": 1791528444.550988, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0024, "lo95": 1.0019, "mean": 1.0245, "ev_only": 1.0029, "ref_ms": 16.0859, "cand_ms": 16.04715, "n_trials": 60, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0009, "r_wall_s": 118.99, "compile_s": 2.66, "r_error": "", "src_len": 948, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1548, "tout": 544, "ts": 1791528325.4931333, "chk": null, "code_len": 948}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1548, "started": 1791528319.7949386}
{"ep": "h1-00285", "task": "L2_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.163, "speedup": 1.163, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 387.6, "calls": 2, "tokens_in": 16469, "tokens_out": 3679, "ctx_chars": 11535, "t_end": 1791528451.1584811, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.163, "lo95": 1.1618, "mean": 1.1624, "ev_only": 1.1641, "ref_ms": 20.0998, "cand_ms": 17.28228, "n_trials": 65, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0304, "r_wall_s": 123.25, "compile_s": 3.55, "r_error": "", "src_len": 2069, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6865, "tout": 2627, "ts": 1791528087.6922808, "chk": "ok", "code_len": 2069}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9604, "tout": 1052, "ts": 1791528327.8617744, "chk": null, "code_len": 2069}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6865, "started": 1791528063.525551}
{"ep": "h1-00309", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3523, "speedup": 1.3523, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.6, "calls": 2, "tokens_in": 5143, "tokens_out": 3936, "ctx_chars": 0, "t_end": 1791528452.2768505, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.3523, "lo95": 1.352, "mean": 1.3536, "ev_only": 1.354, "ref_ms": 7.3005, "cand_ms": 5.39874, "n_trials": 209, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 124.47, "compile_s": 2.57, "r_error": "", "src_len": 2255, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1701, "tout": 2441, "ts": 1791528213.4783187, "chk": "ok", "code_len": 2255}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3442, "tout": 1495, "ts": 1791528327.6605914, "chk": null, "code_len": 2255}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1701, "started": 1791528191.6494768}
{"ep": "h1-00366", "task": "L2_068", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9976, "speedup": 0.9976, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 24.0, "calls": 1, "tokens_in": 1530, "tokens_out": 515, "ctx_chars": 0, "t_end": 1791528453.6921322, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9976, "lo95": 0.9968, "mean": 1.0288, "ev_only": 0.9996, "ref_ms": 4.47926, "cand_ms": 4.49011, "n_trials": 203, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.002, "r_wall_s": 18.28, "compile_s": 2.23, "r_error": "", "src_len": 879, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1530, "tout": 515, "ts": 1791528435.3561528, "chk": null, "code_len": 879}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1530, "started": 1791528429.6476352}
{"ep": "h1-00330", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.3946, "speedup": 4.3946, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.6, "calls": 2, "tokens_in": 5109, "tokens_out": 4856, "ctx_chars": 0, "t_end": 1791528454.1946151, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.3946, "lo95": 4.3854, "mean": 4.5037, "ev_only": 4.4106, "ref_ms": 16.06411, "cand_ms": 3.65545, "n_trials": 79, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9994, "r_wall_s": 35.39, "compile_s": 1.86, "r_error": "", "src_len": 2136, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1574, "tout": 3639, "ts": 1791528328.3938234, "chk": "ok", "code_len": 2136}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3535, "tout": 1217, "ts": 1791528418.747584, "chk": null, "code_len": 2136}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1574, "started": 1791528295.5757039}
{"ep": "h1-00331", "task": "L2_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1334, "speedup": 1.1334, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.0, "calls": 2, "tokens_in": 15380, "tokens_out": 2715, "ctx_chars": 11535, "t_end": 1791528455.8650043, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1334, "lo95": 1.1328, "mean": 1.1343, "ev_only": 1.1341, "ref_ms": 20.10949, "cand_ms": 17.74251, "n_trials": 62, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0587, "r_wall_s": 25.06, "compile_s": 2.08, "r_error": "", "src_len": 2444, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6865, "tout": 1538, "ts": 1791528315.829363, "chk": "ok", "code_len": 2444}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8515, "tout": 1177, "ts": 1791528430.765647, "chk": null, "code_len": 2444}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6865, "started": 1791528300.8432667}
{"ep": "h1-00329", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1109, "speedup": 1.1109, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 169.5, "calls": 2, "tokens_in": 4419, "tokens_out": 2551, "ctx_chars": 0, "t_end": 1791528456.6729858, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1109, "lo95": 1.1096, "mean": 1.1095, "ev_only": 1.1106, "ref_ms": 31.42392, "cand_ms": 28.28712, "n_trials": 56, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0519, "r_wall_s": 136.31, "compile_s": 3.09, "r_error": "", "src_len": 1333, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 1877, "ts": 1791528305.1298773, "chk": "ok", "code_len": 1333}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2736, "tout": 674, "ts": 1791528320.2999399, "chk": null, "code_len": 1333}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1683, "started": 1791528287.1648686}
{"ep": "h1-00340", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0353, "speedup": 1.0353, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 135.5, "calls": 2, "tokens_in": 12276, "tokens_out": 2207, "ctx_chars": 9028, "t_end": 1791528461.6343384, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0353, "lo95": 1.0346, "mean": 1.0355, "ev_only": 1.0355, "ref_ms": 8.27176, "cand_ms": 7.98983, "n_trials": 145, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0058, "r_wall_s": 31.66, "compile_s": 2.02, "r_error": "", "src_len": 1195, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 1521, "ts": 1791528340.0803823, "chk": "ok", "code_len": 1195}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6738, "tout": 686, "ts": 1791528429.881898, "chk": null, "code_len": 1195}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5538, "started": 1791528326.0919907}
{"ep": "h1-00282", "task": "L1_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9957, "speedup": 0.9957, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 402.9, "calls": 2, "tokens_in": 12024, "tokens_out": 1398, "ctx_chars": 9033, "t_end": 1791528462.844998, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9957, "lo95": 0.994, "mean": 0.9951, "ev_only": 0.9948, "ref_ms": 8.02828, "cand_ms": 8.06288, "n_trials": 130, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 76.4, "compile_s": 2.11, "r_error": "", "src_len": 813, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 943, "ts": 1791528071.4569137, "chk": "ok", "code_len": 813}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6538, "tout": 455, "ts": 1791528386.2236152, "chk": null, "code_len": 813}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5486, "started": 1791528059.9185097}
{"ep": "h1-00322", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1454, "speedup": 0.1454, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 214.5, "calls": 2, "tokens_in": 8864, "tokens_out": 5477, "ctx_chars": 2425, "t_end": 1791528468.0770223, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.1454, "lo95": 0.1453, "mean": 0.1454, "ev_only": 0.1453, "ref_ms": 30.91022, "cand_ms": 212.63018, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9228, "r_wall_s": 90.04, "compile_s": 1.91, "r_error": "", "src_len": 3382, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3324, "tout": 3702, "ts": 1791528285.3001966, "chk": "ok", "code_len": 3382}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5540, "tout": 1775, "ts": 1791528377.654643, "chk": null, "code_len": 3382}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3324, "started": 1791528253.5495808}
{"ep": "h1-00362", "task": "L2_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0239, "speedup": 1.0239, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 59.6, "calls": 3, "tokens_in": 20995, "tokens_out": 1942, "ctx_chars": 10191, "t_end": 1791528469.363939, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0239, "lo95": 1.0194, "mean": 1.0278, "ev_only": 1.0284, "ref_ms": 8.51428, "cand_ms": 8.31521, "n_trials": 111, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0365, "r_wall_s": 33.16, "compile_s": 1.97, "r_error": "", "src_len": 1896, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6248, "tout": 995, "ts": 1791528418.8865337, "chk": "ok", "code_len": 1935}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7355, "tout": 13, "ts": 1791528428.1681607, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7392, "tout": 934, "ts": 1791528436.1321318, "chk": null, "code_len": 1896}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6248, "started": 1791528409.753808}
{"ep": "h1-00207", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 10.9061, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 731.2, "calls": 4, "tokens_in": 27616, "tokens_out": 15974, "ctx_chars": 0, "t_end": 1791528471.2209096, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 10.9061, "lo95": 10.0887, "mean": 10.4373, "ev_only": 10.912, "ref_ms": 12.18584, "cand_ms": 1.11734, "n_trials": 113, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.7233, "r_wall_s": 71.01, "compile_s": 11.61, "r_error": "", "src_len": 5010, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2677, "tout": 5040, "ts": 1791527785.8180022, "chk": "incorrect", "code_len": 4282}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5464, "tout": 4813, "ts": 1791527858.6416547, "chk": "incorrect", "code_len": 4842}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8333, "tout": 3603, "ts": 1791528041.6163146, "chk": "ok", "code_len": 5010}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11142, "tout": 2518, "ts": 1791528399.9418201, "chk": null, "code_len": 5010}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2677, "started": 1791527739.998164}
{"ep": "h1-00281", "task": "L3_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.2555, "speedup": 2.2555, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 418.2, "calls": 5, "tokens_in": 89736, "tokens_out": 26462, "ctx_chars": 2425, "t_end": 1791528476.631002, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.2555, "lo95": 2.2441, "mean": 2.2392, "ev_only": 2.2645, "ref_ms": 12.13146, "cand_ms": 5.3787, "n_trials": 111, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4715, "r_wall_s": 96.13, "compile_s": 2.04, "r_error": "", "src_len": 2425, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3591, "tout": 10765, "ts": 1791528156.3772101, "chk": "incorrect", "code_len": 3537}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 14492, "tout": 3759, "ts": 1791528205.7666132, "chk": "incorrect", "code_len": 3520}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 18387, "tout": 5637, "ts": 1791528301.4208448, "chk": "incorrect", "code_len": 3591}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 24160, "tout": 4829, "ts": 1791528366.2931087, "chk": "forbidden", "code_len": 2427}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 29106, "tout": 1472, "ts": 1791528380.393349, "chk": null, "code_len": 2425}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "forbidden", null], "first_tin": 3591, "started": 1791528058.4563832}
{"ep": "h1-00332", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3954, "speedup": 1.3954, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 181.0, "calls": 2, "tokens_in": 5205, "tokens_out": 3631, "ctx_chars": 0, "t_end": 1791528483.2137465, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3954, "lo95": 1.3928, "mean": 1.3978, "ev_only": 1.3981, "ref_ms": 19.28516, "cand_ms": 13.82083, "n_trials": 77, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0578, "r_wall_s": 45.22, "compile_s": 2.0, "r_error": "", "src_len": 2046, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1729, "tout": 2518, "ts": 1791528324.169864, "chk": "ok", "code_len": 2046}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3476, "tout": 1113, "ts": 1791528437.3070233, "chk": null, "code_len": 2046}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1729, "started": 1791528302.2374039}
{"ep": "h1-00253", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 55.2737, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 538.7, "calls": 3, "tokens_in": 31337, "tokens_out": 17869, "ctx_chars": 10613, "t_end": 1791528493.1058164, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 55.2737, "lo95": 55.0418, "mean": 54.3194, "ev_only": 56.4517, "ref_ms": 36.38092, "cand_ms": 0.6582, "n_trials": 38, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.8822, "r_wall_s": 27.29, "compile_s": 12.41, "r_error": "", "src_len": 7282, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6522, "tout": 10586, "ts": 1791528051.1291218, "chk": "no_custom_kernel", "code_len": 7307}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10588, "tout": 3799, "ts": 1791528427.4645963, "chk": "ok", "code_len": 7282}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14227, "tout": 3484, "ts": 1791528465.7528732, "chk": null, "code_len": 7282}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6522, "started": 1791527954.3581111}
{"ep": "h1-00364", "task": "L2_003", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2605, "speedup": 1.2605, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.0, "calls": 1, "tokens_in": 1900, "tokens_out": 6209, "ctx_chars": 0, "t_end": 1791528494.5851963, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2605, "lo95": 1.2599, "mean": 1.2613, "ev_only": 1.2597, "ref_ms": 29.08354, "cand_ms": 23.07252, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2277, "r_wall_s": 27.78, "compile_s": 1.92, "r_error": "", "src_len": 2698, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1900, "tout": 6209, "ts": 1791528466.5935447, "chk": null, "code_len": 2698}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1900, "started": 1791528414.5665097}
{"ep": "h1-00346", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.087, "speedup": 2.087, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 150.1, "calls": 2, "tokens_in": 7001, "tokens_out": 4723, "ctx_chars": 0, "t_end": 1791528498.131135, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.087, "lo95": 2.0835, "mean": 2.0851, "ev_only": 2.0906, "ref_ms": 12.69204, "cand_ms": 6.08134, "n_trials": 92, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4828, "r_wall_s": 56.52, "compile_s": 2.0, "r_error": "", "src_len": 2788, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2484, "tout": 3166, "ts": 1791528375.2913606, "chk": "ok", "code_len": 2788}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4517, "tout": 1557, "ts": 1791528441.4866176, "chk": null, "code_len": 2788}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2484, "started": 1791528347.995494}
{"ep": "h1-00307", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5675, "speedup": 0.5675, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 318.5, "calls": 2, "tokens_in": 14607, "tokens_out": 3910, "ctx_chars": 11132, "t_end": 1791528498.3077316, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.5675, "lo95": 0.5673, "mean": 0.5678, "ev_only": 0.5672, "ref_ms": 3.63685, "cand_ms": 6.40858, "n_trials": 182, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9995, "r_wall_s": 102.72, "compile_s": 1.98, "r_error": "", "src_len": 2371, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 2716, "ts": 1791528204.08096, "chk": "ok", "code_len": 2371}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8181, "tout": 1194, "ts": 1791528394.6970768, "chk": null, "code_len": 2371}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6426, "started": 1791528179.8338342}
{"ep": "h1-00319", "task": "L3_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9466, "speedup": 0.9466, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.3, "calls": 3, "tokens_in": 15966, "tokens_out": 2337, "ctx_chars": 6513, "t_end": 1791528506.584856, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9466, "lo95": 0.9454, "mean": 0.9485, "ev_only": 0.9462, "ref_ms": 33.67856, "cand_ms": 35.58013, "n_trials": 34, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0011, "r_wall_s": 188.69, "compile_s": 3.28, "r_error": "", "src_len": 2317, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4416, "tout": 1214, "ts": 1791528256.296187, "chk": "ok", "code_len": 2317}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5742, "tout": 42, "ts": 1791528307.796799, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5808, "tout": 1081, "ts": 1791528317.8381803, "chk": null, "code_len": 2317}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4416, "started": 1791528245.2948601}
{"ep": "h1-00308", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.1549, "speedup": 0.1549, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 322.3, "calls": 3, "tokens_in": 16407, "tokens_out": 13143, "ctx_chars": 0, "t_end": 1791528509.1667354, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.1549, "lo95": 0.1547, "mean": 0.1563, "ev_only": 0.1543, "ref_ms": 2.17042, "cand_ms": 14.01437, "n_trials": 117, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9999, "r_wall_s": 177.35, "compile_s": 13.57, "r_error": "", "src_len": 7236, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1813, "tout": 5883, "ts": 1791528235.6821632, "chk": "no_custom_kernel", "code_len": 6754}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5457, "tout": 3835, "ts": 1791528278.6430466, "chk": "ok", "code_len": 7236}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9137, "tout": 3425, "ts": 1791528331.7571766, "chk": null, "code_len": 7236}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1813, "started": 1791528186.8252592}
{"ep": "h1-00351", "task": "L1_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8848, "speedup": 1.8848, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.8, "calls": 1, "tokens_in": 6947, "tokens_out": 1620, "ctx_chars": 10864, "t_end": 1791528510.7055697, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.8848, "lo95": 1.8834, "mean": 1.883, "ev_only": 1.8883, "ref_ms": 3.73507, "cand_ms": 1.98168, "n_trials": 230, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 127.41, "compile_s": 2.02, "r_error": "", "src_len": 3412, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6947, "tout": 1620, "ts": 1791528382.1704464, "chk": null, "code_len": 3412}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6947, "started": 1791528367.9138298}
{"ep": "h1-00297", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1735, "speedup": 0.1735, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 396.1, "calls": 2, "tokens_in": 17233, "tokens_out": 7915, "ctx_chars": 10384, "t_end": 1791528522.3085039, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.1735, "lo95": 0.1732, "mean": 0.1738, "ev_only": 0.1727, "ref_ms": 3.64438, "cand_ms": 21.00997, "n_trials": 75, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9728, "r_wall_s": 194.62, "compile_s": 3.4, "r_error": "", "src_len": 4124, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 5855, "ts": 1791528178.447961, "chk": "ok", "code_len": 4124}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9936, "tout": 2060, "ts": 1791528327.2525182, "chk": null, "code_len": 4124}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791528126.2160726}
{"ep": "h1-00288", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 11.1482, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 443.6, "calls": 3, "tokens_in": 16991, "tokens_out": 12997, "ctx_chars": 0, "t_end": 1791528522.3150983, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 11.1482, "lo95": 11.0843, "mean": 10.5188, "ev_only": 11.156, "ref_ms": 12.04912, "cand_ms": 1.08081, "n_trials": 114, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.7001, "r_wall_s": 197.78, "compile_s": 16.31, "r_error": "", "src_len": 5051, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2677, "tout": 5469, "ts": 1791528127.9420347, "chk": "incorrect", "code_len": 5202}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5680, "tout": 4915, "ts": 1791528208.6310246, "chk": "ok", "code_len": 5051}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8634, "tout": 2613, "ts": 1791528324.392577, "chk": null, "code_len": 5051}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2677, "started": 1791528078.6844044}
{"ep": "h1-00345", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0601, "speedup": 1.0601, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.2, "calls": 2, "tokens_in": 6415, "tokens_out": 7190, "ctx_chars": 0, "t_end": 1791528523.9142437, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0601, "lo95": 1.0597, "mean": 1.0604, "ev_only": 1.0606, "ref_ms": 27.88019, "cand_ms": 26.30082, "n_trials": 48, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0163, "r_wall_s": 24.37, "compile_s": 1.98, "r_error": "", "src_len": 4490, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1810, "tout": 4755, "ts": 1791528404.05609, "chk": "ok", "code_len": 4490}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4605, "tout": 2435, "ts": 1791528499.295528, "chk": null, "code_len": 4490}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1810, "started": 1791528362.0585604}
{"ep": "h1-00348", "task": "L2_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0017, "speedup": 1.0017, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.0, "calls": 3, "tokens_in": 23460, "tokens_out": 2130, "ctx_chars": 11755, "t_end": 1791528524.1992683, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0017, "lo95": 1.0012, "mean": 1.0201, "ev_only": 1.0021, "ref_ms": 72.76733, "cand_ms": 72.64692, "n_trials": 19, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0155, "r_wall_s": 115.46, "compile_s": 2.21, "r_error": "", "src_len": 1839, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6938, "tout": 1174, "ts": 1791528373.423746, "chk": "ok", "code_len": 1895}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8224, "tout": 50, "ts": 1791528396.3696475, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8298, "tout": 906, "ts": 1791528408.635383, "chk": null, "code_len": 1839}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6938, "started": 1791528360.2206106}
{"ep": "h1-00245", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.1129, "speedup": 5.1129, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 615.9, "calls": 3, "tokens_in": 16556, "tokens_out": 15566, "ctx_chars": 0, "t_end": 1791528526.3748627, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 5.1129, "lo95": 3.8472, "mean": 5.0257, "ev_only": 5.11, "ref_ms": 103.99778, "cand_ms": 20.34038, "n_trials": 15, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8392, "r_wall_s": 118.72, "compile_s": 14.69, "r_error": "", "src_len": 6363, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1972, "tout": 9237, "ts": 1791527992.4916692, "chk": "no_custom_kernel", "code_len": 6385}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5697, "tout": 3292, "ts": 1791528036.4062226, "chk": "ok", "code_len": 6363}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8887, "tout": 3037, "ts": 1791528407.5420122, "chk": null, "code_len": 6363}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1972, "started": 1791527910.497274}
{"ep": "h1-00344", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4768, "speedup": 1.4768, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 190.9, "calls": 2, "tokens_in": 13985, "tokens_out": 1986, "ctx_chars": 10756, "t_end": 1791528528.1932309, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4768, "lo95": 1.4659, "mean": 1.4758, "ev_only": 1.4793, "ref_ms": 14.31389, "cand_ms": 9.69244, "n_trials": 59, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0669, "r_wall_s": 152.04, "compile_s": 2.08, "r_error": "", "src_len": 1203, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6463, "tout": 1333, "ts": 1791528354.217655, "chk": "ok", "code_len": 1203}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7522, "tout": 653, "ts": 1791528375.30083, "chk": null, "code_len": 1203}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6463, "started": 1791528337.3194473}
{"ep": "h1-00367", "task": "L3_034", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8252, "speedup": 0.8252, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 90.9, "calls": 3, "tokens_in": 16408, "tokens_out": 2377, "ctx_chars": 6034, "t_end": 1791528530.346333, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8252, "lo95": 0.7964, "mean": 0.8704, "ev_only": 0.8253, "ref_ms": 29.87624, "cand_ms": 36.20352, "n_trials": 17, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1713, "r_wall_s": 57.22, "compile_s": 2.62, "r_error": "", "src_len": 2268, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4546, "tout": 1230, "ts": 1791528451.1166184, "chk": "ok", "code_len": 2268}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5888, "tout": 62, "ts": 1791528463.9870765, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5974, "tout": 1085, "ts": 1791528473.098916, "chk": null, "code_len": 2268}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4546, "started": 1791528439.4950588}
{"ep": "h1-00293", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0032, "speedup": 1.0032, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 415.5, "calls": 4, "tokens_in": 39182, "tokens_out": 14746, "ctx_chars": 6513, "t_end": 1791528532.6520102, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0032, "lo95": 1.0024, "mean": 1.0031, "ev_only": 1.0022, "ref_ms": 23.50964, "cand_ms": 23.43475, "n_trials": 65, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0218, "r_wall_s": 152.43, "compile_s": 13.97, "r_error": "", "src_len": 6211, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5439, "tout": 4021, "ts": 1791528151.2890098, "chk": "incorrect", "code_len": 4827}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8316, "tout": 3819, "ts": 1791528193.295589, "chk": "ok", "code_len": 4629}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11015, "tout": 3769, "ts": 1791528342.6799903, "chk": "ok", "code_len": 6211}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14412, "tout": 3137, "ts": 1791528380.154664, "chk": null, "code_len": 6211}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", null], "first_tin": 5439, "started": 1791528117.1543057}
{"ep": "h1-00286", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2902, "speedup": 1.2902, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 476.2, "calls": 2, "tokens_in": 4961, "tokens_out": 4237, "ctx_chars": 0, "t_end": 1791528541.3235824, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2902, "lo95": 1.2896, "mean": 1.2878, "ev_only": 1.2882, "ref_ms": 7.28354, "cand_ms": 5.6453, "n_trials": 192, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 205.85, "compile_s": 3.22, "r_error": "", "src_len": 2380, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1572, "tout": 2641, "ts": 1791528087.513108, "chk": "ok", "code_len": 2380}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3389, "tout": 1596, "ts": 1791528335.3317108, "chk": null, "code_len": 2380}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1572, "started": 1791528065.1608343}
{"ep": "h1-00356", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0591, "speedup": 1.0591, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 168.7, "calls": 2, "tokens_in": 15384, "tokens_out": 4523, "ctx_chars": 11062, "t_end": 1791528546.6703787, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0591, "lo95": 1.0562, "mean": 1.0588, "ev_only": 1.0603, "ref_ms": 12.79688, "cand_ms": 12.08271, "n_trials": 109, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0382, "r_wall_s": 31.87, "compile_s": 2.09, "r_error": "", "src_len": 3067, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6695, "tout": 3012, "ts": 1791528405.4172769, "chk": "ok", "code_len": 3067}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8689, "tout": 1511, "ts": 1791528514.745144, "chk": null, "code_len": 3067}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6695, "started": 1791528378.013915}
{"ep": "h1-00369", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.6097, "speedup": 4.6097, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 97.2, "calls": 2, "tokens_in": 13588, "tokens_out": 3820, "ctx_chars": 9438, "t_end": 1791528548.322777, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.6097, "lo95": 4.5604, "mean": 4.5229, "ev_only": 4.6408, "ref_ms": 7.39955, "cand_ms": 1.60522, "n_trials": 179, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 36.69, "compile_s": 1.89, "r_error": "", "src_len": 2380, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5861, "tout": 2411, "ts": 1791528472.34248, "chk": "ok", "code_len": 2380}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7727, "tout": 1409, "ts": 1791528511.5205696, "chk": null, "code_len": 2380}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5861, "started": 1791528451.1587467}
{"ep": "h1-00372", "task": "L2_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9898, "speedup": 0.9898, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 95.6, "calls": 3, "tokens_in": 23702, "tokens_out": 2266, "ctx_chars": 11755, "t_end": 1791528549.8205225, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9898, "lo95": 0.9895, "mean": 0.9898, "ev_only": 0.99, "ref_ms": 72.79624, "cand_ms": 73.54592, "n_trials": 20, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0286, "r_wall_s": 48.53, "compile_s": 1.89, "r_error": "", "src_len": 1870, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6938, "tout": 1265, "ts": 1791528469.1753576, "chk": "ok", "code_len": 1948}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8315, "tout": 110, "ts": 1791528493.434716, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8449, "tout": 891, "ts": 1791528501.2642124, "chk": null, "code_len": 1870}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6938, "started": 1791528454.1949036}
{"ep": "h1-00327", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.9381, "speedup": 3.9381, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 272.1, "calls": 2, "tokens_in": 8287, "tokens_out": 9319, "ctx_chars": 0, "t_end": 1791528552.625354, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.9381, "lo95": 3.9366, "mean": 4.1739, "ev_only": 3.9291, "ref_ms": 3.72736, "cand_ms": 0.94648, "n_trials": 206, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 142.99, "compile_s": 15.15, "r_error": "", "src_len": 5859, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2325, "tout": 6153, "ts": 1791528353.069335, "chk": "ok", "code_len": 5859}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5962, "tout": 3166, "ts": 1791528408.7964516, "chk": null, "code_len": 5859}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2325, "started": 1791528300.8661995}
{"ep": "h1-00381", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0437, "speedup": 1.0437, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 72.3, "calls": 2, "tokens_in": 11952, "tokens_out": 2046, "ctx_chars": 8989, "t_end": 1791528555.534404, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0437, "lo95": 1.0429, "mean": 1.0433, "ev_only": 1.0439, "ref_ms": 30.3498, "cand_ms": 29.07996, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 41.94, "compile_s": 1.98, "r_error": "", "src_len": 921, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5552, "tout": 1551, "ts": 1791528497.757442, "chk": "ok", "code_len": 921}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6400, "tout": 495, "ts": 1791528513.1766047, "chk": null, "code_len": 921}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5552, "started": 1791528483.214017}
{"ep": "h1-00350", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.034, "speedup": 1.034, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 192.5, "calls": 2, "tokens_in": 4495, "tokens_out": 2105, "ctx_chars": 0, "t_end": 1791528560.0646818, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.034, "lo95": 1.0335, "mean": 1.0478, "ev_only": 1.0347, "ref_ms": 8.23447, "cand_ms": 7.96345, "n_trials": 154, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0041, "r_wall_s": 20.61, "compile_s": 2.26, "r_error": "", "src_len": 1067, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1706, "tout": 1453, "ts": 1791528380.4083757, "chk": "ok", "code_len": 1067}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2789, "tout": 652, "ts": 1791528539.3550954, "chk": null, "code_len": 1067}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1706, "started": 1791528367.5973117}
{"ep": "h1-00269", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.5763, "speedup": 2.5763, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 553.3, "calls": 2, "tokens_in": 6135, "tokens_out": 8986, "ctx_chars": 0, "t_end": 1791528563.625181, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.5763, "lo95": 2.5705, "mean": 2.5931, "ev_only": 2.5943, "ref_ms": 3.68451, "cand_ms": 1.43013, "n_trials": 200, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 160.35, "compile_s": 20.8, "r_error": "", "src_len": 4969, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 6574, "ts": 1791528069.7301795, "chk": "ok", "code_len": 4969}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4546, "tout": 2412, "ts": 1791528402.2570002, "chk": null, "code_len": 4969}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791528010.352692}
{"ep": "h1-00289", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 8.2157, "speedup": 8.2157, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 479.3, "calls": 2, "tokens_in": 18458, "tokens_out": 17136, "ctx_chars": 11175, "t_end": 1791528563.8164287, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 8.2157, "lo95": 8.0069, "mean": 8.2894, "ev_only": 8.2015, "ref_ms": 4.48802, "cand_ms": 0.54627, "n_trials": 203, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 167.77, "compile_s": 21.79, "r_error": "", "src_len": 7840, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 13371, "ts": 1791528203.6685934, "chk": "ok", "code_len": 7840}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11391, "tout": 3765, "ts": 1791528395.859378, "chk": null, "code_len": 7840}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7067, "started": 1791528084.4920144}
{"ep": "h1-00298", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 26.9654, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 437.9, "calls": 3, "tokens_in": 20772, "tokens_out": 10241, "ctx_chars": 6034, "t_end": 1791528565.6999996, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 26.9654, "lo95": 26.6239, "mean": 26.7175, "ev_only": 26.9139, "ref_ms": 29.42383, "cand_ms": 1.09117, "n_trials": 41, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.8768, "r_wall_s": 58.94, "compile_s": 11.98, "r_error": "", "src_len": 3941, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 6045, "ts": 1791528181.001872, "chk": "no_custom_kernel", "code_len": 3963}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7044, "tout": 2223, "ts": 1791528387.6407943, "chk": "ok", "code_len": 3941}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9180, "tout": 1973, "ts": 1791528506.7144966, "chk": null, "code_len": 3941}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 4548, "started": 1791528127.7881246}
{"ep": "h1-00347", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.641, "speedup": 1.641, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 214.4, "calls": 2, "tokens_in": 8749, "tokens_out": 7274, "ctx_chars": 3355, "t_end": 1791528572.1052349, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.641, "lo95": 1.64, "mean": 1.6409, "ev_only": 1.6422, "ref_ms": 20.45797, "cand_ms": 12.46678, "n_trials": 54, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 36.63, "compile_s": 2.6, "r_error": "", "src_len": 3246, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3296, "tout": 5510, "ts": 1791528406.9150274, "chk": "ok", "code_len": 3246}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5453, "tout": 1764, "ts": 1791528535.361567, "chk": null, "code_len": 3246}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3296, "started": 1791528357.659604}
{"ep": "h1-00343", "task": "L1_006", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.839, "speedup": 0.839, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.1, "calls": 4, "tokens_in": 29833, "tokens_out": 4052, "ctx_chars": 9033, "t_end": 1791528574.8971198, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.839, "lo95": 0.8386, "mean": 0.8433, "ev_only": 0.8396, "ref_ms": 3.70194, "cand_ms": 4.41243, "n_trials": 208, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.996, "r_wall_s": 28.49, "compile_s": 2.43, "r_error": "", "src_len": 2084, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 1429, "ts": 1791528348.1398914, "chk": "incorrect", "code_len": 2595}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7050, "tout": 1355, "ts": 1791528389.0078268, "chk": "ok", "code_len": 2084}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8514, "tout": 243, "ts": 1791528537.4370477, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8781, "tout": 1025, "ts": 1791528546.301464, "chk": null, "code_len": 2084}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 5488, "started": 1791528333.8458493}
{"ep": "h1-00376", "task": "L1_083", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.7521, "speedup": 2.7521, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 113.0, "calls": 1, "tokens_in": 6377, "tokens_out": 1371, "ctx_chars": 10362, "t_end": 1791528575.81403, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.7521, "lo95": 2.7447, "mean": 2.598, "ev_only": 2.7467, "ref_ms": 2.92679, "cand_ms": 1.06346, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 99.45, "compile_s": 3.72, "r_error": "", "src_len": 2764, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6377, "tout": 1371, "ts": 1791528475.4669368, "chk": null, "code_len": 2764}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6377, "started": 1791528462.8452492}
{"ep": "h1-00385", "task": "L3_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 78.1, "calls": 1, "tokens_in": 3022, "tokens_out": 2505, "ctx_chars": 0, "t_end": 1791528576.3994696, "error": "RuntimeError: Error building extension 'bn_relu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bn_relu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 56.64, "compile_s": 56.61, "r_error": "RuntimeError: Error building extension 'bn_relu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bn_relu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "src_len": 5633, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3022, "tout": 2505, "ts": 1791528519.7090883, "chk": null, "code_len": 5633}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3022, "started": 1791528498.3079555}
{"ep": "h1-00341", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2073, "speedup": 1.2073, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 252.4, "calls": 2, "tokens_in": 14583, "tokens_out": 22664, "ctx_chars": 0, "t_end": 1791528582.973927, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2073, "lo95": 1.1204, "mean": 1.1892, "ev_only": 1.2082, "ref_ms": 44.15521, "cand_ms": 36.57283, "n_trials": 32, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.069, "r_wall_s": 57.91, "compile_s": 12.63, "r_error": "", "src_len": 16133, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 14820, "ts": 1791528454.0624142, "chk": "ok", "code_len": 16133}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11559, "tout": 7844, "ts": 1791528524.657597, "chk": null, "code_len": 16133}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791528330.5386198}
{"ep": "h1-00358", "task": "L3_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8423, "speedup": 0.8423, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 199.8, "calls": 3, "tokens_in": 12769, "tokens_out": 3945, "ctx_chars": 0, "t_end": 1791528583.2518795, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8423, "lo95": 0.8421, "mean": 0.8421, "ev_only": 0.843, "ref_ms": 4.00449, "cand_ms": 4.75417, "n_trials": 179, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3799, "r_wall_s": 53.92, "compile_s": 2.27, "r_error": "", "src_len": 3428, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2691, "tout": 2212, "ts": 1791528405.733911, "chk": "ok", "code_len": 3638}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5015, "tout": 24, "ts": 1791528515.1836898, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5063, "tout": 1709, "ts": 1791528529.034479, "chk": null, "code_len": 3428}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2691, "started": 1791528383.4110737}
{"ep": "h1-00389", "task": "L2_053", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0126, "speedup": 1.0126, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 62.1, "calls": 1, "tokens_in": 6385, "tokens_out": 592, "ctx_chars": 10749, "t_end": 1791528584.4148297, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0126, "lo95": 1.0116, "mean": 1.0125, "ev_only": 1.0118, "ref_ms": 15.9172, "cand_ms": 15.71985, "n_trials": 98, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0056, "r_wall_s": 56.08, "compile_s": 2.43, "r_error": "", "src_len": 1182, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6385, "tout": 592, "ts": 1791528528.20608, "chk": null, "code_len": 1182}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6385, "started": 1791528522.308751}
{"ep": "h1-00360", "task": "L3_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7174, "speedup": 0.7174, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 195.6, "calls": 5, "tokens_in": 47965, "tokens_out": 12153, "ctx_chars": 0, "t_end": 1791528588.274031, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7174, "lo95": 0.4939, "mean": 0.7313, "ev_only": 0.7201, "ref_ms": 3.60352, "cand_ms": 5.02312, "n_trials": 163, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0013, "r_wall_s": 61.79, "compile_s": 4.19, "r_error": "", "src_len": 3078, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2843, "tout": 4640, "ts": 1791528433.7170322, "chk": "incorrect", "code_len": 4791}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7614, "tout": 2254, "ts": 1791528461.6771102, "chk": "incorrect", "code_len": 4104}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9999, "tout": 3468, "ts": 1791528499.9122908, "chk": "ok", "code_len": 3078}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13576, "tout": 310, "ts": 1791528513.9205809, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13933, "tout": 1481, "ts": 1791528526.4342852, "chk": null, "code_len": 3078}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 2843, "started": 1791528392.641595}
{"ep": "h1-00379", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0199, "speedup": 1.0199, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.2, "calls": 2, "tokens_in": 4693, "tokens_out": 3880, "ctx_chars": 0, "t_end": 1791528588.4591525, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0199, "lo95": 1.0183, "mean": 1.0176, "ev_only": 1.0209, "ref_ms": 31.56767, "cand_ms": 30.95274, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1836, "r_wall_s": 38.05, "compile_s": 1.97, "r_error": "", "src_len": 1701, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 2573, "ts": 1791528524.5367477, "chk": "ok", "code_len": 1701}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3010, "tout": 1307, "ts": 1791528550.3260012, "chk": null, "code_len": 1701}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1683, "started": 1791528491.566674}
{"ep": "h1-00371", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3839, "speedup": 1.3839, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 147.9, "calls": 2, "tokens_in": 15020, "tokens_out": 4094, "ctx_chars": 11132, "t_end": 1791528601.6202078, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.3839, "lo95": 1.3792, "mean": 1.3879, "ev_only": 1.3823, "ref_ms": 10.97802, "cand_ms": 7.93244, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0701, "r_wall_s": 81.57, "compile_s": 3.24, "r_error": "", "src_len": 3214, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6456, "tout": 2494, "ts": 1791528473.6275356, "chk": "ok", "code_len": 3214}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8564, "tout": 1600, "ts": 1791528519.2449741, "chk": null, "code_len": 3214}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6456, "started": 1791528453.6923895}
{"ep": "h1-00357", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.1997, "speedup": 7.1997, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 218.6, "calls": 2, "tokens_in": 5925, "tokens_out": 1363, "ctx_chars": 2425, "t_end": 1791528601.8921576, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.1997, "lo95": 7.1905, "mean": 7.1425, "ev_only": 7.419, "ref_ms": 3.5737, "cand_ms": 0.49637, "n_trials": 219, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 46.62, "compile_s": 2.18, "r_error": "", "src_len": 826, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2480, "tout": 853, "ts": 1791528390.917255, "chk": "ok", "code_len": 826}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3445, "tout": 510, "ts": 1791528554.7082949, "chk": null, "code_len": 826}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2480, "started": 1791528383.294246}
{"ep": "h1-00318", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.3269, "speedup": 3.3269, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 372.2, "calls": 3, "tokens_in": 20559, "tokens_out": 17054, "ctx_chars": 0, "t_end": 1791528606.3340175, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 3.3269, "lo95": 3.3196, "mean": 3.3005, "ev_only": 3.3962, "ref_ms": 2.28342, "cand_ms": 0.68635, "n_trials": 206, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 89.8, "compile_s": 17.3, "r_error": "", "src_len": 8907, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 7949, "ts": 1791528299.5707407, "chk": "no_custom_kernel", "code_len": 8937}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6964, "tout": 4813, "ts": 1791528363.839083, "chk": "ok", "code_len": 8907}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11580, "tout": 4292, "ts": 1791528516.492681, "chk": null, "code_len": 8907}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2015, "started": 1791528234.10206}
{"ep": "h1-00354", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.5268, "speedup": 0.5268, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 236.1, "calls": 2, "tokens_in": 7164, "tokens_out": 10762, "ctx_chars": 0, "t_end": 1791528608.7926219, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.5268, "lo95": 0.5244, "mean": 0.5255, "ev_only": 0.5253, "ref_ms": 20.20192, "cand_ms": 38.3462, "n_trials": 30, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0005, "r_wall_s": 124.49, "compile_s": 28.9, "r_error": "", "src_len": 6574, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1729, "tout": 7423, "ts": 1791528437.458535, "chk": "ok", "code_len": 6593}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5435, "tout": 3339, "ts": 1791528484.2704356, "chk": null, "code_len": 6574}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1729, "started": 1791528372.6496997}
{"ep": "h1-00337", "task": "L1_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9628, "speedup": 0.9628, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 300.7, "calls": 4, "tokens_in": 20904, "tokens_out": 4848, "ctx_chars": 0, "t_end": 1791528609.871552, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9628, "lo95": 0.9625, "mean": 0.963, "ev_only": 0.9664, "ref_ms": 4.37984, "cand_ms": 4.54889, "n_trials": 236, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.029, "r_wall_s": 45.7, "compile_s": 10.79, "r_error": "", "src_len": 3396, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2216, "tout": 1635, "ts": 1791528326.1829603, "chk": "compile_error", "code_len": 3126}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5100, "tout": 1333, "ts": 1791528384.7889297, "chk": "ok", "code_len": 3134}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6545, "tout": 474, "ts": 1791528551.9799342, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7043, "tout": 1406, "ts": 1791528563.8289785, "chk": null, "code_len": 3396}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 2216, "started": 1791528309.169275}
{"ep": "h1-00380", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8928, "speedup": 0.8928, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 138.5, "calls": 2, "tokens_in": 16235, "tokens_out": 10777, "ctx_chars": 6513, "t_end": 1791528615.112034, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8928, "lo95": 0.8892, "mean": 0.8578, "ev_only": 0.8939, "ref_ms": 5.7849, "cand_ms": 6.4793, "n_trials": 159, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3983, "r_wall_s": 42.97, "compile_s": 2.82, "r_error": "", "src_len": 7669, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6068, "tout": 6907, "ts": 1791528535.1428578, "chk": "ok", "code_len": 7669}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10167, "tout": 3870, "ts": 1791528572.0993738, "chk": null, "code_len": 7669}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6068, "started": 1791528476.631252}
{"ep": "h1-00334", "task": "L1_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.1514, "speedup": 0.1514, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 312.1, "calls": 2, "tokens_in": 4351, "tokens_out": 2602, "ctx_chars": 0, "t_end": 1791528618.8554552, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.1514, "lo95": 0.1513, "mean": 0.1516, "ev_only": 0.1512, "ref_ms": 5.2928, "cand_ms": 34.96341, "n_trials": 45, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 67.17, "compile_s": 2.86, "r_error": "", "src_len": 2183, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1474, "tout": 1294, "ts": 1791528319.9610107, "chk": "ok", "code_len": 2257}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2877, "tout": 1308, "ts": 1791528417.8791838, "chk": null, "code_len": 2183}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1474, "started": 1791528306.7876856}
{"ep": "h1-00374", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3106, "speedup": 1.3106, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.9, "calls": 2, "tokens_in": 12780, "tokens_out": 4734, "ctx_chars": 9033, "t_end": 1791528620.5731091, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.3106, "lo95": 1.3098, "mean": 1.3117, "ev_only": 1.3106, "ref_ms": 7.71967, "cand_ms": 5.89001, "n_trials": 164, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 56.8, "compile_s": 2.82, "r_error": "", "src_len": 2368, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 3216, "ts": 1791528486.3842893, "chk": "ok", "code_len": 2368}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7292, "tout": 1518, "ts": 1791528563.67359, "chk": null, "code_len": 2368}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5488, "started": 1791528456.6732583}
{"ep": "h1-00365", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0614, "speedup": 1.0614, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.6, "calls": 2, "tokens_in": 8938, "tokens_out": 12247, "ctx_chars": 0, "t_end": 1791528630.9835758, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0614, "lo95": 1.0608, "mean": 1.0917, "ev_only": 1.0616, "ref_ms": 27.78433, "cand_ms": 26.17625, "n_trials": 49, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.022, "r_wall_s": 57.18, "compile_s": 14.07, "r_error": "", "src_len": 10026, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1810, "tout": 7467, "ts": 1791528476.7416956, "chk": "ok", "code_len": 10026}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7128, "tout": 4780, "ts": 1791528573.566599, "chk": null, "code_len": 10026}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1810, "started": 1791528417.3391364}
{"ep": "h1-00315", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.9501, "speedup": 1.9501, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 416.4, "calls": 3, "tokens_in": 15439, "tokens_out": 14021, "ctx_chars": 0, "t_end": 1791528634.4020216, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.9501, "lo95": 1.9495, "mean": 1.9487, "ev_only": 1.9503, "ref_ms": 44.29137, "cand_ms": 22.71184, "n_trials": 39, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 142.58, "compile_s": 20.69, "r_error": "", "src_len": 5466, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2039, "tout": 8098, "ts": 1791528310.142594, "chk": "no_custom_kernel", "code_len": 5520}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5273, "tout": 3010, "ts": 1791528427.0864384, "chk": "ok", "code_len": 5466}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8127, "tout": 2913, "ts": 1791528490.6073363, "chk": null, "code_len": 5466}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2039, "started": 1791528238.3384178}
{"ep": "h1-00391", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.409, "speedup": 1.409, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 113.6, "calls": 2, "tokens_in": 13986, "tokens_out": 5213, "ctx_chars": 10087, "t_end": 1791528637.5062492, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.409, "lo95": 1.408, "mean": 1.4088, "ev_only": 1.4109, "ref_ms": 19.32144, "cand_ms": 13.71249, "n_trials": 66, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 29.03, "compile_s": 2.75, "r_error": "", "src_len": 3225, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5891, "tout": 3503, "ts": 1791528555.2998955, "chk": "ok", "code_len": 3225}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8095, "tout": 1710, "ts": 1791528608.3640063, "chk": null, "code_len": 3225}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5891, "started": 1791528523.914476}
{"ep": "h1-00390", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0135, "speedup": 1.0135, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 120.0, "calls": 2, "tokens_in": 11936, "tokens_out": 1121, "ctx_chars": 9220, "t_end": 1791528642.317514, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0135, "lo95": 1.0126, "mean": 1.029, "ev_only": 1.015, "ref_ms": 8.24178, "cand_ms": 8.13177, "n_trials": 127, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 35.1, "compile_s": 2.04, "r_error": "", "src_len": 965, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5602, "tout": 620, "ts": 1791528527.8036797, "chk": "ok", "code_len": 965}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6334, "tout": 501, "ts": 1791528607.1014137, "chk": null, "code_len": 965}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5602, "started": 1791528522.3154848}
{"ep": "h1-00363", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4035, "speedup": 1.4035, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 230.6, "calls": 2, "tokens_in": 5275, "tokens_out": 5329, "ctx_chars": 0, "t_end": 1791528644.2349503, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4035, "lo95": 1.4019, "mean": 1.4068, "ev_only": 1.4047, "ref_ms": 11.08766, "cand_ms": 7.89993, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1543, "r_wall_s": 157.09, "compile_s": 5.17, "r_error": "", "src_len": 3117, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1619, "tout": 3731, "ts": 1791528447.2731895, "chk": "ok", "code_len": 3117}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3656, "tout": 1598, "ts": 1791528486.3589842, "chk": null, "code_len": 3117}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1619, "started": 1791528413.6071002}
{"ep": "h1-00375", "task": "L1_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.018, "speedup": 1.018, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 191.8, "calls": 3, "tokens_in": 19057, "tokens_out": 1908, "ctx_chars": 9033, "t_end": 1791528653.4748747, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.018, "lo95": 1.0175, "mean": 1.0397, "ev_only": 1.0193, "ref_ms": 7.51677, "cand_ms": 7.38373, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0044, "r_wall_s": 97.26, "compile_s": 2.58, "r_error": "", "src_len": 1256, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 1135, "ts": 1791528474.1153917, "chk": "ok", "code_len": 1256}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6733, "tout": 79, "ts": 1791528549.6016295, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6836, "tout": 694, "ts": 1791528556.1246102, "chk": null, "code_len": 1256}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5488, "started": 1791528461.6345758}
{"ep": "h1-00417", "task": "L2_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 68.0, "calls": 1, "tokens_in": 1776, "tokens_out": 1211, "ctx_chars": 0, "t_end": 1791528669.928299, "error": "RuntimeError: Error building extension 'ss_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=ss_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 57.0, "compile_s": 56.99, "r_error": "RuntimeError: Error building extension 'ss_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=ss_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "src_len": 2528, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1776, "tout": 1211, "ts": 1791528612.9001613, "chk": null, "code_len": 2528}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1776, "started": 1791528601.8923888}
{"ep": "h1-00397", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.4789, "speedup": 7.4789, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 131.6, "calls": 2, "tokens_in": 12949, "tokens_out": 3276, "ctx_chars": 9033, "t_end": 1791528672.9321177, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.4789, "lo95": 7.4709, "mean": 7.5831, "ev_only": 7.4825, "ref_ms": 7.99717, "cand_ms": 1.06929, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1951, "r_wall_s": 63.56, "compile_s": 2.87, "r_error": "", "src_len": 1987, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5662, "tout": 2205, "ts": 1791528560.6460497, "chk": "ok", "code_len": 1987}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7287, "tout": 1071, "ts": 1791528609.3478758, "chk": null, "code_len": 1987}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5662, "started": 1791528541.323825}
{"ep": "h1-00395", "task": "L3_022", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.3345, "speedup": 0.3345, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.8, "calls": 3, "tokens_in": 24315, "tokens_out": 5791, "ctx_chars": 6513, "t_end": 1791528673.1624792, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.3345, "lo95": 0.3088, "mean": 0.3396, "ev_only": 0.3333, "ref_ms": 9.65414, "cand_ms": 28.86045, "n_trials": 67, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0556, "r_wall_s": 78.89, "compile_s": 2.07, "r_error": "", "src_len": 5869, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6066, "tout": 2922, "ts": 1791528554.1374989, "chk": "ok", "code_len": 5910}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9100, "tout": 25, "ts": 1791528571.576183, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9149, "tout": 2844, "ts": 1791528594.1603253, "chk": null, "code_len": 5869}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6066, "started": 1791528530.3465614}
{"ep": "h1-00283", "task": "L2_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0136, "speedup": 1.0136, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 614.1, "calls": 3, "tokens_in": 25579, "tokens_out": 5620, "ctx_chars": 10177, "t_end": 1791528675.0512202, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0136, "lo95": 1.0131, "mean": 1.0135, "ev_only": 1.015, "ref_ms": 2.37405, "cand_ms": 2.34213, "n_trials": 197, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0851, "r_wall_s": 59.83, "compile_s": 3.26, "r_error": "", "src_len": 2080, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6103, "tout": 2434, "ts": 1791528085.3289933, "chk": "ok", "code_len": 1946}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8649, "tout": 2066, "ts": 1791528414.8348887, "chk": "ok", "code_len": 2080}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10827, "tout": 1120, "ts": 1791528615.177632, "chk": null, "code_len": 2080}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 6103, "started": 1791528060.9046245}
{"ep": "h1-00384", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0409, "speedup": 1.0409, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.2, "calls": 2, "tokens_in": 12196, "tokens_out": 2460, "ctx_chars": 8989, "t_end": 1791528680.348533, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0409, "lo95": 1.0385, "mean": 1.0404, "ev_only": 1.0408, "ref_ms": 30.37434, "cand_ms": 29.18015, "n_trials": 47, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0036, "r_wall_s": 112.9, "compile_s": 2.49, "r_error": "", "src_len": 1020, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5552, "tout": 1887, "ts": 1791528516.621187, "chk": "ok", "code_len": 1020}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6644, "tout": 573, "ts": 1791528566.9549663, "chk": null, "code_len": 1020}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5552, "started": 1791528498.1314013}
{"ep": "h1-00370", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0078, "speedup": 1.0078, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.8, "calls": 2, "tokens_in": 17792, "tokens_out": 18811, "ctx_chars": 6513, "t_end": 1791528690.0386086, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0078, "lo95": 1.0056, "mean": 1.0074, "ev_only": 1.0077, "ref_ms": 39.28192, "cand_ms": 38.97701, "n_trials": 33, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0773, "r_wall_s": 17.11, "compile_s": 1.94, "r_error": "", "src_len": 11683, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 13044, "ts": 1791528563.3787913, "chk": "ok", "code_len": 11683}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12065, "tout": 5767, "ts": 1791528672.8846223, "chk": null, "code_len": 11683}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791528452.2770967}
{"ep": "h1-00399", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3956, "speedup": 1.3956, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.5, "calls": 2, "tokens_in": 13534, "tokens_out": 2062, "ctx_chars": 10210, "t_end": 1791528690.791032, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3956, "lo95": 1.3936, "mean": 1.3971, "ev_only": 1.3964, "ref_ms": 19.33132, "cand_ms": 13.85116, "n_trials": 83, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0711, "r_wall_s": 90.01, "compile_s": 2.61, "r_error": "", "src_len": 1831, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 1155, "ts": 1791528558.0607405, "chk": "ok", "code_len": 1831}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7399, "tout": 907, "ts": 1791528600.2448082, "chk": null, "code_len": 1831}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791528548.3230207}
{"ep": "h1-00373", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.3174, "speedup": 2.3174, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.1, "calls": 2, "tokens_in": 5919, "tokens_out": 8229, "ctx_chars": 0, "t_end": 1791528696.9729247, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.3174, "lo95": 2.3148, "mean": 2.405, "ev_only": 2.3307, "ref_ms": 3.64637, "cand_ms": 1.5735, "n_trials": 220, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 95.15, "compile_s": 14.13, "r_error": "", "src_len": 4571, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 5933, "ts": 1791528513.3500626, "chk": "ok", "code_len": 4571}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4330, "tout": 2296, "ts": 1791528600.90287, "chk": null, "code_len": 4571}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791528455.865246}
{"ep": "h1-00336", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3897, "speedup": 1.3897, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 393.5, "calls": 2, "tokens_in": 14071, "tokens_out": 4508, "ctx_chars": 10177, "t_end": 1791528702.5203097, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3897, "lo95": 1.3881, "mean": 1.388, "ev_only": 1.3837, "ref_ms": 2.3716, "cand_ms": 1.70659, "n_trials": 207, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 24.2, "compile_s": 2.38, "r_error": "", "src_len": 2800, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6105, "tout": 3108, "ts": 1791528336.2877963, "chk": "ok", "code_len": 2800}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7966, "tout": 1400, "ts": 1791528542.7077694, "chk": null, "code_len": 2800}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6105, "started": 1791528308.9888308}
{"ep": "h1-00392", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0069, "speedup": 1.0069, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.3, "calls": 2, "tokens_in": 4116, "tokens_out": 1961, "ctx_chars": 0, "t_end": 1791528706.5369968, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0069, "lo95": 1.0063, "mean": 1.0075, "ev_only": 1.0073, "ref_ms": 7.9811, "cand_ms": 7.92656, "n_trials": 130, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 20.0, "compile_s": 2.53, "r_error": "", "src_len": 980, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1588, "tout": 1391, "ts": 1791528536.6118917, "chk": "ok", "code_len": 980}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2528, "tout": 570, "ts": 1791528552.3733754, "chk": null, "code_len": 980}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1588, "started": 1791528524.1995232}
{"ep": "h1-00413", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0838, "speedup": 1.0838, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 130.5, "calls": 2, "tokens_in": 13739, "tokens_out": 5622, "ctx_chars": 9898, "t_end": 1791528714.939805, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0838, "lo95": 1.0832, "mean": 1.0958, "ev_only": 1.0851, "ref_ms": 16.05769, "cand_ms": 14.81619, "n_trials": 69, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2799, "r_wall_s": 32.61, "compile_s": 1.93, "r_error": "", "src_len": 1944, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6027, "tout": 4233, "ts": 1791528624.704242, "chk": "ok", "code_len": 1944}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7712, "tout": 1389, "ts": 1791528682.3070571, "chk": null, "code_len": 1944}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6027, "started": 1791528584.4150567}
{"ep": "h1-00361", "task": "L2_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9795, "speedup": 0.9795, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 307.8, "calls": 2, "tokens_in": 5375, "tokens_out": 3095, "ctx_chars": 0, "t_end": 1791528717.4816542, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9795, "lo95": 0.979, "mean": 0.9801, "ev_only": 0.9798, "ref_ms": 72.93079, "cand_ms": 74.45605, "n_trials": 19, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0364, "r_wall_s": 171.54, "compile_s": 50.58, "r_error": "", "src_len": 2603, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1697, "tout": 1869, "ts": 1791528449.3171282, "chk": "ok", "code_len": 2656}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3678, "tout": 1226, "ts": 1791528545.891245, "chk": null, "code_len": 2603}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1697, "started": 1791528430.0183241}
{"ep": "h1-00404", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3181, "speedup": 1.3181, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 166.8, "calls": 3, "tokens_in": 11097, "tokens_out": 7621, "ctx_chars": 0, "t_end": 1791528730.38769, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3181, "lo95": 1.3139, "mean": 1.3091, "ev_only": 1.3153, "ref_ms": 7.82273, "cand_ms": 5.93469, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 52.14, "compile_s": 1.85, "r_error": "", "src_len": 2504, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 4216, "ts": 1791528601.7183924, "chk": "incorrect", "code_len": 3001}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3877, "tout": 1959, "ts": 1791528629.505845, "chk": "ok", "code_len": 2504}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5655, "tout": 1446, "ts": 1791528678.1361346, "chk": null, "code_len": 2504}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1565, "started": 1791528563.6254418}
{"ep": "h1-00378", "task": "L2_037", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2227, "speedup": 1.2227, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 268.6, "calls": 2, "tokens_in": 13070, "tokens_out": 1878, "ctx_chars": 9893, "t_end": 1791528737.9630938, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2227, "lo95": 1.2221, "mean": 1.2225, "ev_only": 1.2216, "ref_ms": 19.68714, "cand_ms": 16.10176, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0972, "r_wall_s": 163.26, "compile_s": 2.85, "r_error": "", "src_len": 1857, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5989, "tout": 980, "ts": 1791528478.5020227, "chk": "ok", "code_len": 1857}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7081, "tout": 898, "ts": 1791528573.716955, "chk": null, "code_len": 1857}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5989, "started": 1791528469.3641675}
{"ep": "h1-00434", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 7.2712, "speedup": 7.2712, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 63.3, "calls": 1, "tokens_in": 1564, "tokens_out": 742, "ctx_chars": 0, "t_end": 1791528743.6603827, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 7.2712, "lo95": 7.2227, "mean": 7.0721, "ev_only": 7.2615, "ref_ms": 3.58353, "cand_ms": 0.49284, "n_trials": 212, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 55.29, "compile_s": 1.92, "r_error": "", "src_len": 844, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1564, "tout": 742, "ts": 1791528687.6719046, "chk": null, "code_len": 844}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1564, "started": 1791528680.3487914}
{"ep": "h1-00416", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0033, "speedup": 1.0033, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 143.5, "calls": 2, "tokens_in": 13719, "tokens_out": 1581, "ctx_chars": 10909, "t_end": 1791528745.135496, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0033, "lo95": 1.001, "mean": 1.044, "ev_only": 1.0033, "ref_ms": 16.1628, "cand_ms": 16.10946, "n_trials": 77, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.001, "r_wall_s": 36.88, "compile_s": 1.97, "r_error": "", "src_len": 948, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6428, "tout": 1022, "ts": 1791528631.0994625, "chk": "ok", "code_len": 948}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7291, "tout": 559, "ts": 1791528708.1870716, "chk": null, "code_len": 948}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6428, "started": 1791528621.9672894}
{"ep": "h1-00342", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9725, "speedup": 0.9725, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 416.7, "calls": 3, "tokens_in": 17048, "tokens_out": 15290, "ctx_chars": 0, "t_end": 1791528750.0201776, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9725, "lo95": 0.9711, "mean": 0.9735, "ev_only": 0.9709, "ref_ms": 20.21846, "cand_ms": 20.7903, "n_trials": 59, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 177.13, "compile_s": 14.36, "r_error": "", "src_len": 6413, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2008, "tout": 8421, "ts": 1791528408.4608438, "chk": "no_custom_kernel", "code_len": 6442}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5832, "tout": 3736, "ts": 1791528511.5157769, "chk": "ok", "code_len": 6413}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9208, "tout": 3133, "ts": 1791528572.0989676, "chk": null, "code_len": 6413}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2008, "started": 1791528333.2958064}
{"ep": "h1-00432", "task": "L2_079", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 81.2, "calls": 1, "tokens_in": 1811, "tokens_out": 2419, "ctx_chars": 0, "t_end": 1791528754.3965483, "error": "RuntimeError: Error building extension 'fused079': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused079 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 58.28, "compile_s": 58.27, "r_error": "RuntimeError: Error building extension 'fused079': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused079 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "src_len": 4242, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1811, "tout": 2419, "ts": 1791528696.0950687, "chk": null, "code_len": 4242}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1811, "started": 1791528673.1628804}
{"ep": "h1-00349", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 55.5485, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 393.4, "calls": 3, "tokens_in": 36440, "tokens_out": 22131, "ctx_chars": 10613, "t_end": 1791528756.5602198, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 55.5485, "lo95": 53.9326, "mean": 47.2533, "ev_only": 57.0426, "ref_ms": 36.43363, "cand_ms": 0.65589, "n_trials": 38, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.0425, "r_wall_s": 174.07, "compile_s": 16.73, "r_error": "", "src_len": 8861, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6522, "tout": 12103, "ts": 1791528470.2126517, "chk": "compile_error", "code_len": 8700}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 12611, "tout": 5646, "ts": 1791528537.5640693, "chk": "ok", "code_len": 8861}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 17307, "tout": 4382, "ts": 1791528582.4237082, "chk": null, "code_len": 8861}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", null], "first_tin": 6522, "started": 1791528363.1105304}
{"ep": "h1-00353", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.4834, "speedup": 4.4834, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 385.2, "calls": 3, "tokens_in": 16661, "tokens_out": 14300, "ctx_chars": 0, "t_end": 1791528757.327123, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.4834, "lo95": 3.8941, "mean": 4.7965, "ev_only": 4.4854, "ref_ms": 70.64622, "cand_ms": 15.75718, "n_trials": 12, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8431, "r_wall_s": 160.77, "compile_s": 13.49, "r_error": "", "src_len": 6453, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1959, "tout": 7842, "ts": 1791528440.0025353, "chk": "no_custom_kernel", "code_len": 6475}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5729, "tout": 3360, "ts": 1791528481.9203563, "chk": "ok", "code_len": 6453}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8973, "tout": 3098, "ts": 1791528596.5166209, "chk": null, "code_len": 6453}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1959, "started": 1791528372.09527}
{"ep": "h1-00257", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4495, "speedup": 1.4495, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 795.5, "calls": 3, "tokens_in": 15597, "tokens_out": 13128, "ctx_chars": 0, "t_end": 1791528760.419564, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4495, "lo95": 1.4449, "mean": 1.4299, "ev_only": 1.4501, "ref_ms": 2.16003, "cand_ms": 1.49019, "n_trials": 208, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9954, "r_wall_s": 73.97, "compile_s": 13.34, "r_error": "", "src_len": 5815, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1813, "tout": 6944, "ts": 1791528044.0614223, "chk": "no_custom_kernel", "code_len": 5860}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5300, "tout": 3190, "ts": 1791528393.328054, "chk": "ok", "code_len": 5815}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8484, "tout": 2994, "ts": 1791528551.569399, "chk": null, "code_len": 5815}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1813, "started": 1791527964.9508123}
{"ep": "h1-00265", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9422, "speedup": 0.9422, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 766.6, "calls": 4, "tokens_in": 56543, "tokens_out": 46789, "ctx_chars": 0, "t_end": 1791528766.499862, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9422, "lo95": 0.8093, "mean": 1.049, "ev_only": 0.9414, "ref_ms": 5.20022, "cand_ms": 5.51898, "n_trials": 201, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0072, "r_wall_s": 130.47, "compile_s": 18.24, "r_error": "", "src_len": 5477, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2845, "tout": 20759, "ts": 1791528175.0173314, "chk": "runtime_error", "code_len": 12970}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11031, "tout": 10889, "ts": 1791528444.318196, "chk": "incorrect", "code_len": 14442}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 19638, "tout": 12028, "ts": 1791528582.6439288, "chk": "ok", "code_len": 5477}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 23029, "tout": 3113, "ts": 1791528635.999978, "chk": null, "code_len": 5477}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "ok", null], "first_tin": 2845, "started": 1791527999.8969576}
{"ep": "h1-00421", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.397, "speedup": 1.397, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 152.1, "calls": 2, "tokens_in": 12946, "tokens_out": 5171, "ctx_chars": 9033, "t_end": 1791528767.1759179, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.397, "lo95": 1.3933, "mean": 1.3957, "ev_only": 1.403, "ref_ms": 7.74956, "cand_ms": 5.54713, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 67.19, "compile_s": 2.77, "r_error": "", "src_len": 2651, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 3345, "ts": 1791528644.69368, "chk": "ok", "code_len": 2651}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7458, "tout": 1826, "ts": 1791528699.8867822, "chk": null, "code_len": 2651}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5488, "started": 1791528615.1122844}
{"ep": "h1-00338", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7008, "speedup": 0.7008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 448.9, "calls": 3, "tokens_in": 16891, "tokens_out": 20232, "ctx_chars": 0, "t_end": 1791528768.426971, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7008, "lo95": 0.7006, "mean": 0.7406, "ev_only": 0.7009, "ref_ms": 20.29883, "cand_ms": 28.96646, "n_trials": 47, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9999, "r_wall_s": 161.31, "compile_s": 16.81, "r_error": "", "src_len": 6288, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2008, "tout": 13391, "ts": 1791528439.4115374, "chk": "no_custom_kernel", "code_len": 6292}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5730, "tout": 3714, "ts": 1791528516.1047833, "chk": "ok", "code_len": 6288}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9153, "tout": 3127, "ts": 1791528606.073398, "chk": null, "code_len": 6288}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2008, "started": 1791528319.5393946}
{"ep": "h1-00438", "task": "L1_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 66.0, "calls": 1, "tokens_in": 1562, "tokens_out": 789, "ctx_chars": 0, "t_end": 1791528768.5552444, "error": "RuntimeError: Error building extension 'gelu_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 58.26, "compile_s": 58.26, "r_error": "RuntimeError: Error building extension 'gelu_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "src_len": 1629, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1562, "tout": 789, "ts": 1791528710.2719026, "chk": null, "code_len": 1629}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1562, "started": 1791528702.520561}
{"ep": "h1-00442", "task": "L3_039", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "forbidden", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 39.3, "calls": 1, "tokens_in": 1944, "tokens_out": 1987, "ctx_chars": 0, "t_end": 1791528769.6670878, "error": "static check failed: line 84: getattr needs a literal, non-private attribute name; line 85: getattr needs a literal, non-private attribute name; line 87: getatt", "f_status": "forbidden", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 0.03, "compile_s": null, "r_error": "static check failed: line 84: getattr needs a literal, non-private attribute name; line 85: getattr needs a literal, non-private attribute name; line 87: getatt", "src_len": 3948, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1944, "tout": 1987, "ts": 1791528769.5395594, "chk": null, "code_len": 3948}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1944, "started": 1791528750.7431083}
{"ep": "h1-00398", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 7.3218, "speedup": 7.3218, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 223.4, "calls": 2, "tokens_in": 4113, "tokens_out": 1369, "ctx_chars": 0, "t_end": 1791528770.045452, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.3218, "lo95": 7.3143, "mean": 7.275, "ev_only": 7.5054, "ref_ms": 3.58295, "cand_ms": 0.48935, "n_trials": 198, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 187.78, "compile_s": 2.71, "r_error": "", "src_len": 768, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 873, "ts": 1791528554.66451, "chk": "ok", "code_len": 768}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2549, "tout": 496, "ts": 1791528581.832465, "chk": null, "code_len": 768}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791528546.6706307}
{"ep": "h1-00396", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3724, "speedup": 1.3724, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.1, "calls": 2, "tokens_in": 16965, "tokens_out": 6950, "ctx_chars": 13278, "t_end": 1791528775.706974, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3724, "lo95": 1.3714, "mean": 1.3864, "ev_only": 1.37, "ref_ms": 5.29892, "cand_ms": 3.86109, "n_trials": 221, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9984, "r_wall_s": 68.58, "compile_s": 2.05, "r_error": "", "src_len": 3690, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 4843, "ts": 1791528595.0392177, "chk": "ok", "code_len": 3690}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9803, "tout": 2107, "ts": 1791528706.428149, "chk": null, "code_len": 3690}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791528552.9979024}
{"ep": "h1-00394", "task": "L2_084", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.007, "speedup": 1.007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 248.8, "calls": 1, "tokens_in": 1769, "tokens_out": 2096, "ctx_chars": 0, "t_end": 1791528777.0144541, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.007, "lo95": 1.0066, "mean": 1.0061, "ev_only": 1.0051, "ref_ms": 8.10011, "cand_ms": 8.04394, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 90.53, "compile_s": 3.14, "r_error": "", "src_len": 1572, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1769, "tout": 2096, "ts": 1791528552.239965, "chk": null, "code_len": 1572}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1769, "started": 1791528528.1934845}
{"ep": "h1-00328", "task": "L2_097", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0087, "speedup": 1.0087, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 498.9, "calls": 4, "tokens_in": 23892, "tokens_out": 7569, "ctx_chars": 0, "t_end": 1791528780.1068425, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0087, "lo95": 1.0081, "mean": 1.0081, "ev_only": 1.0088, "ref_ms": 8.22044, "cand_ms": 8.1495, "n_trials": 146, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0195, "r_wall_s": 212.71, "compile_s": 13.61, "r_error": "", "src_len": 5551, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1728, "tout": 2654, "ts": 1791528304.876738, "chk": "compile_error", "code_len": 5672}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5663, "tout": 2436, "ts": 1791528380.1363237, "chk": "ok", "code_len": 5551}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8211, "tout": 55, "ts": 1791528547.9211023, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8290, "tout": 2424, "ts": 1791528567.3001444, "chk": null, "code_len": 5551}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1728, "started": 1791528281.2335172}
{"ep": "h1-00409", "task": "L1_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.3311, "speedup": 0.3311, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 204.4, "calls": 3, "tokens_in": 8791, "tokens_out": 4109, "ctx_chars": 0, "t_end": 1791528780.230593, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.3311, "lo95": 0.3308, "mean": 0.3315, "ev_only": 0.3306, "ref_ms": 5.29611, "cand_ms": 15.99392, "n_trials": 62, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 66.98, "compile_s": 1.96, "r_error": "", "src_len": 2419, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1474, "tout": 1212, "ts": 1791528588.080088, "chk": "ok", "code_len": 2106}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 2795, "tout": 1618, "ts": 1791528637.70281, "chk": "ok", "code_len": 2419}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4522, "tout": 1279, "ts": 1791528712.7920973, "chk": null, "code_len": 2419}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 1474, "started": 1791528575.8142526}
{"ep": "h1-00433", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0288, "speedup": 1.0288, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 108.4, "calls": 2, "tokens_in": 4296, "tokens_out": 2091, "ctx_chars": 0, "t_end": 1791528783.4098537, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0288, "lo95": 1.0285, "mean": 1.0289, "ev_only": 1.0285, "ref_ms": 30.43053, "cand_ms": 29.57899, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0104, "r_wall_s": 77.05, "compile_s": 2.06, "r_error": "", "src_len": 1013, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1696, "tout": 1571, "ts": 1791528690.1844645, "chk": "ok", "code_len": 1013}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2600, "tout": 520, "ts": 1791528705.9369433, "chk": null, "code_len": 1013}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1696, "started": 1791528675.0514534}
{"ep": "h1-00437", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.6576, "speedup": 6.6576, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 89.0, "calls": 2, "tokens_in": 5873, "tokens_out": 1339, "ctx_chars": 2425, "t_end": 1791528785.9534302, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 6.6576, "lo95": 6.5765, "mean": 6.7522, "ev_only": 6.7667, "ref_ms": 3.63359, "cand_ms": 0.54578, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 60.13, "compile_s": 3.77, "r_error": "", "src_len": 846, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2480, "tout": 801, "ts": 1791528704.5645094, "chk": "ok", "code_len": 846}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3393, "tout": 538, "ts": 1791528725.3979468, "chk": null, "code_len": 846}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2480, "started": 1791528696.97316}
{"ep": "h1-00393", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7612, "speedup": 0.7612, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 265.7, "calls": 2, "tokens_in": 16356, "tokens_out": 13888, "ctx_chars": 6513, "t_end": 1791528792.0630765, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7612, "lo95": 0.6577, "mean": 0.7235, "ev_only": 0.7617, "ref_ms": 15.9178, "cand_ms": 20.91117, "n_trials": 52, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0907, "r_wall_s": 60.86, "compile_s": 2.66, "r_error": "", "src_len": 8802, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 9612, "ts": 1791528608.9243615, "chk": "ok", "code_len": 8802}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10629, "tout": 4276, "ts": 1791528731.1745677, "chk": null, "code_len": 8802}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791528526.375347}
{"ep": "h1-00424", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2785, "speedup": 1.2785, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.7, "calls": 2, "tokens_in": 5116, "tokens_out": 4334, "ctx_chars": 0, "t_end": 1791528793.641269, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2785, "lo95": 1.278, "mean": 1.2778, "ev_only": 1.2806, "ref_ms": 7.29336, "cand_ms": 5.70483, "n_trials": 227, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 58.77, "compile_s": 2.98, "r_error": "", "src_len": 2325, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1701, "tout": 2591, "ts": 1791528652.891901, "chk": "ok", "code_len": 2325}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3415, "tout": 1743, "ts": 1791528734.7446585, "chk": null, "code_len": 2325}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1701, "started": 1791528630.9838388}
{"ep": "h1-00418", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.1711, "speedup": 4.1711, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 194.0, "calls": 2, "tokens_in": 17644, "tokens_out": 6895, "ctx_chars": 12352, "t_end": 1791528800.338725, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.1711, "lo95": 4.1674, "mean": 4.0678, "ev_only": 4.1712, "ref_ms": 27.81994, "cand_ms": 6.66963, "n_trials": 55, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0871, "r_wall_s": 63.98, "compile_s": 2.74, "r_error": "", "src_len": 4487, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7394, "tout": 4680, "ts": 1791528646.3909283, "chk": "ok", "code_len": 4487}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10250, "tout": 2215, "ts": 1791528736.1827188, "chk": null, "code_len": 4487}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7394, "started": 1791528606.3342643}
{"ep": "h1-00333", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0551, "speedup": 1.0551, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 507.4, "calls": 2, "tokens_in": 18188, "tokens_out": 20011, "ctx_chars": 6513, "t_end": 1791528811.1402824, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0551, "lo95": 1.0511, "mean": 1.0619, "ev_only": 1.0553, "ref_ms": 39.12511, "cand_ms": 37.08126, "n_trials": 31, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0481, "r_wall_s": 167.33, "compile_s": 3.0, "r_error": "", "src_len": 11916, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 13871, "ts": 1791528422.3982205, "chk": "ok", "code_len": 11916}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12461, "tout": 6140, "ts": 1791528643.7816687, "chk": null, "code_len": 11916}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791528303.7192504}
{"ep": "h1-00352", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.077, "speedup": 6.077, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 446.2, "calls": 3, "tokens_in": 35362, "tokens_out": 21260, "ctx_chars": 11175, "t_end": 1791528817.9742332, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 6.077, "lo95": 6.0485, "mean": 6.1436, "ev_only": 6.3682, "ref_ms": 4.41751, "cand_ms": 0.72692, "n_trials": 186, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 79.12, "compile_s": 10.43, "r_error": "", "src_len": 8973, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 12248, "ts": 1791528482.485595, "chk": "no_custom_kernel", "code_len": 8998}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11913, "tout": 4734, "ts": 1791528654.008102, "chk": "ok", "code_len": 8973}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16382, "tout": 4278, "ts": 1791528738.4652934, "chk": null, "code_len": 8973}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 7067, "started": 1791528371.750924}
{"ep": "h1-00383", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7182, "speedup": 0.7182, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 323.6, "calls": 2, "tokens_in": 18330, "tokens_out": 15504, "ctx_chars": 6513, "t_end": 1791528818.1651137, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7182, "lo95": 0.6904, "mean": 0.7701, "ev_only": 0.7161, "ref_ms": 21.44566, "cand_ms": 29.86083, "n_trials": 37, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2388, "r_wall_s": 171.57, "compile_s": 3.5, "r_error": "", "src_len": 10274, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6296, "tout": 10263, "ts": 1791528577.4364479, "chk": "ok", "code_len": 10274}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12034, "tout": 5241, "ts": 1791528646.5648916, "chk": null, "code_len": 10274}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6296, "started": 1791528494.5854318}
{"ep": "h1-00410", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7102, "speedup": 1.7102, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.8, "calls": 2, "tokens_in": 12850, "tokens_out": 4244, "ctx_chars": 9033, "t_end": 1791528818.1736312, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.7102, "lo95": 1.7004, "mean": 1.7109, "ev_only": 1.7058, "ref_ms": 8.09797, "cand_ms": 4.73523, "n_trials": 211, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 184.05, "compile_s": 3.85, "r_error": "", "src_len": 2263, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 2975, "ts": 1791528603.2306619, "chk": "ok", "code_len": 2327}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7362, "tout": 1269, "ts": 1791528633.8260443, "chk": null, "code_len": 2263}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5488, "started": 1791528576.3997092}
{"ep": "h1-00406", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 8.8934, "speedup": 8.8934, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 268.2, "calls": 2, "tokens_in": 6843, "tokens_out": 9864, "ctx_chars": 0, "t_end": 1791528833.8732834, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 8.8934, "lo95": 8.8648, "mean": 8.947, "ev_only": 9.0819, "ref_ms": 5.87464, "cand_ms": 0.66056, "n_trials": 105, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 40.73, "compile_s": 11.17, "r_error": "", "src_len": 5208, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1845, "tout": 7269, "ts": 1791528630.6995664, "chk": "ok", "code_len": 5208}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4998, "tout": 2595, "ts": 1791528793.0734613, "chk": null, "code_len": 5208}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1845, "started": 1791528565.7002337}
{"ep": "h1-00457", "task": "L3_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6452, "speedup": 0.6452, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 59.8, "calls": 3, "tokens_in": 21855, "tokens_out": 4366, "ctx_chars": 6513, "t_end": 1791528835.5035365, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.6452, "lo95": 0.6382, "mean": 0.614, "ev_only": 0.6451, "ref_ms": 38.52332, "cand_ms": 59.7116, "n_trials": 25, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0197, "r_wall_s": 14.15, "compile_s": 1.86, "r_error": "", "src_len": 4931, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5725, "tout": 2196, "ts": 1791528793.8318686, "chk": "ok", "code_len": 4958}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8033, "tout": 40, "ts": 1791528803.9719248, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8097, "tout": 2130, "ts": 1791528821.3091707, "chk": null, "code_len": 4931}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5725, "started": 1791528775.7072327}
{"ep": "h1-00411", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2809, "speedup": 1.2809, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.0, "calls": 2, "tokens_in": 4863, "tokens_out": 3113, "ctx_chars": 0, "t_end": 1791528838.0063426, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2809, "lo95": 1.2804, "mean": 1.2804, "ev_only": 1.2814, "ref_ms": 19.74884, "cand_ms": 15.41828, "n_trials": 80, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0417, "r_wall_s": 205.37, "compile_s": 3.05, "r_error": "", "src_len": 1878, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1709, "tout": 2158, "ts": 1791528604.078252, "chk": "ok", "code_len": 1878}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3154, "tout": 955, "ts": 1791528631.8470275, "chk": null, "code_len": 1878}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1709, "started": 1791528582.9741578}
{"ep": "h1-00465", "task": "L2_059", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9032, "speedup": 0.9032, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 39.6, "calls": 1, "tokens_in": 1548, "tokens_out": 579, "ctx_chars": 0, "t_end": 1791528839.9434705, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9032, "lo95": 0.9027, "mean": 0.9054, "ev_only": 0.9033, "ref_ms": 16.12206, "cand_ms": 17.85025, "n_trials": 65, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0009, "r_wall_s": 33.31, "compile_s": 2.05, "r_error": "", "src_len": 1100, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1548, "tout": 579, "ts": 1791528806.562173, "chk": null, "code_len": 1100}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1548, "started": 1791528800.3389823}
{"ep": "h1-00429", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5698, "speedup": 0.5698, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.5, "calls": 2, "tokens_in": 16118, "tokens_out": 8702, "ctx_chars": 10864, "t_end": 1791528842.9368062, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.5698, "lo95": 0.5693, "mean": 0.5683, "ev_only": 0.5706, "ref_ms": 10.05374, "cand_ms": 17.64481, "n_trials": 80, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 91.87, "compile_s": 1.97, "r_error": "", "src_len": 4251, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6627, "tout": 6433, "ts": 1791528710.1943128, "chk": "ok", "code_len": 4307}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9491, "tout": 2269, "ts": 1791528750.2088215, "chk": null, "code_len": 4251}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6627, "started": 1791528653.4751158}
{"ep": "h1-00452", "task": "L2_035", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 76.0, "calls": 1, "tokens_in": 1691, "tokens_out": 1346, "ctx_chars": 0, "t_end": 1791528843.195593, "error": "RuntimeError: Error building extension 'fused_m035': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_m035 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 63.45, "compile_s": 63.4, "r_error": "RuntimeError: Error building extension 'fused_m035': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_m035 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "src_len": 2784, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1691, "tout": 1346, "ts": 1791528779.6381416, "chk": null, "code_len": 2784}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1691, "started": 1791528767.1761708}
{"ep": "h1-00407", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0019, "speedup": 1.0019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 272.9, "calls": 2, "tokens_in": 4062, "tokens_out": 1845, "ctx_chars": 0, "t_end": 1791528844.9802392, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0019, "lo95": 1.0009, "mean": 1.0041, "ev_only": 1.005, "ref_ms": 8.03718, "cand_ms": 8.02201, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 35.61, "compile_s": 2.81, "r_error": "", "src_len": 1007, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1588, "tout": 1303, "ts": 1791528583.7906213, "chk": "ok", "code_len": 1007}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2474, "tout": 542, "ts": 1791528673.4581497, "chk": null, "code_len": 1007}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1588, "started": 1791528572.1054444}
{"ep": "h1-00446", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0703, "speedup": 1.0703, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 97.6, "calls": 2, "tokens_in": 14868, "tokens_out": 3293, "ctx_chars": 11062, "t_end": 1791528847.6639233, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0703, "lo95": 1.0697, "mean": 1.076, "ev_only": 1.0707, "ref_ms": 12.67735, "cand_ms": 11.84491, "n_trials": 104, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0245, "r_wall_s": 12.77, "compile_s": 1.96, "r_error": "", "src_len": 2093, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6695, "tout": 2211, "ts": 1791528770.8115537, "chk": "ok", "code_len": 2093}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8173, "tout": 1082, "ts": 1791528834.8483043, "chk": null, "code_len": 2093}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6695, "started": 1791528750.0204363}
{"ep": "h1-00454", "task": "L3_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 80.2, "calls": 1, "tokens_in": 2190, "tokens_out": 1905, "ctx_chars": 0, "t_end": 1791528848.750612, "error": "RuntimeError: Error building extension 'regnet_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=regnet_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 62.67, "compile_s": 62.66, "r_error": "RuntimeError: Error building extension 'regnet_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=regnet_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 4160, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2190, "tout": 1905, "ts": 1791528785.9734902, "chk": null, "code_len": 4160}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2190, "started": 1791528768.555446}
{"ep": "h1-00402", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.185, "speedup": 1.185, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 294.5, "calls": 2, "tokens_in": 4860, "tokens_out": 4858, "ctx_chars": 0, "t_end": 1791528850.0369658, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.185, "lo95": 1.184, "mean": 1.1786, "ev_only": 1.1817, "ref_ms": 4.48636, "cand_ms": 3.78605, "n_trials": 216, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 222.38, "compile_s": 2.28, "r_error": "", "src_len": 2193, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1532, "tout": 3595, "ts": 1791528588.3516057, "chk": "ok", "code_len": 2193}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3328, "tout": 1263, "ts": 1791528627.6136637, "chk": null, "code_len": 2193}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1532, "started": 1791528555.5346456}
{"ep": "h1-00377", "task": "L1_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9475, "speedup": 0.9475, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 382.6, "calls": 3, "tokens_in": 8763, "tokens_out": 3661, "ctx_chars": 0, "t_end": 1791528850.7159665, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9475, "lo95": 0.9472, "mean": 0.9475, "ev_only": 0.9461, "ref_ms": 7.3248, "cand_ms": 7.73095, "n_trials": 162, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 197.88, "compile_s": 2.6, "r_error": "", "src_len": 3023, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1570, "tout": 1899, "ts": 1791528484.4004784, "chk": "ok", "code_len": 3023}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3578, "tout": 13, "ts": 1791528634.8684576, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3615, "tout": 1749, "ts": 1791528652.7079973, "chk": null, "code_len": 3023}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1570, "started": 1791528468.0773537}
{"ep": "h1-00359", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.7819, "speedup": 4.7819, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 461.1, "calls": 2, "tokens_in": 7263, "tokens_out": 13093, "ctx_chars": 0, "t_end": 1791528851.6649642, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.7819, "lo95": 4.7658, "mean": 4.7334, "ev_only": 4.7827, "ref_ms": 12.75884, "cand_ms": 2.66816, "n_trials": 113, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0021, "r_wall_s": 185.4, "compile_s": 11.9, "r_error": "", "src_len": 6609, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1863, "tout": 10043, "ts": 1791528490.5582056, "chk": "ok", "code_len": 6609}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5400, "tout": 3050, "ts": 1791528666.2391615, "chk": null, "code_len": 6609}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1863, "started": 1791528390.607813}
{"ep": "h1-00401", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.8212, "speedup": 6.8212, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 301.8, "calls": 3, "tokens_in": 29264, "tokens_out": 22399, "ctx_chars": 8224, "t_end": 1791528854.4491088, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 6.8212, "lo95": 6.7585, "mean": 7.8005, "ev_only": 6.8264, "ref_ms": 32.5979, "cand_ms": 4.77894, "n_trials": 33, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9934, "r_wall_s": 71.48, "compile_s": 11.93, "r_error": "", "src_len": 7442, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 14541, "ts": 1791528682.851, "chk": "no_custom_kernel", "code_len": 7490}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9911, "tout": 4124, "ts": 1791528726.4288704, "chk": "ok", "code_len": 7442}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13863, "tout": 3734, "ts": 1791528782.8328397, "chk": null, "code_len": 7442}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791528552.6255984}
{"ep": "h1-00430", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.3938, "speedup": 4.3938, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 186.2, "calls": 2, "tokens_in": 7299, "tokens_out": 11453, "ctx_chars": 0, "t_end": 1791528856.1706564, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.3938, "lo95": 4.3925, "mean": 4.3923, "ev_only": 4.4057, "ref_ms": 20.04831, "cand_ms": 4.56291, "n_trials": 80, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 20.92, "compile_s": 11.09, "r_error": "", "src_len": 6573, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1729, "tout": 8234, "ts": 1791528764.262571, "chk": "ok", "code_len": 6573}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5570, "tout": 3219, "ts": 1791528835.2104647, "chk": null, "code_len": 6573}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1729, "started": 1791528690.2774968}
{"ep": "h1-00455", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9207, "speedup": 0.9207, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 92.0, "calls": 2, "tokens_in": 10591, "tokens_out": 4490, "ctx_chars": 6513, "t_end": 1791528861.6374712, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9207, "lo95": 0.9203, "mean": 0.9578, "ev_only": 0.9208, "ref_ms": 10.6663, "cand_ms": 11.5855, "n_trials": 98, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 33.44, "compile_s": 1.94, "r_error": "", "src_len": 2773, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4389, "tout": 3016, "ts": 1791528796.2330368, "chk": "ok", "code_len": 2773}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6202, "tout": 1474, "ts": 1791528828.1672568, "chk": null, "code_len": 2773}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4389, "started": 1791528769.6673164}
{"ep": "h1-00460", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0285, "speedup": 1.0285, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 82.4, "calls": 2, "tokens_in": 7911, "tokens_out": 3789, "ctx_chars": 3355, "t_end": 1791528862.665203, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0285, "lo95": 1.0277, "mean": 1.0539, "ev_only": 1.0289, "ref_ms": 20.51467, "cand_ms": 19.9453, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0007, "r_wall_s": 26.12, "compile_s": 2.07, "r_error": "", "src_len": 1538, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3296, "tout": 2947, "ts": 1791528807.577749, "chk": "ok", "code_len": 1538}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4615, "tout": 842, "ts": 1791528836.509862, "chk": null, "code_len": 1538}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3296, "started": 1791528780.2308488}
{"ep": "h1-00426", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 67.2053, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 225.5, "calls": 2, "tokens_in": 17655, "tokens_out": 15298, "ctx_chars": 10613, "t_end": 1791528863.0201433, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 67.2053, "lo95": 65.2002, "mean": 65.3836, "ev_only": 69.2366, "ref_ms": 36.30603, "cand_ms": 0.54023, "n_trials": 15, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.0671, "r_wall_s": 35.72, "compile_s": 12.0, "r_error": "", "src_len": 8049, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6522, "tout": 11251, "ts": 1791528740.9812093, "chk": "ok", "code_len": 8049}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11133, "tout": 4047, "ts": 1791528827.2301185, "chk": null, "code_len": 8049}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6522, "started": 1791528637.5064952}
{"ep": "h1-00414", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.017, "speedup": 1.017, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 284.2, "calls": 2, "tokens_in": 5880, "tokens_out": 5333, "ctx_chars": 0, "t_end": 1791528872.4391067, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.017, "lo95": 1.0166, "mean": 1.0173, "ev_only": 1.0176, "ref_ms": 8.14851, "cand_ms": 8.01206, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0112, "r_wall_s": 32.01, "compile_s": 2.23, "r_error": "", "src_len": 3377, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1771, "tout": 3514, "ts": 1791528617.9946134, "chk": "ok", "code_len": 3458}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4109, "tout": 1819, "ts": 1791528840.337323, "chk": null, "code_len": 3377}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1771, "started": 1791528588.274266}
{"ep": "h1-00466", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0144, "speedup": 1.0144, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 65.0, "calls": 2, "tokens_in": 11892, "tokens_out": 1080, "ctx_chars": 9220, "t_end": 1791528876.178376, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0144, "lo95": 1.0134, "mean": 1.0121, "ev_only": 1.0151, "ref_ms": 8.13073, "cand_ms": 8.01542, "n_trials": 156, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0048, "r_wall_s": 45.48, "compile_s": 1.96, "r_error": "", "src_len": 913, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5602, "tout": 576, "ts": 1791528816.5951757, "chk": "ok", "code_len": 913}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6290, "tout": 504, "ts": 1791528830.5773182, "chk": null, "code_len": 913}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5602, "started": 1791528811.1405454}
{"ep": "h1-00419", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.0541, "speedup": 4.0541, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 267.7, "calls": 3, "tokens_in": 15007, "tokens_out": 13748, "ctx_chars": 0, "t_end": 1791528876.4859657, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.0541, "lo95": 4.0505, "mean": 4.0503, "ev_only": 4.0624, "ref_ms": 19.48296, "cand_ms": 4.80569, "n_trials": 71, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 54.28, "compile_s": 10.96, "r_error": "", "src_len": 5733, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1782, "tout": 7884, "ts": 1791528680.2140203, "chk": "no_custom_kernel", "code_len": 5759}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5141, "tout": 3053, "ts": 1791528723.3133326, "chk": "ok", "code_len": 5733}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8084, "tout": 2811, "ts": 1791528821.8777883, "chk": null, "code_len": 5733}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1782, "started": 1791528608.792888}
{"ep": "h1-00368", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.5734, "speedup": 2.5734, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 432.6, "calls": 3, "tokens_in": 27632, "tokens_out": 17793, "ctx_chars": 8224, "t_end": 1791528877.166501, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.5734, "lo95": 2.5616, "mean": 2.6736, "ev_only": 2.5747, "ref_ms": 61.08878, "cand_ms": 23.73882, "n_trials": 26, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9067, "r_wall_s": 214.14, "compile_s": 11.96, "r_error": "", "src_len": 6647, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5503, "tout": 10092, "ts": 1791528534.8310456, "chk": "no_custom_kernel", "code_len": 6746}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9317, "tout": 4496, "ts": 1791528588.6814969, "chk": "ok", "code_len": 6647}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12812, "tout": 3205, "ts": 1791528663.0030015, "chk": null, "code_len": 6647}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5503, "started": 1791528444.5512705}
{"ep": "h1-00408", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0062, "speedup": 1.0062, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 305.9, "calls": 2, "tokens_in": 11718, "tokens_out": 1231, "ctx_chars": 9033, "t_end": 1791528880.7683105, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0062, "lo95": 0.9998, "mean": 1.0023, "ev_only": 1.0021, "ref_ms": 4.52661, "cand_ms": 4.49871, "n_trials": 208, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0021, "r_wall_s": 268.12, "compile_s": 2.92, "r_error": "", "src_len": 941, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5455, "tout": 699, "ts": 1791528581.2268746, "chk": "ok", "code_len": 941}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6263, "tout": 532, "ts": 1791528612.6091597, "chk": null, "code_len": 941}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5455, "started": 1791528574.897406}
{"ep": "h1-00387", "task": "L3_044", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3804, "speedup": 1.3804, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 378.6, "calls": 4, "tokens_in": 24517, "tokens_out": 4645, "ctx_chars": 2425, "t_end": 1791528887.7776234, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3804, "lo95": 1.38, "mean": 1.3805, "ev_only": 1.3801, "ref_ms": 75.66147, "cand_ms": 54.81095, "n_trials": 23, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0213, "r_wall_s": 252.15, "compile_s": 5.0, "r_error": "", "src_len": 2766, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3935, "tout": 1731, "ts": 1791528524.714585, "chk": "ok", "code_len": 2908}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5778, "tout": 1476, "ts": 1791528595.660023, "chk": "ok", "code_len": 2766}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7366, "tout": 48, "ts": 1791528623.4828079, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7438, "tout": 1390, "ts": 1791528635.1375175, "chk": null, "code_len": 2766}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", "no_code", null], "first_tin": 3935, "started": 1791528509.167125}
{"ep": "h1-00405", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 24.9783, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 325.7, "calls": 2, "tokens_in": 12811, "tokens_out": 4322, "ctx_chars": 8570, "t_end": 1791528889.491242, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 24.9783, "lo95": 24.3966, "mean": 23.9442, "ev_only": 25.6226, "ref_ms": 16.08055, "cand_ms": 0.64378, "n_trials": 87, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.9593, "r_wall_s": 251.67, "compile_s": 7.34, "r_error": "", "src_len": 2728, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5372, "tout": 2796, "ts": 1791528588.9622703, "chk": "ok", "code_len": 2728}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7439, "tout": 1526, "ts": 1791528637.7038548, "chk": null, "code_len": 2728}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5372, "started": 1791528563.8166478}
{"ep": "h1-00440", "task": "L1_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0134, "speedup": 1.0134, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 176.7, "calls": 4, "tokens_in": 32086, "tokens_out": 2938, "ctx_chars": 10864, "t_end": 1791528891.6781104, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0134, "lo95": 1.0126, "mean": 1.0135, "ev_only": 1.0133, "ref_ms": 10.02427, "cand_ms": 9.8916, "n_trials": 77, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 109.99, "compile_s": 2.64, "r_error": "", "src_len": 1847, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6625, "tout": 980, "ts": 1791528723.898135, "chk": "ok", "code_len": 1920}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7714, "tout": 996, "ts": 1791528752.0111835, "chk": "ok", "code_len": 1847}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8819, "tout": 85, "ts": 1791528773.40186, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8928, "tout": 877, "ts": 1791528780.763114, "chk": null, "code_len": 1847}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", "no_code", null], "first_tin": 6625, "started": 1791528714.9400656}
{"ep": "h1-00462", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4922, "speedup": 1.4922, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 106.2, "calls": 2, "tokens_in": 14716, "tokens_out": 4167, "ctx_chars": 10508, "t_end": 1791528892.157648, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4922, "lo95": 1.4873, "mean": 1.5284, "ev_only": 1.481, "ref_ms": 2.18139, "cand_ms": 1.46186, "n_trials": 176, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1237, "r_wall_s": 43.52, "compile_s": 1.94, "r_error": "", "src_len": 2716, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6405, "tout": 2699, "ts": 1791528809.504181, "chk": "ok", "code_len": 2716}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8311, "tout": 1468, "ts": 1791528848.5971482, "chk": null, "code_len": 2716}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6405, "started": 1791528785.9536867}
{"ep": "h1-00470", "task": "L2_067", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 60.2, "calls": 1, "tokens_in": 1655, "tokens_out": 1106, "ctx_chars": 0, "t_end": 1791528894.033184, "error": "RuntimeError: Error building extension 'gelu_avgpool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_avgpool_mod -DTORCH_API_INCLUDE_EXTENSION_H -", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 49.75, "compile_s": 49.75, "r_error": "RuntimeError: Error building extension 'gelu_avgpool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_avgpool_mod -DTORCH_API_INCLUDE_EXTENSION_H -", "src_len": 2271, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1655, "tout": 1106, "ts": 1791528844.2269104, "chk": null, "code_len": 2271}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1655, "started": 1791528833.873512}
{"ep": "h1-00474", "task": "L2_068", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 54.8, "calls": 1, "tokens_in": 1530, "tokens_out": 861, "ctx_chars": 0, "t_end": 1791528897.7613344, "error": "RuntimeError: Error building extension 'fused_epilogue_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_epilogue_mod -DTORCH_API_INCLUDE_EXTENSION", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 46.43, "compile_s": 46.43, "r_error": "RuntimeError: Error building extension 'fused_epilogue_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_epilogue_mod -DTORCH_API_INCLUDE_EXTENSION", "src_len": 1831, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1530, "tout": 861, "ts": 1791528851.28606, "chk": null, "code_len": 1831}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1530, "started": 1791528842.937086}
{"ep": "h1-00469", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0357, "speedup": 1.0357, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.4, "calls": 2, "tokens_in": 12213, "tokens_out": 1685, "ctx_chars": 9028, "t_end": 1791528898.595187, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0357, "lo95": 1.0354, "mean": 1.0385, "ev_only": 1.0351, "ref_ms": 8.22776, "cand_ms": 7.9445, "n_trials": 162, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0057, "r_wall_s": 37.45, "compile_s": 2.16, "r_error": "", "src_len": 1212, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 1025, "ts": 1791528827.226351, "chk": "ok", "code_len": 1212}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6675, "tout": 660, "ts": 1791528861.0594957, "chk": null, "code_len": 1212}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5538, "started": 1791528818.1738648}
{"ep": "h1-00403", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.7825, "speedup": 3.7825, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 342.1, "calls": 3, "tokens_in": 14648, "tokens_out": 13024, "ctx_chars": 0, "t_end": 1791528902.210047, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.7825, "lo95": 3.7767, "mean": 3.7808, "ev_only": 3.7812, "ref_ms": 12.70254, "cand_ms": 3.35823, "n_trials": 125, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 134.03, "compile_s": 15.42, "r_error": "", "src_len": 5507, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1863, "tout": 7355, "ts": 1791528626.4382522, "chk": "no_custom_kernel", "code_len": 5531}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4984, "tout": 3035, "ts": 1791528730.3175874, "chk": "ok", "code_len": 5507}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7801, "tout": 2634, "ts": 1791528768.064486, "chk": null, "code_len": 5507}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1863, "started": 1791528560.065124}
{"ep": "h1-00451", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.3133, "speedup": 7.3133, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 136.5, "calls": 2, "tokens_in": 5824, "tokens_out": 1242, "ctx_chars": 2425, "t_end": 1791528902.9782763, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 7.3133, "lo95": 7.297, "mean": 7.2506, "ev_only": 7.4538, "ref_ms": 3.58857, "cand_ms": 0.49069, "n_trials": 209, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 69.42, "compile_s": 2.0, "r_error": "", "src_len": 820, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2480, "tout": 752, "ts": 1791528773.9115062, "chk": "ok", "code_len": 820}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3344, "tout": 490, "ts": 1791528833.027995, "chk": null, "code_len": 820}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2480, "started": 1791528766.5003412}
{"ep": "h1-00400", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8737, "speedup": 1.8737, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 368.2, "calls": 2, "tokens_in": 15762, "tokens_out": 8256, "ctx_chars": 10508, "t_end": 1791528918.0178344, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.8737, "lo95": 1.8694, "mean": 1.8651, "ev_only": 1.8646, "ref_ms": 2.1798, "cand_ms": 1.16339, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 254.23, "compile_s": 2.17, "r_error": "", "src_len": 4530, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6405, "tout": 5812, "ts": 1791528601.1892848, "chk": "ok", "code_len": 4530}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9357, "tout": 2444, "ts": 1791528663.7607505, "chk": null, "code_len": 4530}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6405, "started": 1791528549.820963}
{"ep": "h1-00422", "task": "L2_012", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0071, "speedup": 1.0071, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 305.3, "calls": 1, "tokens_in": 5888, "tokens_out": 526, "ctx_chars": 9890, "t_end": 1791528924.1262617, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0071, "lo95": 1.0068, "mean": 1.0085, "ev_only": 1.0059, "ref_ms": 8.01504, "cand_ms": 7.9588, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 299.73, "compile_s": 2.23, "r_error": "", "src_len": 1001, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5888, "tout": 526, "ts": 1791528624.3191779, "chk": null, "code_len": 1001}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5888, "started": 1791528618.8557048}
{"ep": "h1-00428", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1808, "speedup": 2.1808, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 295.8, "calls": 2, "tokens_in": 12558, "tokens_out": 1492, "ctx_chars": 9855, "t_end": 1791528940.0449948, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.1808, "lo95": 2.1797, "mean": 2.1768, "ev_only": 2.1761, "ref_ms": 6.30065, "cand_ms": 2.88912, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2715, "r_wall_s": 177.12, "compile_s": 2.69, "r_error": "", "src_len": 877, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 998, "ts": 1791528653.6986992, "chk": "ok", "code_len": 877}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6712, "tout": 494, "ts": 1791528761.882969, "chk": null, "code_len": 877}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791528644.2353523}
{"ep": "h1-00443", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.294, "speedup": 1.294, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 204.1, "calls": 2, "tokens_in": 6092, "tokens_out": 9516, "ctx_chars": 0, "t_end": 1791528942.0799458, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.294, "lo95": 1.2929, "mean": 1.3301, "ev_only": 1.2898, "ref_ms": 5.32056, "cand_ms": 4.11174, "n_trials": 209, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9988, "r_wall_s": 93.36, "compile_s": 14.89, "r_error": "", "src_len": 5267, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1476, "tout": 6797, "ts": 1791528797.9701383, "chk": "ok", "code_len": 5267}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4616, "tout": 2719, "ts": 1791528848.2167394, "chk": null, "code_len": 5267}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1476, "started": 1791528737.9633296}
{"ep": "h1-00478", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0679, "speedup": 1.0679, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 99.8, "calls": 2, "tokens_in": 11986, "tokens_out": 1830, "ctx_chars": 8462, "t_end": 1791528948.585747, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0679, "lo95": 1.0673, "mean": 1.0665, "ev_only": 1.0661, "ref_ms": 8.51524, "cand_ms": 7.97375, "n_trials": 147, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 63.02, "compile_s": 1.98, "r_error": "", "src_len": 1449, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1070, "ts": 1791528860.615423, "chk": "ok", "code_len": 1449}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6584, "tout": 760, "ts": 1791528885.4204147, "chk": null, "code_len": 1449}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791528848.750884}
{"ep": "h1-00467", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 27.1325, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 133.9, "calls": 2, "tokens_in": 5156, "tokens_out": 3890, "ctx_chars": 0, "t_end": 1791528951.872448, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 27.1325, "lo95": 26.4291, "mean": 28.0014, "ev_only": 28.4472, "ref_ms": 16.03285, "cand_ms": 0.59091, "n_trials": 84, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.9445, "r_wall_s": 87.77, "compile_s": 2.07, "r_error": "", "src_len": 2497, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1708, "tout": 2571, "ts": 1791528840.9923098, "chk": "ok", "code_len": 2497}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3448, "tout": 1319, "ts": 1791528863.941137, "chk": null, "code_len": 2497}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1708, "started": 1791528817.97452}
{"ep": "h1-00449", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4036, "speedup": 1.4036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 201.6, "calls": 2, "tokens_in": 13603, "tokens_out": 2729, "ctx_chars": 10210, "t_end": 1791528958.9378376, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4036, "lo95": 1.3988, "mean": 1.4031, "ev_only": 1.4036, "ref_ms": 19.30817, "cand_ms": 13.75636, "n_trials": 90, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0643, "r_wall_s": 79.95, "compile_s": 1.97, "r_error": "", "src_len": 1726, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 1835, "ts": 1791528777.4854238, "chk": "ok", "code_len": 1726}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7468, "tout": 894, "ts": 1791528878.5289862, "chk": null, "code_len": 1726}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791528757.3273344}
{"ep": "h1-00491", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.013, "speedup": 1.013, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 84.3, "calls": 2, "tokens_in": 4165, "tokens_out": 1651, "ctx_chars": 0, "t_end": 1791528965.06528, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.013, "lo95": 1.0122, "mean": 1.0152, "ev_only": 1.0155, "ref_ms": 8.12102, "cand_ms": 8.01665, "n_trials": 151, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 47.61, "compile_s": 1.98, "r_error": "", "src_len": 890, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1670, "tout": 1084, "ts": 1791528890.664482, "chk": "ok", "code_len": 890}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2495, "tout": 567, "ts": 1791528917.3579195, "chk": null, "code_len": 890}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1670, "started": 1791528880.7685652}
{"ep": "h1-00496", "task": "L1_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 71.9, "calls": 1, "tokens_in": 1960, "tokens_out": 1552, "ctx_chars": 0, "t_end": 1791528965.9123833, "error": "RuntimeError: Error building extension 'wtransform': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=wtransform -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 56.57, "compile_s": 56.56, "r_error": "RuntimeError: Error building extension 'wtransform': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=wtransform -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "src_len": 2347, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1960, "tout": 1552, "ts": 1791528909.3185372, "chk": null, "code_len": 2347}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1960, "started": 1791528894.0337937}
{"ep": "h1-00425", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9374, "speedup": 1.9374, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 341.3, "calls": 2, "tokens_in": 14813, "tokens_out": 4447, "ctx_chars": 10743, "t_end": 1791528975.732529, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.9374, "lo95": 1.9351, "mean": 1.9368, "ev_only": 1.9357, "ref_ms": 19.47904, "cand_ms": 10.05443, "n_trials": 65, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0844, "r_wall_s": 220.13, "compile_s": 3.28, "r_error": "", "src_len": 2460, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6466, "tout": 3150, "ts": 1791528664.597132, "chk": "ok", "code_len": 2460}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8347, "tout": 1297, "ts": 1791528755.3055918, "chk": null, "code_len": 2460}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6466, "started": 1791528634.402252}
{"ep": "h1-00388", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.1445, "speedup": 4.1445, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 465.2, "calls": 3, "tokens_in": 27852, "tokens_out": 17461, "ctx_chars": 8224, "t_end": 1791528975.9138103, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.1445, "lo95": 4.137, "mean": 4.1391, "ev_only": 4.1503, "ref_ms": 32.05076, "cand_ms": 7.73331, "n_trials": 36, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9818, "r_wall_s": 60.14, "compile_s": 43.47, "r_error": "", "src_len": 6415, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5510, "tout": 10732, "ts": 1791528610.5151753, "chk": "no_custom_kernel", "code_len": 6439}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9460, "tout": 3491, "ts": 1791528800.673978, "chk": "ok", "code_len": 6415}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12882, "tout": 3238, "ts": 1791528915.729069, "chk": null, "code_len": 6415}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5510, "started": 1791528510.7058718}
{"ep": "h1-00461", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3869, "speedup": 1.3869, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 197.3, "calls": 2, "tokens_in": 5968, "tokens_out": 6723, "ctx_chars": 0, "t_end": 1791528980.7188687, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3869, "lo95": 1.3834, "mean": 1.3851, "ev_only": 1.3854, "ref_ms": 7.55379, "cand_ms": 5.44639, "n_trials": 195, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1368, "r_wall_s": 118.73, "compile_s": 15.16, "r_error": "", "src_len": 4142, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1685, "tout": 4716, "ts": 1791528825.9680471, "chk": "ok", "code_len": 4142}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4283, "tout": 2007, "ts": 1791528861.5829217, "chk": null, "code_len": 4142}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1685, "started": 1791528783.4100947}
{"ep": "h1-00473", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2826, "speedup": 1.2826, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 143.0, "calls": 2, "tokens_in": 13254, "tokens_out": 2350, "ctx_chars": 9893, "t_end": 1791528982.9086282, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2826, "lo95": 1.2822, "mean": 1.2824, "ev_only": 1.2829, "ref_ms": 19.75651, "cand_ms": 15.40314, "n_trials": 83, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0404, "r_wall_s": 74.61, "compile_s": 1.96, "r_error": "", "src_len": 1562, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5991, "tout": 1547, "ts": 1791528853.5407925, "chk": "ok", "code_len": 1562}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7263, "tout": 803, "ts": 1791528907.4901211, "chk": null, "code_len": 1562}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5991, "started": 1791528839.9436996}
{"ep": "h1-00448", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4458, "speedup": 1.4458, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 227.0, "calls": 2, "tokens_in": 4636, "tokens_out": 2176, "ctx_chars": 0, "t_end": 1791528983.5437918, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4458, "lo95": 1.4453, "mean": 1.4448, "ev_only": 1.4473, "ref_ms": 13.95911, "cand_ms": 9.65507, "n_trials": 129, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0693, "r_wall_s": 97.89, "compile_s": 2.48, "r_error": "", "src_len": 1292, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 1432, "ts": 1791528768.8858023, "chk": "ok", "code_len": 1292}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2885, "tout": 744, "ts": 1791528884.8753788, "chk": null, "code_len": 1292}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1751, "started": 1791528756.5604467}
{"ep": "h1-00431", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3996, "speedup": 1.3996, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 323.9, "calls": 2, "tokens_in": 7371, "tokens_out": 8781, "ctx_chars": 0, "t_end": 1791528996.8700705, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3996, "lo95": 1.3977, "mean": 1.3991, "ev_only": 1.4011, "ref_ms": 11.04019, "cand_ms": 7.88822, "n_trials": 143, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1675, "r_wall_s": 231.82, "compile_s": 15.83, "r_error": "", "src_len": 7150, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1619, "tout": 5256, "ts": 1791528714.8670025, "chk": "ok", "code_len": 7150}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5752, "tout": 3525, "ts": 1791528764.11193, "chk": null, "code_len": 7150}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1619, "started": 1791528672.9323382}
{"ep": "h1-00464", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 19.1373, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 209.2, "calls": 2, "tokens_in": 11610, "tokens_out": 8271, "ctx_chars": 6034, "t_end": 1791529002.8565447, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 19.1373, "lo95": 19.0849, "mean": 19.2214, "ev_only": 19.1633, "ref_ms": 28.52332, "cand_ms": 1.49046, "n_trials": 28, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9137, "r_wall_s": 103.22, "compile_s": 17.55, "r_error": "", "src_len": 3973, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 6362, "ts": 1791528850.0050895, "chk": "ok", "code_len": 3973}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7062, "tout": 1909, "ts": 1791528899.6099966, "chk": null, "code_len": 3973}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4548, "started": 1791528793.6415546}
{"ep": "h1-00427", "task": "L3_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9992, "speedup": 0.9992, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 362.3, "calls": 2, "tokens_in": 9798, "tokens_out": 1705, "ctx_chars": 6513, "t_end": 1791529004.6404805, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9992, "lo95": 0.9989, "mean": 0.9996, "ev_only": 0.9986, "ref_ms": 10.67145, "cand_ms": 10.67946, "n_trials": 54, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0018, "r_wall_s": 99.22, "compile_s": 3.73, "r_error": "", "src_len": 1662, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4387, "tout": 915, "ts": 1791528651.772316, "chk": "ok", "code_len": 1749}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5411, "tout": 790, "ts": 1791528905.2062945, "chk": null, "code_len": 1662}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4387, "started": 1791528642.3177772}
{"ep": "h1-00415", "task": "L3_038", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9638, "speedup": 0.9638, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 424.4, "calls": 2, "tokens_in": 12253, "tokens_out": 2032, "ctx_chars": 8224, "t_end": 1791529012.8192325, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9638, "lo95": 0.6474, "mean": 0.8307, "ev_only": 0.9636, "ref_ms": 118.7218, "cand_ms": 123.18398, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 234.79, "compile_s": 4.3, "r_error": "", "src_len": 1678, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5514, "tout": 1113, "ts": 1791528599.9947166, "chk": "ok", "code_len": 1698}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6739, "tout": 919, "ts": 1791528777.915237, "chk": null, "code_len": 1678}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5514, "started": 1791528588.4593933}
{"ep": "h1-00471", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1592, "speedup": 1.1592, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 178.9, "calls": 2, "tokens_in": 4957, "tokens_out": 4417, "ctx_chars": 0, "t_end": 1791529014.3757424, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1592, "lo95": 1.1589, "mean": 1.1802, "ev_only": 1.1602, "ref_ms": 7.37074, "cand_ms": 6.35853, "n_trials": 203, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 28.69, "compile_s": 1.84, "r_error": "", "src_len": 2292, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 2974, "ts": 1791528862.10143, "chk": "ok", "code_len": 2292}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3393, "tout": 1443, "ts": 1791528985.6080842, "chk": null, "code_len": 2292}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791528835.5039032}
{"ep": "h1-00463", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3785, "speedup": 1.3785, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 223.2, "calls": 2, "tokens_in": 14317, "tokens_out": 5053, "ctx_chars": 10384, "t_end": 1791529015.246785, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3785, "lo95": 1.3768, "mean": 1.3766, "ev_only": 1.382, "ref_ms": 2.86656, "cand_ms": 2.07944, "n_trials": 215, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 97.77, "compile_s": 2.63, "r_error": "", "src_len": 2657, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6193, "tout": 3209, "ts": 1791528840.5274806, "chk": "ok", "code_len": 2657}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8124, "tout": 1844, "ts": 1791528917.2927659, "chk": null, "code_len": 2657}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6193, "started": 1791528812.4139166}
{"ep": "h1-00453", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2422, "speedup": 0.2422, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 248.1, "calls": 3, "tokens_in": 12319, "tokens_out": 8582, "ctx_chars": 0, "t_end": 1791529016.5448098, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.2422, "lo95": 0.2411, "mean": 0.2428, "ev_only": 0.2405, "ref_ms": 2.45176, "cand_ms": 10.12114, "n_trials": 114, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 135.73, "compile_s": 14.02, "r_error": "", "src_len": 3907, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 4413, "ts": 1791528806.5364344, "chk": "no_custom_kernel", "code_len": 3929}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4245, "tout": 2139, "ts": 1791528839.596131, "chk": "ok", "code_len": 3907}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6323, "tout": 2030, "ts": 1791528880.6937697, "chk": null, "code_len": 3907}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1751, "started": 1791528768.4271984}
{"ep": "h1-00504", "task": "L2_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 74.6, "calls": 1, "tokens_in": 1694, "tokens_out": 854, "ctx_chars": 0, "t_end": 1791529016.6739774, "error": "RuntimeError: Error building extension 'scale_add_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=scale_add_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 66.27, "compile_s": 66.26, "r_error": "RuntimeError: Error building extension 'scale_add_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=scale_add_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "src_len": 1870, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1694, "tout": 854, "ts": 1791528950.3745801, "chk": null, "code_len": 1870}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1694, "started": 1791528942.0801842}
{"ep": "h1-00480", "task": "L2_052", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3443, "speedup": 1.3443, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 198.1, "calls": 3, "tokens_in": 23014, "tokens_out": 3321, "ctx_chars": 11132, "t_end": 1791529048.7854478, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3443, "lo95": 1.3425, "mean": 1.3444, "ev_only": 1.3433, "ref_ms": 11.02869, "cand_ms": 8.2043, "n_trials": 137, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1776, "r_wall_s": 110.16, "compile_s": 3.52, "r_error": "", "src_len": 3076, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6454, "tout": 1608, "ts": 1791528864.5976844, "chk": "ok", "code_len": 3076}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8172, "tout": 192, "ts": 1791528924.0219631, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8388, "tout": 1521, "ts": 1791528936.9517386, "chk": null, "code_len": 3076}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6454, "started": 1791528850.7161946}
{"ep": "h1-00441", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4398, "speedup": 1.4398, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 331.4, "calls": 2, "tokens_in": 4612, "tokens_out": 2171, "ctx_chars": 0, "t_end": 1791529048.8815064, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4398, "lo95": 1.4393, "mean": 1.4393, "ev_only": 1.4395, "ref_ms": 14.18995, "cand_ms": 9.85567, "n_trials": 59, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0839, "r_wall_s": 259.82, "compile_s": 2.24, "r_error": "", "src_len": 1307, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 1488, "ts": 1791528730.9787128, "chk": "ok", "code_len": 1307}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2861, "tout": 683, "ts": 1791528787.8587832, "chk": null, "code_len": 1307}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1751, "started": 1791528717.4819129}
{"ep": "h1-00498", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4546, "speedup": 1.4546, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 152.4, "calls": 2, "tokens_in": 5094, "tokens_out": 4077, "ctx_chars": 0, "t_end": 1791529050.9977505, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4546, "lo95": 1.441, "mean": 1.4825, "ev_only": 1.4444, "ref_ms": 7.3915, "cand_ms": 5.08164, "n_trials": 200, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 97.78, "compile_s": 7.44, "r_error": "", "src_len": 2186, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1701, "tout": 2734, "ts": 1791528923.55915, "chk": "ok", "code_len": 2186}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3393, "tout": 1343, "ts": 1791528952.8963091, "chk": null, "code_len": 2186}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1701, "started": 1791528898.5954406}
{"ep": "h1-00522", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0052, "speedup": 1.0052, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 49.8, "calls": 2, "tokens_in": 13365, "tokens_out": 1362, "ctx_chars": 10823, "t_end": 1791529066.4952128, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0052, "lo95": 1.0049, "mean": 1.0058, "ev_only": 1.0057, "ref_ms": 7.97238, "cand_ms": 7.93124, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0048, "r_wall_s": 25.4, "compile_s": 2.58, "r_error": "", "src_len": 884, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6277, "tout": 892, "ts": 1791529024.9318032, "chk": "ok", "code_len": 884}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7088, "tout": 470, "ts": 1791529041.0009499, "chk": null, "code_len": 884}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6277, "started": 1791529016.674191}
{"ep": "h1-00412", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0144, "speedup": 1.0144, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 486.4, "calls": 2, "tokens_in": 18012, "tokens_out": 19922, "ctx_chars": 6513, "t_end": 1791529069.654926, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0144, "lo95": 1.0095, "mean": 1.0181, "ev_only": 1.0145, "ref_ms": 38.76258, "cand_ms": 38.21241, "n_trials": 35, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0724, "r_wall_s": 313.35, "compile_s": 2.91, "r_error": "", "src_len": 12376, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 13967, "ts": 1791528701.3276865, "chk": "ok", "code_len": 12376}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12285, "tout": 5955, "ts": 1791528756.1396313, "chk": null, "code_len": 12376}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791528583.2520971}
{"ep": "h1-00458", "task": "L3_038", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7762, "speedup": 0.7762, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 295.1, "calls": 1, "tokens_in": 1970, "tokens_out": 1216, "ctx_chars": 0, "t_end": 1791529072.0723977, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7762, "lo95": 0.7722, "mean": 0.8185, "ev_only": 0.7763, "ref_ms": 81.00397, "cand_ms": 104.35779, "n_trials": 11, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0003, "r_wall_s": 282.62, "compile_s": 57.42, "r_error": "", "src_len": 2165, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1970, "tout": 1216, "ts": 1791528789.339016, "chk": null, "code_len": 2165}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1970, "started": 1791528777.0147104}
{"ep": "h1-00472", "task": "L1_065", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4028, "speedup": 0.4028, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 234.6, "calls": 2, "tokens_in": 10193, "tokens_out": 7471, "ctx_chars": 0, "t_end": 1791529072.572073, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4028, "lo95": 0.402, "mean": 0.4028, "ev_only": 0.4024, "ref_ms": 44.46438, "cand_ms": 110.3829, "n_trials": 10, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 140.67, "compile_s": 1.95, "r_error": "", "src_len": 3092, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2037, "tout": 6007, "ts": 1791528895.1602376, "chk": "ok", "code_len": 3092}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8156, "tout": 1464, "ts": 1791528930.371637, "chk": null, "code_len": 3092}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2037, "started": 1791528838.006569}
{"ep": "h1-00386", "task": "L3_045", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0041, "speedup": 1.0041, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 578.8, "calls": 5, "tokens_in": 36662, "tokens_out": 10657, "ctx_chars": 0, "t_end": 1791529085.345551, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0041, "lo95": 1.0018, "mean": 1.0054, "ev_only": 1.0024, "ref_ms": 23.56508, "cand_ms": 23.46772, "n_trials": 67, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 42.63, "compile_s": 2.32, "r_error": "", "src_len": 3303, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2734, "tout": 2261, "ts": 1791528526.6703217, "chk": "incorrect", "code_len": 4447}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5127, "tout": 1918, "ts": 1791528574.5135045, "chk": "incorrect", "code_len": 3543}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7178, "tout": 2427, "ts": 1791528754.1740363, "chk": "incorrect", "code_len": 3589}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9738, "tout": 2015, "ts": 1791528784.58087, "chk": "ok", "code_len": 3303}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11885, "tout": 2036, "ts": 1791529042.6818619, "chk": null, "code_len": 3303}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 2734, "started": 1791528506.5850925}
{"ep": "h1-00382", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.1264, "speedup": 3.1264, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 592.9, "calls": 3, "tokens_in": 16993, "tokens_out": 14401, "ctx_chars": 0, "t_end": 1791529085.9773016, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.1264, "lo95": 3.1198, "mean": 3.1406, "ev_only": 3.1426, "ref_ms": 35.90645, "cand_ms": 11.48485, "n_trials": 42, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9992, "r_wall_s": 161.46, "compile_s": 12.71, "r_error": "", "src_len": 6493, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 7608, "ts": 1791528559.2772539, "chk": "no_custom_kernel", "code_len": 6588}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5796, "tout": 3608, "ts": 1791528620.589195, "chk": "ok", "code_len": 6493}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9235, "tout": 3185, "ts": 1791528923.7405455, "chk": null, "code_len": 6493}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1962, "started": 1791528493.1060832}
{"ep": "h1-00450", "task": "L1_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9634, "speedup": 0.9634, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 331.4, "calls": 3, "tokens_in": 24055, "tokens_out": 2255, "ctx_chars": 11175, "t_end": 1791529091.779227, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9634, "lo95": 0.9626, "mean": 0.9667, "ev_only": 0.9605, "ref_ms": 4.38828, "cand_ms": 4.55483, "n_trials": 205, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0328, "r_wall_s": 56.5, "compile_s": 2.5, "r_error": "", "src_len": 2116, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7065, "tout": 1262, "ts": 1791528773.4657948, "chk": "ok", "code_len": 2116}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8439, "tout": 88, "ts": 1791529027.3067403, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8551, "tout": 905, "ts": 1791529035.101962, "chk": null, "code_len": 2116}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7065, "started": 1791528760.4199266}
{"ep": "h1-00420", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0625, "speedup": 1.0625, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 482.7, "calls": 2, "tokens_in": 15916, "tokens_out": 4374, "ctx_chars": 10864, "t_end": 1791529092.531931, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0625, "lo95": 1.0619, "mean": 1.0616, "ev_only": 1.0645, "ref_ms": 3.72607, "cand_ms": 3.5069, "n_trials": 245, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 315.65, "compile_s": 3.39, "r_error": "", "src_len": 3205, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6949, "tout": 2737, "ts": 1791528633.1240313, "chk": "ok", "code_len": 3205}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8967, "tout": 1637, "ts": 1791528775.9850214, "chk": null, "code_len": 3205}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6949, "started": 1791528609.871842}
{"ep": "h1-00477", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9622, "speedup": 0.9622, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.1, "calls": 3, "tokens_in": 15092, "tokens_out": 13370, "ctx_chars": 0, "t_end": 1791529108.7163906, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9622, "lo95": 0.9621, "mean": 0.9621, "ev_only": 0.9619, "ref_ms": 20.29034, "cand_ms": 21.08664, "n_trials": 75, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 77.11, "compile_s": 12.63, "r_error": "", "src_len": 4412, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2008, "tout": 8113, "ts": 1791528921.0359828, "chk": "no_custom_kernel", "code_len": 4412}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5215, "tout": 2759, "ts": 1791528990.856444, "chk": "ok", "code_len": 4412}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7869, "tout": 2498, "ts": 1791529030.8273304, "chk": null, "code_len": 4412}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2008, "started": 1791528847.6641624}
{"ep": "h1-00479", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.0367, "speedup": 0.0367, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.7, "calls": 3, "tokens_in": 24295, "tokens_out": 10147, "ctx_chars": 9898, "t_end": 1791529111.701354, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0367, "lo95": 0.0366, "mean": 0.0387, "ev_only": 0.0366, "ref_ms": 16.10269, "cand_ms": 439.34977, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9999, "r_wall_s": 41.13, "compile_s": 2.04, "r_error": "", "src_len": 2310, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6027, "tout": 5778, "ts": 1791528904.6578722, "chk": "incorrect", "code_len": 2798}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8304, "tout": 3010, "ts": 1791529028.255659, "chk": "ok", "code_len": 2310}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9964, "tout": 1359, "ts": 1791529070.550664, "chk": null, "code_len": 2310}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 6027, "started": 1791528850.0373757}
{"ep": "h1-00481", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3891, "speedup": 1.3891, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 273.3, "calls": 2, "tokens_in": 5256, "tokens_out": 4519, "ctx_chars": 0, "t_end": 1791529124.9613156, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3891, "lo95": 1.3818, "mean": 1.3883, "ev_only": 1.3904, "ref_ms": 33.57215, "cand_ms": 24.1679, "n_trials": 31, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 180.4, "compile_s": 4.15, "r_error": "", "src_len": 2627, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 3090, "ts": 1791528879.0592306, "chk": "ok", "code_len": 2627}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3541, "tout": 1429, "ts": 1791528944.520646, "chk": null, "code_len": 2627}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791528851.6652176}
{"ep": "h1-00514", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.5791, "speedup": 2.5791, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.6, "calls": 2, "tokens_in": 7627, "tokens_out": 8711, "ctx_chars": 0, "t_end": 1791529126.1793642, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.5791, "lo95": 2.5772, "mean": 2.5697, "ev_only": 2.6068, "ref_ms": 4.01067, "cand_ms": 1.55508, "n_trials": 217, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3668, "r_wall_s": 54.05, "compile_s": 2.03, "r_error": "", "src_len": 3209, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 7034, "ts": 1791529050.2861524, "chk": "ok", "code_len": 3209}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4934, "tout": 1677, "ts": 1791529071.7814713, "chk": null, "code_len": 3209}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791528983.544375}
{"ep": "h1-00528", "task": "L2_025", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 62.9, "calls": 1, "tokens_in": 1584, "tokens_out": 1045, "ctx_chars": 0, "t_end": 1791529134.9371734, "error": "RuntimeError: Error building extension 'min_tanh_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=min_tanh_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 52.65, "compile_s": 52.65, "r_error": "RuntimeError: Error building extension 'min_tanh_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=min_tanh_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 1945, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1584, "tout": 1045, "ts": 1791529082.2597017, "chk": null, "code_len": 1945}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1584, "started": 1791529072.0726323}
{"ep": "h1-00493", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0039, "speedup": 1.0039, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 249.6, "calls": 2, "tokens_in": 13646, "tokens_out": 1498, "ctx_chars": 10909, "t_end": 1791529139.127138, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0039, "lo95": 1.0012, "mean": 1.0022, "ev_only": 1.0036, "ref_ms": 16.12293, "cand_ms": 16.05952, "n_trials": 62, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.001, "r_wall_s": 160.48, "compile_s": 3.86, "r_error": "", "src_len": 938, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6428, "tout": 964, "ts": 1791528898.1502724, "chk": "ok", "code_len": 938}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7218, "tout": 534, "ts": 1791528978.5975595, "chk": null, "code_len": 938}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6428, "started": 1791528889.4914944}
{"ep": "h1-00456", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2436, "speedup": 1.2436, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 374.1, "calls": 2, "tokens_in": 15711, "tokens_out": 2620, "ctx_chars": 12155, "t_end": 1791529144.1073859, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2436, "lo95": 1.2432, "mean": 1.2432, "ev_only": 1.2421, "ref_ms": 12.04387, "cand_ms": 9.6844, "n_trials": 138, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0677, "r_wall_s": 96.77, "compile_s": 3.48, "r_error": "", "src_len": 1596, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7203, "tout": 1732, "ts": 1791528786.4812284, "chk": "ok", "code_len": 1596}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8508, "tout": 888, "ts": 1791529046.103171, "chk": null, "code_len": 1596}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7203, "started": 1791528770.0456727}
{"ep": "h1-00439", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.3728, "speedup": 0.3728, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 451.0, "calls": 2, "tokens_in": 6566, "tokens_out": 10011, "ctx_chars": 0, "t_end": 1791529157.5150607, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.3728, "lo95": 0.3724, "mean": 0.3736, "ev_only": 0.3732, "ref_ms": 28.89378, "cand_ms": 77.49763, "n_trials": 22, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9999, "r_wall_s": 196.64, "compile_s": 4.2, "r_error": "", "src_len": 4174, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1902, "tout": 7878, "ts": 1791528776.9261258, "chk": "ok", "code_len": 4174}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4664, "tout": 2133, "ts": 1791528960.5269208, "chk": null, "code_len": 4174}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1902, "started": 1791528706.5372336}
{"ep": "h1-00511", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0507, "speedup": 1.0507, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 184.0, "calls": 2, "tokens_in": 15893, "tokens_out": 3875, "ctx_chars": 10864, "t_end": 1791529159.907512, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0507, "lo95": 1.0311, "mean": 1.0395, "ev_only": 1.0486, "ref_ms": 3.74385, "cand_ms": 3.56321, "n_trials": 229, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 139.23, "compile_s": 1.97, "r_error": "", "src_len": 3129, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6949, "tout": 2293, "ts": 1791528994.18518, "chk": "ok", "code_len": 3129}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8944, "tout": 1582, "ts": 1791529019.5419357, "chk": null, "code_len": 3129}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6949, "started": 1791528975.9140384}
{"ep": "h1-00523", "task": "L2_084", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0024, "speedup": 1.0024, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 112.5, "calls": 3, "tokens_in": 20711, "tokens_out": 3082, "ctx_chars": 9192, "t_end": 1791529161.3282845, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0024, "lo95": 1.0021, "mean": 1.0025, "ev_only": 1.0029, "ref_ms": 8.09286, "cand_ms": 8.07339, "n_trials": 165, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0185, "r_wall_s": 17.72, "compile_s": 1.9, "r_error": "", "src_len": 2756, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5719, "tout": 1624, "ts": 1791529084.5858772, "chk": "ok", "code_len": 2756}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7455, "tout": 58, "ts": 1791529132.0275304, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7537, "tout": 1400, "ts": 1791529143.4510589, "chk": null, "code_len": 2756}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5719, "started": 1791529069.3220785}
{"ep": "h1-00526", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0677, "speedup": 1.0677, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 101.9, "calls": 2, "tokens_in": 4699, "tokens_out": 2600, "ctx_chars": 0, "t_end": 1791529168.3820097, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0677, "lo95": 1.0659, "mean": 1.0671, "ev_only": 1.0675, "ref_ms": 8.50909, "cand_ms": 7.96973, "n_trials": 184, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0052, "r_wall_s": 69.36, "compile_s": 2.16, "r_error": "", "src_len": 1656, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 1680, "ts": 1791529080.7300496, "chk": "ok", "code_len": 1656}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2984, "tout": 920, "ts": 1791529098.9521687, "chk": null, "code_len": 1656}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791529066.4954648}
{"ep": "h1-00486", "task": "L2_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0775, "speedup": 1.0775, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 306.9, "calls": 2, "tokens_in": 6074, "tokens_out": 3262, "ctx_chars": 0, "t_end": 1791529169.9221966, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0775, "lo95": 1.0722, "mean": 1.07, "ev_only": 1.0736, "ref_ms": 12.8088, "cand_ms": 11.88712, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0323, "r_wall_s": 230.58, "compile_s": 3.44, "r_error": "", "src_len": 2152, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1861, "tout": 2240, "ts": 1791528885.2251658, "chk": "ok", "code_len": 2152}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4213, "tout": 1022, "ts": 1791528939.3113866, "chk": null, "code_len": 2152}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1861, "started": 1791528863.0203586}
{"ep": "h1-00487", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5829, "speedup": 0.5829, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 298.9, "calls": 2, "tokens_in": 14640, "tokens_out": 4016, "ctx_chars": 11132, "t_end": 1791529171.3655019, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.5829, "lo95": 0.5826, "mean": 0.5877, "ev_only": 0.5825, "ref_ms": 3.6353, "cand_ms": 6.23673, "n_trials": 192, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 210.0, "compile_s": 4.64, "r_error": "", "src_len": 2499, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 2744, "ts": 1791528897.1453938, "chk": "ok", "code_len": 2499}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8214, "tout": 1272, "ts": 1791528959.6650631, "chk": null, "code_len": 2499}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6426, "started": 1791528872.439345}
{"ep": "h1-00445", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8211, "speedup": 0.8211, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 427.0, "calls": 2, "tokens_in": 4935, "tokens_out": 4773, "ctx_chars": 0, "t_end": 1791529172.1302276, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8211, "lo95": 0.8205, "mean": 0.8211, "ev_only": 0.8212, "ref_ms": 7.51435, "cand_ms": 9.15128, "n_trials": 180, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 219.2, "compile_s": 6.11, "r_error": "", "src_len": 2339, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 3212, "ts": 1791528774.3593056, "chk": "ok", "code_len": 2339}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3368, "tout": 1561, "ts": 1791528952.8477314, "chk": null, "code_len": 2339}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791528745.1357434}
{"ep": "h1-00533", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.553, "speedup": 1.553, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.4, "calls": 2, "tokens_in": 15836, "tokens_out": 4235, "ctx_chars": 11288, "t_end": 1791529172.9254909, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.553, "lo95": 1.551, "mean": 1.5506, "ev_only": 1.5536, "ref_ms": 28.84339, "cand_ms": 18.57284, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0406, "r_wall_s": 33.46, "compile_s": 1.83, "r_error": "", "src_len": 2448, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6972, "tout": 2891, "ts": 1791529118.8865006, "chk": "ok", "code_len": 2448}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8864, "tout": 1344, "ts": 1791529139.0898764, "chk": null, "code_len": 2448}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6972, "started": 1791529092.5321743}
{"ep": "h1-00519", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0903, "speedup": 1.0903, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.0, "calls": 2, "tokens_in": 4477, "tokens_out": 2348, "ctx_chars": 0, "t_end": 1791529177.3627107, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0903, "lo95": 1.0839, "mean": 1.1422, "ev_only": 1.0872, "ref_ms": 16.1053, "cand_ms": 14.77172, "n_trials": 76, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0049, "r_wall_s": 117.58, "compile_s": 3.74, "r_error": "", "src_len": 1378, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1671, "tout": 1598, "ts": 1791529028.6865041, "chk": "ok", "code_len": 1378}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2806, "tout": 750, "ts": 1791529059.6193974, "chk": null, "code_len": 1378}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1671, "started": 1791529014.376008}
{"ep": "h1-00484", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.0106, "speedup": 2.0106, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 319.2, "calls": 2, "tokens_in": 6190, "tokens_out": 6535, "ctx_chars": 0, "t_end": 1791529180.7934818, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.0106, "lo95": 2.0004, "mean": 2.0067, "ev_only": 2.0256, "ref_ms": 8.68923, "cand_ms": 4.32174, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1868, "r_wall_s": 147.12, "compile_s": 2.2, "r_error": "", "src_len": 3262, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2023, "tout": 4895, "ts": 1791528907.0906973, "chk": "ok", "code_len": 3262}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4167, "tout": 1640, "ts": 1791529032.6717825, "chk": null, "code_len": 3262}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2023, "started": 1791528861.6377277}
{"ep": "h1-00512", "task": "L1_080", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9631, "speedup": 0.9631, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 204.6, "calls": 3, "tokens_in": 22732, "tokens_out": 2194, "ctx_chars": 10864, "t_end": 1791529185.3424838, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9631, "lo95": 0.9622, "mean": 0.9718, "ev_only": 0.9643, "ref_ms": 20.38477, "cand_ms": 21.16675, "n_trials": 66, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0363, "r_wall_s": 143.22, "compile_s": 2.99, "r_error": "", "src_len": 1710, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6630, "tout": 1202, "ts": 1791529014.0109475, "chk": "ok", "code_len": 1710}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7941, "tout": 196, "ts": 1791529034.2559345, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8161, "tout": 796, "ts": 1791529041.2686868, "chk": null, "code_len": 1710}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6630, "started": 1791529001.106509}
{"ep": "h1-00535", "task": "L2_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 77.3, "calls": 1, "tokens_in": 1727, "tokens_out": 1370, "ctx_chars": 0, "t_end": 1791529189.0203047, "error": "RuntimeError: Error building extension 'fused_conv_sub_tanh': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_conv_sub_tanh -DTORCH_API_INCLUDE_EXTENSI", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 44.13, "compile_s": 44.13, "r_error": "RuntimeError: Error building extension 'fused_conv_sub_tanh': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_conv_sub_tanh -DTORCH_API_INCLUDE_EXTENSI", "src_len": 2892, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1727, "tout": 1370, "ts": 1791529144.8145149, "chk": null, "code_len": 2892}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1727, "started": 1791529132.0454495}
{"ep": "h1-00537", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0021, "speedup": 1.0021, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 71.1, "calls": 2, "tokens_in": 13688, "tokens_out": 1504, "ctx_chars": 10909, "t_end": 1791529197.238556, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0021, "lo95": 1.0019, "mean": 1.0207, "ev_only": 1.0025, "ref_ms": 16.04166, "cand_ms": 16.00741, "n_trials": 79, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0009, "r_wall_s": 40.47, "compile_s": 1.85, "r_error": "", "src_len": 916, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6428, "tout": 935, "ts": 1791529135.431011, "chk": "ok", "code_len": 916}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7260, "tout": 569, "ts": 1791529156.6395643, "chk": null, "code_len": 916}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6428, "started": 1791529126.1795897}
{"ep": "h1-00499", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 26.8472, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 300.1, "calls": 3, "tokens_in": 10322, "tokens_out": 5615, "ctx_chars": 0, "t_end": 1791529202.307329, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 26.8472, "lo95": 26.7707, "mean": 26.4865, "ev_only": 26.8237, "ref_ms": 15.93309, "cand_ms": 0.59347, "n_trials": 92, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.9619, "r_wall_s": 30.28, "compile_s": 2.26, "r_error": "", "src_len": 2501, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1708, "tout": 2687, "ts": 1791528927.5285358, "chk": "ok", "code_len": 2464}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3552, "tout": 1503, "ts": 1791528951.6913137, "chk": "ok", "code_len": 2501}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5062, "tout": 1425, "ts": 1791529171.8212137, "chk": null, "code_len": 2501}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 1708, "started": 1791528902.2102973}
{"ep": "h1-00505", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8485, "speedup": 0.8485, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.2, "calls": 2, "tokens_in": 15730, "tokens_out": 5777, "ctx_chars": 10864, "t_end": 1791529203.8262324, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8485, "lo95": 0.8481, "mean": 0.8665, "ev_only": 0.8483, "ref_ms": 20.15313, "cand_ms": 23.7506, "n_trials": 42, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 114.63, "compile_s": 2.14, "r_error": "", "src_len": 3907, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6632, "tout": 3764, "ts": 1791528980.3669374, "chk": "ok", "code_len": 3907}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9098, "tout": 2013, "ts": 1791529088.3764517, "chk": null, "code_len": 3907}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6632, "started": 1791528948.586016}
{"ep": "h1-00490", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1066, "speedup": 1.1066, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 329.5, "calls": 2, "tokens_in": 14332, "tokens_out": 2029, "ctx_chars": 11296, "t_end": 1791529206.647996, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1066, "lo95": 1.1054, "mean": 1.1075, "ev_only": 1.1088, "ref_ms": 31.48947, "cand_ms": 28.45582, "n_trials": 44, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0549, "r_wall_s": 135.13, "compile_s": 2.91, "r_error": "", "src_len": 1236, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6639, "tout": 1381, "ts": 1791528890.2764957, "chk": "ok", "code_len": 1236}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7693, "tout": 648, "ts": 1791528935.8003051, "chk": null, "code_len": 1236}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6639, "started": 1791528877.166754}
{"ep": "h1-00495", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 37.3568, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 316.1, "calls": 2, "tokens_in": 12021, "tokens_out": 2781, "ctx_chars": 8570, "t_end": 1791529208.2988045, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 37.3568, "lo95": 37.2761, "mean": 36.6466, "ev_only": 38.4454, "ref_ms": 15.9648, "cand_ms": 0.42736, "n_trials": 89, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.3563, "r_wall_s": 275.22, "compile_s": 2.71, "r_error": "", "src_len": 1573, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5372, "tout": 1954, "ts": 1791528910.2891502, "chk": "ok", "code_len": 1573}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6649, "tout": 827, "ts": 1791528932.9007652, "chk": null, "code_len": 1573}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5372, "started": 1791528892.1579182}
{"ep": "h1-00355", "task": "L3_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 839.8, "calls": 5, "tokens_in": 55896, "tokens_out": 16066, "ctx_chars": 0, "t_end": 1791529214.5588293, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.0471, "r_wall_s": 20.17, "compile_s": 1.95, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 2246, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2675, "tout": 5127, "ts": 1791528423.20755, "chk": "incorrect", "code_len": 2486}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7938, "tout": 3957, "ts": 1791528478.3249836, "chk": "incorrect", "code_len": 2807}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12031, "tout": 3801, "ts": 1791528611.228674, "chk": "forbidden", "code_len": 2191}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 15926, "tout": 1238, "ts": 1791528755.13897, "chk": "incorrect", "code_len": 2289}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 17326, "tout": 1943, "ts": 1791529058.208168, "chk": null, "code_len": 2246}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "forbidden", "incorrect", null], "first_tin": 2675, "started": 1791528374.772943}
{"ep": "h1-00444", "task": "L2_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3376, "speedup": 1.3376, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 473.9, "calls": 2, "tokens_in": 15393, "tokens_out": 2939, "ctx_chars": 11357, "t_end": 1791529217.5227797, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3376, "lo95": 1.3371, "mean": 1.3372, "ev_only": 1.3378, "ref_ms": 7.49737, "cand_ms": 5.60492, "n_trials": 220, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0984, "r_wall_s": 276.93, "compile_s": 3.26, "r_error": "", "src_len": 2298, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6779, "tout": 1723, "ts": 1791528760.024534, "chk": "ok", "code_len": 2298}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8614, "tout": 1216, "ts": 1791528940.1400979, "chk": null, "code_len": 2298}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6779, "started": 1791528743.6606412}
{"ep": "h1-00436", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0129, "speedup": 1.0129, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 527.0, "calls": 2, "tokens_in": 11406, "tokens_out": 13353, "ctx_chars": 0, "t_end": 1791529217.819324, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0129, "lo95": 1.0053, "mean": 1.0209, "ev_only": 1.0124, "ref_ms": 39.5035, "cand_ms": 39.0009, "n_trials": 36, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0657, "r_wall_s": 27.58, "compile_s": 1.99, "r_error": "", "src_len": 9623, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 8617, "ts": 1791528762.6023257, "chk": "ok", "code_len": 9623}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8382, "tout": 4736, "ts": 1791529057.6749866, "chk": null, "code_len": 9623}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791528690.7913096}
{"ep": "h1-00540", "task": "L3_034", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8201, "speedup": 0.8201, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 77.9, "calls": 3, "tokens_in": 16323, "tokens_out": 2231, "ctx_chars": 6034, "t_end": 1791529222.0460713, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8201, "lo95": 0.8004, "mean": 0.7489, "ev_only": 0.82, "ref_ms": 28.88189, "cand_ms": 35.21567, "n_trials": 30, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1716, "r_wall_s": 49.28, "compile_s": 2.49, "r_error": "", "src_len": 2110, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4546, "tout": 1206, "ts": 1791529155.2459013, "chk": "ok", "code_len": 2180}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5864, "tout": 25, "ts": 1791529164.382943, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5913, "tout": 1000, "ts": 1791529172.7424273, "chk": null, "code_len": 2110}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4546, "started": 1791529144.107694}
{"ep": "h1-00543", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0626, "speedup": 1.0626, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 62.0, "calls": 2, "tokens_in": 12252, "tokens_out": 2269, "ctx_chars": 8462, "t_end": 1791529223.3557522, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0626, "lo95": 1.0621, "mean": 1.0631, "ev_only": 1.066, "ref_ms": 8.52211, "cand_ms": 8.02023, "n_trials": 137, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0052, "r_wall_s": 30.07, "compile_s": 2.02, "r_error": "", "src_len": 1714, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1336, "ts": 1791529173.2813947, "chk": "ok", "code_len": 1714}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6850, "tout": 933, "ts": 1791529193.1907375, "chk": null, "code_len": 1714}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791529161.3285236}
{"ep": "h1-00530", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5901, "speedup": 1.5901, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 138.6, "calls": 2, "tokens_in": 16902, "tokens_out": 7606, "ctx_chars": 13278, "t_end": 1791529223.925025, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5901, "lo95": 1.5884, "mean": 1.6006, "ev_only": 1.5934, "ref_ms": 5.29959, "cand_ms": 3.33279, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9868, "r_wall_s": 56.05, "compile_s": 1.87, "r_error": "", "src_len": 3790, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 5548, "ts": 1791529134.4578896, "chk": "ok", "code_len": 3790}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9740, "tout": 2058, "ts": 1791529167.382877, "chk": null, "code_len": 3790}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791529085.3458219}
{"ep": "h1-00468", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4905, "speedup": 0.4905, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 415.5, "calls": 2, "tokens_in": 16908, "tokens_out": 13669, "ctx_chars": 6513, "t_end": 1791529233.6541142, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4905, "lo95": 0.4867, "mean": 0.501, "ev_only": 0.4899, "ref_ms": 6.05381, "cand_ms": 12.34274, "n_trials": 104, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3408, "r_wall_s": 290.52, "compile_s": 3.25, "r_error": "", "src_len": 8501, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6068, "tout": 9301, "ts": 1791528897.5534647, "chk": "ok", "code_len": 8501}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10840, "tout": 4368, "ts": 1791528943.1024258, "chk": null, "code_len": 8501}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6068, "started": 1791528818.1653707}
{"ep": "h1-00447", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.8801, "speedup": 1.8801, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 482.2, "calls": 3, "tokens_in": 13883, "tokens_out": 12915, "ctx_chars": 0, "t_end": 1791529236.5549297, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.8801, "lo95": 1.8783, "mean": 1.8734, "ev_only": 1.8802, "ref_ms": 12.85752, "cand_ms": 6.83888, "n_trials": 118, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 313.63, "compile_s": 12.21, "r_error": "", "src_len": 5258, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1657, "tout": 7395, "ts": 1791528821.3650575, "chk": "no_custom_kernel", "code_len": 5283}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4730, "tout": 2943, "ts": 1791528875.8922155, "chk": "ok", "code_len": 5258}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7496, "tout": 2577, "ts": 1791528922.901981, "chk": null, "code_len": 5258}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1657, "started": 1791528754.3968043}
{"ep": "h1-00518", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0331, "speedup": 1.0331, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 229.5, "calls": 2, "tokens_in": 6880, "tokens_out": 8373, "ctx_chars": 0, "t_end": 1791529242.320378, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0331, "lo95": 1.0284, "mean": 1.0404, "ev_only": 1.0335, "ref_ms": 8.26242, "cand_ms": 7.99794, "n_trials": 147, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9996, "r_wall_s": 68.22, "compile_s": 3.32, "r_error": "", "src_len": 5298, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1771, "tout": 5530, "ts": 1791529060.015398, "chk": "ok", "code_len": 5298}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5109, "tout": 2843, "ts": 1791529173.9981894, "chk": null, "code_len": 5298}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1771, "started": 1791529012.8194902}
{"ep": "h1-00488", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2751, "speedup": 1.2751, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 371.1, "calls": 2, "tokens_in": 5292, "tokens_out": 4403, "ctx_chars": 0, "t_end": 1791529247.276128, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2751, "lo95": 1.2705, "mean": 1.2736, "ev_only": 1.2739, "ref_ms": 17.49704, "cand_ms": 13.7225, "n_trials": 82, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0718, "r_wall_s": 281.77, "compile_s": 22.41, "r_error": "", "src_len": 2857, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1693, "tout": 2983, "ts": 1791528901.988784, "chk": "ok", "code_len": 2857}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3599, "tout": 1420, "ts": 1791528965.062559, "chk": null, "code_len": 2857}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1693, "started": 1791528876.1786194}
{"ep": "h1-00506", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2801, "speedup": 0.2801, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 295.7, "calls": 3, "tokens_in": 11932, "tokens_out": 8665, "ctx_chars": 0, "t_end": 1791529247.6033165, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.2801, "lo95": 0.279, "mean": 0.2794, "ev_only": 0.2811, "ref_ms": 2.37705, "cand_ms": 8.48743, "n_trials": 146, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 57.34, "compile_s": 13.49, "r_error": "", "src_len": 3644, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 4907, "ts": 1791528995.3406951, "chk": "no_custom_kernel", "code_len": 3666}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4123, "tout": 1977, "ts": 1791529025.2218704, "chk": "ok", "code_len": 3644}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6058, "tout": 1781, "ts": 1791529054.2237933, "chk": null, "code_len": 3644}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1751, "started": 1791528951.8727224}
{"ep": "h1-00524", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1909, "speedup": 1.1909, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 203.1, "calls": 2, "tokens_in": 5509, "tokens_out": 4082, "ctx_chars": 0, "t_end": 1791529251.9418483, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1909, "lo95": 1.1904, "mean": 1.1907, "ev_only": 1.1896, "ref_ms": 11.96987, "cand_ms": 10.05142, "n_trials": 121, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0507, "r_wall_s": 139.36, "compile_s": 14.7, "r_error": "", "src_len": 2958, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1778, "tout": 2638, "ts": 1791529071.6416538, "chk": "ok", "code_len": 2958}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3731, "tout": 1444, "ts": 1791529111.404554, "chk": null, "code_len": 2958}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1778, "started": 1791529048.8817255}
{"ep": "h1-00539", "task": "L2_037", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1588, "speedup": 1.1588, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.5, "calls": 3, "tokens_in": 7368, "tokens_out": 1883, "ctx_chars": 0, "t_end": 1791529256.5819209, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1588, "lo95": 1.1583, "mean": 1.1585, "ev_only": 1.1587, "ref_ms": 19.79164, "cand_ms": 17.08, "n_trials": 78, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1507, "r_wall_s": 82.37, "compile_s": 2.14, "r_error": "", "src_len": 1885, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1707, "tout": 993, "ts": 1791529149.2013137, "chk": "ok", "code_len": 1932}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2812, "tout": 13, "ts": 1791529165.7082102, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 2849, "tout": 877, "ts": 1791529173.2729347, "chk": null, "code_len": 1885}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1707, "started": 1791529139.127374}
{"ep": "h1-00507", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2445, "speedup": 1.2445, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 300.5, "calls": 2, "tokens_in": 9924, "tokens_out": 10183, "ctx_chars": 0, "t_end": 1791529259.3888347, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2445, "lo95": 1.2438, "mean": 1.2443, "ev_only": 1.2443, "ref_ms": 75.24689, "cand_ms": 60.46197, "n_trials": 22, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1833, "r_wall_s": 60.45, "compile_s": 3.06, "r_error": "", "src_len": 6089, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 6815, "ts": 1791529016.432729, "chk": "ok", "code_len": 6089}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6903, "tout": 3368, "ts": 1791529065.8354542, "chk": null, "code_len": 6089}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791528958.9382052}
{"ep": "h1-00497", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4893, "speedup": 0.4893, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 362.9, "calls": 2, "tokens_in": 7185, "tokens_out": 8769, "ctx_chars": 0, "t_end": 1791529260.6134381, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.4893, "lo95": 0.4875, "mean": 0.4886, "ev_only": 0.4876, "ref_ms": 3.29973, "cand_ms": 6.7441, "n_trials": 227, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 180.94, "compile_s": 15.59, "r_error": "", "src_len": 5300, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2031, "tout": 6279, "ts": 1791528951.875265, "chk": "ok", "code_len": 5300}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5154, "tout": 2490, "ts": 1791529078.8411841, "chk": null, "code_len": 5300}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2031, "started": 1791528897.761569}
{"ep": "h1-00534", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 24.1547, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 159.4, "calls": 2, "tokens_in": 11819, "tokens_out": 8932, "ctx_chars": 6034, "t_end": 1791529268.1447995, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 24.1547, "lo95": 19.7293, "mean": 22.2941, "ev_only": 24.7627, "ref_ms": 42.28816, "cand_ms": 1.75072, "n_trials": 24, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9089, "r_wall_s": 69.37, "compile_s": 12.32, "r_error": "", "src_len": 4491, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 6768, "ts": 1791529167.5503874, "chk": "ok", "code_len": 4491}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7271, "tout": 2164, "ts": 1791529198.7432218, "chk": null, "code_len": 4491}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4548, "started": 1791529108.7166805}
{"ep": "h1-00510", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7223, "speedup": 1.7223, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 298.2, "calls": 3, "tokens_in": 27698, "tokens_out": 11447, "ctx_chars": 11132, "t_end": 1791529273.9675436, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.7223, "lo95": 1.7162, "mean": 1.6909, "ev_only": 1.7215, "ref_ms": 3.73228, "cand_ms": 2.16704, "n_trials": 210, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 111.85, "compile_s": 11.3, "r_error": "", "src_len": 5048, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 6473, "ts": 1791529033.832871, "chk": "no_custom_kernel", "code_len": 5074}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9351, "tout": 2626, "ts": 1791529118.6110716, "chk": "ok", "code_len": 5048}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11921, "tout": 2348, "ts": 1791529161.1930635, "chk": null, "code_len": 5048}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6426, "started": 1791528975.732798}
{"ep": "h1-00502", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5458, "speedup": 1.5458, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 365.9, "calls": 2, "tokens_in": 5003, "tokens_out": 4241, "ctx_chars": 0, "t_end": 1791529290.0210454, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.5458, "lo95": 1.5451, "mean": 1.5442, "ev_only": 1.5493, "ref_ms": 7.7286, "cand_ms": 4.99989, "n_trials": 184, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 23.86, "compile_s": 1.96, "r_error": "", "src_len": 2485, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 2853, "ts": 1791528949.3659992, "chk": "ok", "code_len": 2485}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3438, "tout": 1388, "ts": 1791529266.097034, "chk": null, "code_len": 2485}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791528924.1265101}
{"ep": "h1-00520", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 14.7934, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 277.2, "calls": 2, "tokens_in": 6257, "tokens_out": 6587, "ctx_chars": 0, "t_end": 1791529292.4869819, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 14.7934, "lo95": 14.7639, "mean": 14.3846, "ev_only": 14.7745, "ref_ms": 10.15588, "cand_ms": 0.68651, "n_trials": 132, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 111.51, "compile_s": 16.85, "r_error": "", "src_len": 5216, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1642, "tout": 4055, "ts": 1791529048.5462663, "chk": "ok", "code_len": 5216}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4615, "tout": 2532, "ts": 1791529180.4130352, "chk": null, "code_len": 5216}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1642, "started": 1791529015.2470126}
{"ep": "h1-00525", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 8.7594, "speedup": 8.7594, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 245.3, "calls": 3, "tokens_in": 16466, "tokens_out": 9586, "ctx_chars": 2425, "t_end": 1791529296.2652748, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 8.7594, "lo95": 8.286, "mean": 8.7502, "ev_only": 8.9748, "ref_ms": 12.0451, "cand_ms": 1.3751, "n_trials": 130, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.7074, "r_wall_s": 32.91, "compile_s": 1.9, "r_error": "", "src_len": 3244, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 3775, "ts": 1791529087.0872228, "chk": "incorrect", "code_len": 2598}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5368, "tout": 4222, "ts": 1791529214.9533834, "chk": "ok", "code_len": 3244}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7505, "tout": 1589, "ts": 1791529263.2295349, "chk": null, "code_len": 3244}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 3593, "started": 1791529050.998037}
{"ep": "h1-00325", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1117, "speedup": 1.1117, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 1036.2, "calls": 5, "tokens_in": 89952, "tokens_out": 57091, "ctx_chars": 0, "t_end": 1791529298.1975143, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1117, "lo95": 1.1065, "mean": 1.1175, "ev_only": 1.1092, "ref_ms": 3.52984, "cand_ms": 3.17513, "n_trials": 194, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0012, "r_wall_s": 38.57, "compile_s": 13.34, "r_error": "", "src_len": 4607, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2845, "tout": 16848, "ts": 1791528402.6262481, "chk": "runtime_error", "code_len": 15704}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11409, "tout": 12075, "ts": 1791528578.1057365, "chk": "incorrect", "code_len": 18459}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 21142, "tout": 9990, "ts": 1791528726.4826837, "chk": "incorrect", "code_len": 8066}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 25817, "tout": 15701, "ts": 1791528935.7724123, "chk": "ok", "code_len": 4607}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 28739, "tout": 2477, "ts": 1791529259.5156395, "chk": null, "code_len": 4607}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "incorrect", "ok", null], "first_tin": 2845, "started": 1791528262.002065}
{"ep": "h1-00560", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.4064, "speedup": 4.4064, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.9, "calls": 2, "tokens_in": 13436, "tokens_out": 3349, "ctx_chars": 9438, "t_end": 1791529299.7182355, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.4064, "lo95": 4.392, "mean": 4.3491, "ev_only": 4.4311, "ref_ms": 7.45605, "cand_ms": 1.69208, "n_trials": 184, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9714, "r_wall_s": 41.64, "compile_s": 2.0, "r_error": "", "src_len": 2202, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5861, "tout": 2052, "ts": 1791529235.00543, "chk": "ok", "code_len": 2202}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7575, "tout": 1297, "ts": 1791529257.973644, "chk": null, "code_len": 2202}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5861, "started": 1791529217.819558}
{"ep": "h1-00569", "task": "L1_013", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9401, "speedup": 0.9401, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 56.4, "calls": 1, "tokens_in": 1699, "tokens_out": 1265, "ctx_chars": 0, "t_end": 1791529308.3601885, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9401, "lo95": 0.9399, "mean": 0.9403, "ev_only": 0.9392, "ref_ms": 7.28481, "cand_ms": 7.74871, "n_trials": 207, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 43.28, "compile_s": 1.98, "r_error": "", "src_len": 2109, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1699, "tout": 1265, "ts": 1791529264.7768474, "chk": null, "code_len": 2109}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1699, "started": 1791529251.9420795}
{"ep": "h1-00532", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2422, "speedup": 1.2422, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 221.6, "calls": 2, "tokens_in": 13090, "tokens_out": 10259, "ctx_chars": 6513, "t_end": 1791529313.3856335, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2422, "lo95": 1.2406, "mean": 1.24, "ev_only": 1.2389, "ref_ms": 5.24912, "cand_ms": 4.22582, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1078, "r_wall_s": 125.18, "compile_s": 2.93, "r_error": "", "src_len": 6128, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4677, "tout": 7053, "ts": 1791529154.357898, "chk": "ok", "code_len": 6128}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8413, "tout": 3206, "ts": 1791529187.8206468, "chk": null, "code_len": 6128}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4677, "started": 1791529091.7795057}
{"ep": "h1-00517", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2746, "speedup": 1.2746, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 309.9, "calls": 2, "tokens_in": 5062, "tokens_out": 3761, "ctx_chars": 0, "t_end": 1791529314.5370939, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2746, "lo95": 1.2717, "mean": 1.2767, "ev_only": 1.2736, "ref_ms": 17.60757, "cand_ms": 13.81437, "n_trials": 81, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0697, "r_wall_s": 115.41, "compile_s": 19.85, "r_error": "", "src_len": 2623, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1693, "tout": 2412, "ts": 1791529025.524797, "chk": "ok", "code_len": 2623}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3369, "tout": 1349, "ts": 1791529062.2132108, "chk": null, "code_len": 2623}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1693, "started": 1791529004.6407113}
{"ep": "h1-00536", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4547, "speedup": 1.4547, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 192.9, "calls": 3, "tokens_in": 24879, "tokens_out": 7885, "ctx_chars": 10384, "t_end": 1791529317.8912418, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4547, "lo95": 1.4529, "mean": 1.4705, "ev_only": 1.4518, "ref_ms": 7.33335, "cand_ms": 5.04104, "n_trials": 192, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 93.15, "compile_s": 1.96, "r_error": "", "src_len": 2503, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6176, "tout": 4479, "ts": 1791529166.4738195, "chk": "ok", "code_len": 3119}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8504, "tout": 1976, "ts": 1791529195.221171, "chk": "ok", "code_len": 2503}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10199, "tout": 1430, "ts": 1791529224.593699, "chk": null, "code_len": 2503}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 6176, "started": 1791529124.9616532}
{"ep": "h1-00508", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.3859, "speedup": 2.3859, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 355.4, "calls": 2, "tokens_in": 8238, "tokens_out": 8498, "ctx_chars": 0, "t_end": 1791529320.5097518, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.3859, "lo95": 2.3835, "mean": 2.5245, "ev_only": 2.3783, "ref_ms": 3.73769, "cand_ms": 1.56656, "n_trials": 191, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 117.06, "compile_s": 18.87, "r_error": "", "src_len": 5697, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2325, "tout": 5513, "ts": 1791529012.9514804, "chk": "ok", "code_len": 5697}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5913, "tout": 2985, "ts": 1791529066.301563, "chk": null, "code_len": 5697}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2325, "started": 1791528965.065543}
{"ep": "h1-00553", "task": "L1_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "runtime_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 131.3, "calls": 1, "tokens_in": 2478, "tokens_out": 429, "ctx_chars": 2425, "t_end": 1791529328.5212872, "error": "CompilationError: at 8:8:\ndef gelu_kernel(x_ptr, out_ptr, n, BLOCK: tl.constexpr):\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    m", "f_status": "runtime_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": null, "r_wall_s": 126.45, "compile_s": 2.18, "r_error": "CompilationError: at 8:8:\ndef gelu_kernel(x_ptr, out_ptr, n, BLOCK: tl.constexpr):\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    m", "src_len": 769, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2478, "tout": 429, "ts": 1791529201.937126, "chk": null, "code_len": 769}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2478, "started": 1791529197.2388089}
{"ep": "h1-00541", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0413, "speedup": 1.0413, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 173.6, "calls": 2, "tokens_in": 12110, "tokens_out": 2019, "ctx_chars": 8989, "t_end": 1791529331.114848, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0413, "lo95": 1.0409, "mean": 1.0417, "ev_only": 1.0412, "ref_ms": 30.54377, "cand_ms": 29.33221, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 137.74, "compile_s": 3.29, "r_error": "", "src_len": 919, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5552, "tout": 1485, "ts": 1791529172.1332703, "chk": "ok", "code_len": 919}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6558, "tout": 534, "ts": 1791529192.827352, "chk": null, "code_len": 919}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5552, "started": 1791529157.515306}
{"ep": "h1-00557", "task": "L1_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8824, "speedup": 1.8824, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 133.1, "calls": 1, "tokens_in": 6947, "tokens_out": 1615, "ctx_chars": 10864, "t_end": 1791529341.3691316, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.8824, "lo95": 1.8809, "mean": 1.8787, "ev_only": 1.8877, "ref_ms": 3.74166, "cand_ms": 1.98766, "n_trials": 214, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 118.12, "compile_s": 2.14, "r_error": "", "src_len": 3336, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6947, "tout": 1615, "ts": 1791529222.327447, "chk": null, "code_len": 3336}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6947, "started": 1791529208.2990367}
{"ep": "h1-00562", "task": "L2_070", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0123, "speedup": 1.0123, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 118.5, "calls": 1, "tokens_in": 5600, "tokens_out": 464, "ctx_chars": 9220, "t_end": 1791529341.852198, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0123, "lo95": 1.0107, "mean": 1.0419, "ev_only": 1.0147, "ref_ms": 8.14199, "cand_ms": 8.04315, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 113.64, "compile_s": 2.05, "r_error": "", "src_len": 876, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5600, "tout": 464, "ts": 1791529228.1132095, "chk": null, "code_len": 876}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5600, "started": 1791529223.356017}
{"ep": "h1-00485", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.062, "speedup": 1.062, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 481.9, "calls": 2, "tokens_in": 17070, "tokens_out": 13930, "ctx_chars": 6513, "t_end": 1791529344.5785012, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.062, "lo95": 1.0538, "mean": 0.9973, "ev_only": 1.0627, "ref_ms": 20.17848, "cand_ms": 19.00034, "n_trials": 66, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1932, "r_wall_s": 138.25, "compile_s": 1.99, "r_error": "", "src_len": 8442, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6296, "tout": 9798, "ts": 1791528944.6702852, "chk": "ok", "code_len": 8442}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10774, "tout": 4132, "ts": 1791529206.3034158, "chk": null, "code_len": 8442}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6296, "started": 1791528862.6654289}
{"ep": "h1-00567", "task": "L3_048", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 99.5, "calls": 1, "tokens_in": 2835, "tokens_out": 5071, "ctx_chars": 0, "t_end": 1791529346.7780757, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.9992, "r_wall_s": 42.58, "compile_s": 2.75, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 3119, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2835, "tout": 5071, "ts": 1791529303.8951128, "chk": null, "code_len": 3119}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2835, "started": 1791529247.2763617}
{"ep": "h1-00515", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.9714, "speedup": 2.9714, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 352.1, "calls": 2, "tokens_in": 7860, "tokens_out": 8277, "ctx_chars": 0, "t_end": 1791529348.9830077, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.9714, "lo95": 2.9383, "mean": 2.9238, "ev_only": 2.9752, "ref_ms": 3.71328, "cand_ms": 1.24968, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5247, "r_wall_s": 120.98, "compile_s": 2.06, "r_error": "", "src_len": 3684, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 6415, "ts": 1791529055.3646538, "chk": "ok", "code_len": 3684}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5167, "tout": 1862, "ts": 1791529227.742678, "chk": null, "code_len": 3684}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791528996.8706076}
{"ep": "h1-00494", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6788, "speedup": 1.6788, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 465.6, "calls": 2, "tokens_in": 14139, "tokens_out": 12002, "ctx_chars": 6513, "t_end": 1791529357.254142, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.6788, "lo95": 1.6177, "mean": 1.4723, "ev_only": 1.6657, "ref_ms": 6.43684, "cand_ms": 3.83414, "n_trials": 205, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.326, "r_wall_s": 116.91, "compile_s": 48.52, "r_error": "", "src_len": 7591, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 8458, "ts": 1791528965.7972865, "chk": "ok", "code_len": 7591}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9056, "tout": 3544, "ts": 1791529240.2371469, "chk": null, "code_len": 7591}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791528891.678569}
{"ep": "h1-00531", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2704, "speedup": 1.2704, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 271.9, "calls": 2, "tokens_in": 13181, "tokens_out": 2295, "ctx_chars": 9835, "t_end": 1791529357.8636842, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2704, "lo95": 1.2683, "mean": 1.2705, "ev_only": 1.2715, "ref_ms": 17.54874, "cand_ms": 13.81326, "n_trials": 78, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0624, "r_wall_s": 165.87, "compile_s": 3.26, "r_error": "", "src_len": 1795, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5910, "tout": 1249, "ts": 1791529096.7396777, "chk": "ok", "code_len": 1795}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7271, "tout": 1046, "ts": 1791529191.580456, "chk": null, "code_len": 1795}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5910, "started": 1791529085.9775386}
{"ep": "h1-00575", "task": "L2_098", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 71.9, "calls": 1, "tokens_in": 1737, "tokens_out": 1280, "ctx_chars": 0, "t_end": 1791529361.9100142, "error": "RuntimeError: Error building extension 'fuse_pgsm': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_pgsm -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 58.79, "compile_s": 58.78, "r_error": "RuntimeError: Error building extension 'fuse_pgsm': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_pgsm -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "src_len": 2466, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1737, "tout": 1280, "ts": 1791529303.0992055, "chk": null, "code_len": 2466}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1737, "started": 1791529290.0212908}
{"ep": "h1-00568", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9184, "speedup": 0.9184, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.0, "calls": 2, "tokens_in": 5221, "tokens_out": 4421, "ctx_chars": 0, "t_end": 1791529363.609404, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9184, "lo95": 0.917, "mean": 0.914, "ev_only": 0.9177, "ref_ms": 2.88496, "cand_ms": 3.14117, "n_trials": 195, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 56.48, "compile_s": 3.05, "r_error": "", "src_len": 2549, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 2875, "ts": 1791529272.6719086, "chk": "ok", "code_len": 2549}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3632, "tout": 1546, "ts": 1791529306.99496, "chk": null, "code_len": 2549}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791529247.6036263}
{"ep": "h1-00566", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5834, "speedup": 1.5834, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 123.3, "calls": 2, "tokens_in": 16993, "tokens_out": 5817, "ctx_chars": 11886, "t_end": 1791529365.660532, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5834, "lo95": 1.5725, "mean": 1.583, "ev_only": 1.5917, "ref_ms": 4.79915, "cand_ms": 3.03094, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2618, "r_wall_s": 45.52, "compile_s": 2.62, "r_error": "", "src_len": 4044, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7269, "tout": 3772, "ts": 1791529274.1974816, "chk": "ok", "code_len": 4106}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9724, "tout": 2045, "ts": 1791529320.0100973, "chk": null, "code_len": 4044}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7269, "started": 1791529242.3206158}
{"ep": "h1-00546", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.7124, "speedup": 1.7124, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 195.9, "calls": 3, "tokens_in": 9870, "tokens_out": 6942, "ctx_chars": 0, "t_end": 1791529367.2485864, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.7124, "lo95": 1.7094, "mean": 1.7254, "ev_only": 1.7078, "ref_ms": 8.03307, "cand_ms": 4.69102, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 72.77, "compile_s": 2.42, "r_error": "", "src_len": 2101, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 3850, "ts": 1791529207.6213093, "chk": "incorrect", "code_len": 2262}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3429, "tout": 1881, "ts": 1791529267.8935795, "chk": "ok", "code_len": 2101}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4876, "tout": 1211, "ts": 1791529294.2930112, "chk": null, "code_len": 2101}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1565, "started": 1791529171.3657265}
{"ep": "h1-00559", "task": "L2_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6822, "speedup": 1.6822, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 154.0, "calls": 3, "tokens_in": 28820, "tokens_out": 5989, "ctx_chars": 10613, "t_end": 1791529371.4955447, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.6822, "lo95": 1.6759, "mean": 1.7011, "ev_only": 1.6804, "ref_ms": 36.46001, "cand_ms": 21.67427, "n_trials": 43, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0639, "r_wall_s": 88.79, "compile_s": 1.91, "r_error": "", "src_len": 2969, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6520, "tout": 4492, "ts": 1791529258.830549, "chk": "ok", "code_len": 2969}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11124, "tout": 28, "ts": 1791529270.3841767, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11176, "tout": 1469, "ts": 1791529282.656547, "chk": null, "code_len": 2969}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6520, "started": 1791529217.523011}
{"ep": "h1-00459", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.0336, "speedup": 6.0336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 593.7, "calls": 3, "tokens_in": 32594, "tokens_out": 17802, "ctx_chars": 11175, "t_end": 1791529373.8489692, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 6.0336, "lo95": 6.0259, "mean": 6.1285, "ev_only": 6.1442, "ref_ms": 4.36955, "cand_ms": 0.7242, "n_trials": 202, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 187.59, "compile_s": 2.52, "r_error": "", "src_len": 7063, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 10860, "ts": 1791528878.8541074, "chk": "no_custom_kernel", "code_len": 7086}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11018, "tout": 3616, "ts": 1791528962.545389, "chk": "ok", "code_len": 7063}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14509, "tout": 3326, "ts": 1791529186.0617163, "chk": null, "code_len": 7063}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 7067, "started": 1791528780.107115}
{"ep": "h1-00552", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2694, "speedup": 1.2694, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 185.6, "calls": 2, "tokens_in": 5267, "tokens_out": 4465, "ctx_chars": 0, "t_end": 1791529374.642512, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2694, "lo95": 1.2654, "mean": 1.284, "ev_only": 1.273, "ref_ms": 17.60833, "cand_ms": 13.87108, "n_trials": 84, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0712, "r_wall_s": 75.05, "compile_s": 17.18, "r_error": "", "src_len": 3020, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1693, "tout": 2768, "ts": 1791529213.6805816, "chk": "ok", "code_len": 3020}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3574, "tout": 1697, "ts": 1791529298.8775575, "chk": null, "code_len": 3020}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1693, "started": 1791529189.0205522}
{"ep": "h1-00513", "task": "L1_080", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.1046, "speedup": 0.1046, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 399.8, "calls": 4, "tokens_in": 22373, "tokens_out": 6070, "ctx_chars": 0, "t_end": 1791529382.7030814, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.1046, "lo95": 0.0937, "mean": 0.098, "ev_only": 0.1046, "ref_ms": 20.15385, "cand_ms": 192.60336, "n_trials": 10, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.2172, "r_wall_s": 95.54, "compile_s": 13.95, "r_error": "", "src_len": 3861, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2006, "tout": 2162, "ts": 1791529002.913517, "chk": "compile_error", "code_len": 4096}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1832, "ts": 1791529065.4226599, "chk": "ok", "code_len": 3861}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7343, "tout": 255, "ts": 1791529270.7156875, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7622, "tout": 1821, "ts": 1791529285.85224, "chk": null, "code_len": 3861}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 2006, "started": 1791528982.9089065}
{"ep": "h1-00475", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.003, "speedup": 1.003, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 539.8, "calls": 4, "tokens_in": 27383, "tokens_out": 14038, "ctx_chars": 0, "t_end": 1791529382.991653, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.003, "lo95": 1.0025, "mean": 1.0174, "ev_only": 1.0039, "ref_ms": 23.34553, "cand_ms": 23.27525, "n_trials": 60, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0179, "r_wall_s": 42.94, "compile_s": 3.3, "r_error": "", "src_len": 4652, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2736, "tout": 5025, "ts": 1791528887.391537, "chk": "incorrect", "code_len": 4483}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5507, "tout": 3004, "ts": 1791528926.8181107, "chk": "incorrect", "code_len": 4484}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8170, "tout": 3563, "ts": 1791529217.281529, "chk": "ok", "code_len": 4652}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10970, "tout": 2446, "ts": 1791529339.998421, "chk": null, "code_len": 4652}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2736, "started": 1791528843.1958582}
{"ep": "h1-00516", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6098, "speedup": 0.6098, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 392.9, "calls": 2, "tokens_in": 7589, "tokens_out": 10213, "ctx_chars": 0, "t_end": 1791529395.787077, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6098, "lo95": 0.6059, "mean": 0.6139, "ev_only": 0.6091, "ref_ms": 3.29785, "cand_ms": 5.4077, "n_trials": 151, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 112.18, "compile_s": 15.67, "r_error": "", "src_len": 5840, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2031, "tout": 7353, "ts": 1791529066.2332044, "chk": "ok", "code_len": 5840}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5558, "tout": 2860, "ts": 1791529282.774876, "chk": null, "code_len": 5840}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2031, "started": 1791529002.8568153}
{"ep": "h1-00492", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 20.8628, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 522.5, "calls": 3, "tokens_in": 30135, "tokens_out": 11872, "ctx_chars": 11393, "t_end": 1791529410.3065996, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 20.8628, "lo95": 20.8347, "mean": 20.7459, "ev_only": 20.8656, "ref_ms": 25.02403, "cand_ms": 1.19946, "n_trials": 55, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 137.84, "compile_s": 15.98, "r_error": "", "src_len": 5538, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6822, "tout": 6283, "ts": 1791528944.197546, "chk": "no_custom_kernel", "code_len": 5560}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10222, "tout": 2886, "ts": 1791529066.6243143, "chk": "ok", "code_len": 5538}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13091, "tout": 2703, "ts": 1791529272.2570846, "chk": null, "code_len": 5538}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6822, "started": 1791528887.7842445}
{"ep": "h1-00501", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 7.5898, "speedup": 7.5898, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 492.7, "calls": 4, "tokens_in": 34293, "tokens_out": 27660, "ctx_chars": 0, "t_end": 1791529410.7168775, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 7.5898, "lo95": 7.5841, "mean": 7.7829, "ev_only": 7.5817, "ref_ms": 15.88341, "cand_ms": 2.09274, "n_trials": 89, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9827, "r_wall_s": 122.64, "compile_s": 13.53, "r_error": "", "src_len": 7230, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2837, "tout": 8896, "ts": 1791529018.926982, "chk": "incorrect", "code_len": 7242}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6861, "tout": 4808, "ts": 1791529082.3638709, "chk": "incorrect", "code_len": 7012}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 10422, "tout": 10517, "ts": 1791529238.0210168, "chk": "ok", "code_len": 7230}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14173, "tout": 3439, "ts": 1791529286.8382192, "chk": null, "code_len": 7230}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2837, "started": 1791528938.3734314}
{"ep": "h1-00555", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9167, "speedup": 1.9167, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.3, "calls": 2, "tokens_in": 14569, "tokens_out": 3931, "ctx_chars": 10743, "t_end": 1791529417.1456587, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.9167, "lo95": 1.9154, "mean": 1.9281, "ev_only": 1.915, "ref_ms": 19.52371, "cand_ms": 10.18636, "n_trials": 69, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1783, "r_wall_s": 51.97, "compile_s": 2.17, "r_error": "", "src_len": 2277, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6466, "tout": 2808, "ts": 1791529229.7512994, "chk": "ok", "code_len": 2277}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8103, "tout": 1123, "ts": 1791529364.772004, "chk": null, "code_len": 2277}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6466, "started": 1791529203.8264678}
{"ep": "h1-00538", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.467, "speedup": 0.467, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 293.5, "calls": 2, "tokens_in": 7206, "tokens_out": 9872, "ctx_chars": 0, "t_end": 1791529428.3985019, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.467, "lo95": 0.4664, "mean": 0.468, "ev_only": 0.4667, "ref_ms": 10.03544, "cand_ms": 21.49134, "n_trials": 55, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 151.0, "compile_s": 12.72, "r_error": "", "src_len": 5488, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 7175, "ts": 1791529198.4733012, "chk": "ok", "code_len": 5539}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5203, "tout": 2697, "ts": 1791529276.4796362, "chk": null, "code_len": 5488}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791529134.9374335}
{"ep": "h1-00554", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1912, "speedup": 1.1912, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 226.5, "calls": 2, "tokens_in": 4826, "tokens_out": 4268, "ctx_chars": 0, "t_end": 1791529428.8146331, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1912, "lo95": 1.1904, "mean": 1.1915, "ev_only": 1.1903, "ref_ms": 16.10762, "cand_ms": 13.52238, "n_trials": 100, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 120.98, "compile_s": 2.79, "r_error": "", "src_len": 2113, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1550, "tout": 3062, "ts": 1791529229.5897102, "chk": "ok", "code_len": 2113}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3276, "tout": 1206, "ts": 1791529307.786541, "chk": null, "code_len": 2113}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1550, "started": 1791529202.3075588}
{"ep": "h1-00590", "task": "L3_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 82.7, "calls": 1, "tokens_in": 1972, "tokens_out": 1593, "ctx_chars": 0, "t_end": 1791529429.5197906, "error": "RuntimeError: Error building extension 'arblk': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=arblk -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -is", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 67.25, "compile_s": 67.25, "r_error": "RuntimeError: Error building extension 'arblk': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=arblk -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -is", "src_len": 2912, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1972, "tout": 1593, "ts": 1791529362.2238653, "chk": null, "code_len": 2912}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1972, "started": 1791529346.7783146}
{"ep": "h1-00571", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0673, "speedup": 1.0673, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 173.0, "calls": 2, "tokens_in": 12091, "tokens_out": 2029, "ctx_chars": 8462, "t_end": 1791529432.3483562, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0673, "lo95": 1.0664, "mean": 1.0686, "ev_only": 1.068, "ref_ms": 8.4787, "cand_ms": 7.94399, "n_trials": 94, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 146.08, "compile_s": 2.21, "r_error": "", "src_len": 1493, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1175, "ts": 1791529269.7588375, "chk": "ok", "code_len": 1493}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6689, "tout": 854, "ts": 1791529286.1895294, "chk": null, "code_len": 1493}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791529259.3890543}
{"ep": "h1-00545", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0885, "speedup": 1.0885, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 298.8, "calls": 2, "tokens_in": 14519, "tokens_out": 8166, "ctx_chars": 9898, "t_end": 1791529468.6933165, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0885, "lo95": 1.0855, "mean": 1.0824, "ev_only": 1.0885, "ref_ms": 16.23291, "cand_ms": 14.91373, "n_trials": 91, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2781, "r_wall_s": 118.12, "compile_s": 2.19, "r_error": "", "src_len": 3616, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6027, "tout": 5948, "ts": 1791529224.0685399, "chk": "ok", "code_len": 3616}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8492, "tout": 2218, "ts": 1791529350.5285108, "chk": null, "code_len": 3616}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6027, "started": 1791529169.9224472}
{"ep": "h1-00580", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2061, "speedup": 1.2061, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.0, "calls": 2, "tokens_in": 9809, "tokens_out": 9689, "ctx_chars": 0, "t_end": 1791529469.3739378, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2061, "lo95": 1.2058, "mean": 1.2059, "ev_only": 1.2058, "ref_ms": 75.32842, "cand_ms": 62.45637, "n_trials": 22, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2054, "r_wall_s": 63.77, "compile_s": 3.68, "r_error": "", "src_len": 5779, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 6482, "ts": 1791529363.1194484, "chk": "ok", "code_len": 5779}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6788, "tout": 3207, "ts": 1791529405.2224162, "chk": null, "code_len": 5779}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791529308.360564}
{"ep": "h1-00423", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1856, "speedup": 1.1856, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 851.0, "calls": 5, "tokens_in": 38890, "tokens_out": 18739, "ctx_chars": 2425, "t_end": 1791529471.591819, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1856, "lo95": 1.1847, "mean": 1.1843, "ev_only": 1.1844, "ref_ms": 15.88424, "cand_ms": 13.39734, "n_trials": 87, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0271, "r_wall_s": 198.22, "compile_s": 2.63, "r_error": "", "src_len": 2974, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3753, "tout": 4416, "ts": 1791528660.048722, "chk": "incorrect", "code_len": 2959}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5803, "tout": 3107, "ts": 1791528748.6740437, "chk": "incorrect", "code_len": 3088}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7748, "tout": 4867, "ts": 1791528856.8818457, "chk": "incorrect", "code_len": 3138}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9795, "tout": 4609, "ts": 1791528934.2466655, "chk": "ok", "code_len": 2974}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11791, "tout": 1740, "ts": 1791529272.5263562, "chk": null, "code_len": 2974}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 3753, "started": 1791528620.573365}
{"ep": "h1-00594", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0313, "speedup": 1.0313, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 118.2, "calls": 2, "tokens_in": 12653, "tokens_out": 4346, "ctx_chars": 8449, "t_end": 1791529480.1005213, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0313, "lo95": 1.0295, "mean": 1.0291, "ev_only": 1.0328, "ref_ms": 8.29604, "cand_ms": 8.04461, "n_trials": 150, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 47.22, "compile_s": 1.94, "r_error": "", "src_len": 3027, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5359, "tout": 2800, "ts": 1791529385.319361, "chk": "ok", "code_len": 3027}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7294, "tout": 1546, "ts": 1791529432.7712152, "chk": null, "code_len": 3027}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5359, "started": 1791529361.9102588}
{"ep": "h1-00558", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9996, "speedup": 0.9996, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 266.1, "calls": 2, "tokens_in": 18514, "tokens_out": 25121, "ctx_chars": 6513, "t_end": 1791529480.6689522, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9996, "lo95": 0.827, "mean": 0.8945, "ev_only": 1.002, "ref_ms": 22.62431, "cand_ms": 22.63388, "n_trials": 87, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0898, "r_wall_s": 40.83, "compile_s": 2.46, "r_error": "", "src_len": 12848, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 18676, "ts": 1791529376.5506322, "chk": "ok", "code_len": 12848}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12787, "tout": 6445, "ts": 1791529439.7355623, "chk": null, "code_len": 12848}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791529214.5590546}
{"ep": "h1-00564", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5598, "speedup": 0.5598, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.2, "calls": 2, "tokens_in": 16280, "tokens_out": 3983, "ctx_chars": 12471, "t_end": 1791529491.842499, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.5598, "lo95": 0.5596, "mean": 0.5349, "ev_only": 0.5584, "ref_ms": 3.63578, "cand_ms": 6.49426, "n_trials": 160, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9995, "r_wall_s": 155.94, "compile_s": 3.04, "r_error": "", "src_len": 2454, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7230, "tout": 2648, "ts": 1791529277.2656403, "chk": "ok", "code_len": 2454}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9050, "tout": 1335, "ts": 1791529334.5744464, "chk": null, "code_len": 2454}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7230, "started": 1791529254.006082}
{"ep": "h1-00587", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2838, "speedup": 1.2838, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.3, "calls": 2, "tokens_in": 13492, "tokens_out": 3101, "ctx_chars": 9893, "t_end": 1791529503.7073312, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2838, "lo95": 1.2832, "mean": 1.2848, "ev_only": 1.2825, "ref_ms": 19.77377, "cand_ms": 15.40201, "n_trials": 78, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0409, "r_wall_s": 118.23, "compile_s": 2.97, "r_error": "", "src_len": 2140, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5991, "tout": 2006, "ts": 1791529359.1824734, "chk": "ok", "code_len": 2140}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7501, "tout": 1095, "ts": 1791529384.6040049, "chk": null, "code_len": 2140}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5991, "started": 1791529341.3693755}
{"ep": "h1-00563", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1631, "speedup": 2.1631, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 286.5, "calls": 2, "tokens_in": 12515, "tokens_out": 1223, "ctx_chars": 9855, "t_end": 1791529510.4005492, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.1631, "lo95": 2.161, "mean": 2.1579, "ev_only": 2.1724, "ref_ms": 6.29974, "cand_ms": 2.91239, "n_trials": 206, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2733, "r_wall_s": 170.52, "compile_s": 2.97, "r_error": "", "src_len": 896, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 714, "ts": 1791529230.8525288, "chk": "ok", "code_len": 896}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6669, "tout": 509, "ts": 1791529338.9570694, "chk": null, "code_len": 896}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791529223.9252462}
{"ep": "h1-00602", "task": "L2_020", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4473, "speedup": 1.4473, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 129.0, "calls": 2, "tokens_in": 13855, "tokens_out": 1478, "ctx_chars": 10756, "t_end": 1791529511.9765787, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4473, "lo95": 1.4468, "mean": 1.4466, "ev_only": 1.4488, "ref_ms": 13.98724, "cand_ms": 9.66434, "n_trials": 90, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0685, "r_wall_s": 76.35, "compile_s": 1.97, "r_error": "", "src_len": 1329, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6461, "tout": 821, "ts": 1791529390.7467544, "chk": "ok", "code_len": 1329}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7394, "tout": 657, "ts": 1791529434.8179274, "chk": null, "code_len": 1329}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6461, "started": 1791529382.9919264}
{"ep": "h1-00595", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7406, "speedup": 0.7406, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.2, "calls": 2, "tokens_in": 5016, "tokens_out": 4727, "ctx_chars": 0, "t_end": 1791529518.7975268, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7406, "lo95": 0.7398, "mean": 0.743, "ev_only": 0.7407, "ref_ms": 7.71956, "cand_ms": 10.42358, "n_trials": 142, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 21.89, "compile_s": 1.9, "r_error": "", "src_len": 2553, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 3132, "ts": 1791529391.5731468, "chk": "ok", "code_len": 2553}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3451, "tout": 1595, "ts": 1791529496.775515, "chk": null, "code_len": 2553}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791529363.6096308}
{"ep": "h1-00527", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.55, "speedup": 0.55, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 457.0, "calls": 3, "tokens_in": 27509, "tokens_out": 26464, "ctx_chars": 0, "t_end": 1791529526.6124961, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.55, "lo95": 0.5469, "mean": 0.549, "ev_only": 0.5495, "ref_ms": 5.96325, "cand_ms": 10.84272, "n_trials": 128, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4054, "r_wall_s": 141.91, "compile_s": 3.3, "r_error": "", "src_len": 10811, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3365, "tout": 15479, "ts": 1791529206.4105752, "chk": "runtime_error", "code_len": 10795}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9297, "tout": 5634, "ts": 1791529287.7876403, "chk": "ok", "code_len": 10811}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14847, "tout": 5351, "ts": 1791529384.657139, "chk": null, "code_len": 10811}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 3365, "started": 1791529069.6551547}
{"ep": "h1-00482", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.7541, "speedup": 3.7541, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 672.5, "calls": 5, "tokens_in": 36376, "tokens_out": 14978, "ctx_chars": 2425, "t_end": 1791529526.9109619, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.7541, "lo95": 3.7434, "mean": 3.1747, "ev_only": 3.776, "ref_ms": 12.03456, "cand_ms": 3.20571, "n_trials": 126, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0428, "r_wall_s": 33.77, "compile_s": 1.83, "r_error": "", "src_len": 3135, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 3447, "ts": 1791528916.2257013, "chk": "incorrect", "code_len": 2790}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5461, "tout": 2911, "ts": 1791528955.67431, "chk": "incorrect", "code_len": 2703}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7216, "tout": 3995, "ts": 1791529300.1007748, "chk": "incorrect", "code_len": 2959}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9071, "tout": 2989, "ts": 1791529383.8807092, "chk": "ok", "code_len": 3135}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11035, "tout": 1636, "ts": 1791529492.9344428, "chk": null, "code_len": 3135}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 3593, "started": 1791528874.801488}
{"ep": "h1-00582", "task": "L1_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7084, "speedup": 0.7084, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 214.4, "calls": 1, "tokens_in": 6878, "tokens_out": 996, "ctx_chars": 11175, "t_end": 1791529528.9344602, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7084, "lo95": 0.7058, "mean": 0.7173, "ev_only": 0.7135, "ref_ms": 3.33041, "cand_ms": 4.70134, "n_trials": 206, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0006, "r_wall_s": 204.52, "compile_s": 3.81, "r_error": "", "src_len": 2043, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6878, "tout": 996, "ts": 1791529323.6020768, "chk": null, "code_len": 2043}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6878, "started": 1791529314.5374875}
{"ep": "h1-00549", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0016, "speedup": 1.0016, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 355.7, "calls": 2, "tokens_in": 5330, "tokens_out": 4547, "ctx_chars": 0, "t_end": 1791529533.0709095, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0016, "lo95": 1.0013, "mean": 1.024, "ev_only": 1.0014, "ref_ms": 33.57802, "cand_ms": 33.52297, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 241.2, "compile_s": 1.95, "r_error": "", "src_len": 2741, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 3119, "ts": 1791529204.8952038, "chk": "ok", "code_len": 2741}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3615, "tout": 1428, "ts": 1791529291.7574983, "chk": null, "code_len": 2741}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791529177.363172}
{"ep": "h1-00476", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.5145, "speedup": 7.5145, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 694.8, "calls": 3, "tokens_in": 28660, "tokens_out": 21004, "ctx_chars": 8224, "t_end": 1791529539.8014352, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.5145, "lo95": 7.4781, "mean": 7.6222, "ev_only": 7.5025, "ref_ms": 31.71149, "cand_ms": 4.22003, "n_trials": 47, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9939, "r_wall_s": 268.36, "compile_s": 15.83, "r_error": "", "src_len": 7597, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 13361, "ts": 1791528965.2224395, "chk": "no_custom_kernel", "code_len": 7649}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9664, "tout": 4158, "ts": 1791529204.9478357, "chk": "ok", "code_len": 7597}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13506, "tout": 3485, "ts": 1791529271.3163009, "chk": null, "code_len": 7597}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791528844.9804995}
{"ep": "h1-00614", "task": "L2_070", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 60.5, "calls": 1, "tokens_in": 1668, "tokens_out": 828, "ctx_chars": 0, "t_end": 1791529540.6148255, "error": "RuntimeError: Error building extension 'fused_sig': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_sig -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 52.3, "compile_s": 52.29, "r_error": "RuntimeError: Error building extension 'fused_sig': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_sig -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "src_len": 1716, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1668, "tout": 828, "ts": 1791529488.2839835, "chk": null, "code_len": 1716}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1668, "started": 1791529480.1007931}
{"ep": "h1-00577", "task": "L2_081", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0383, "speedup": 1.0383, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 244.7, "calls": 1, "tokens_in": 1704, "tokens_out": 530, "ctx_chars": 0, "t_end": 1791529540.972354, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0383, "lo95": 1.0368, "mean": 1.0376, "ev_only": 1.0371, "ref_ms": 8.23408, "cand_ms": 7.93072, "n_trials": 134, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 218.51, "compile_s": 2.97, "r_error": "", "src_len": 907, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1704, "tout": 530, "ts": 1791529322.350586, "chk": null, "code_len": 907}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1704, "started": 1791529316.61967}
{"ep": "h1-00500", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5343, "speedup": 1.5343, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 638.7, "calls": 2, "tokens_in": 15154, "tokens_out": 5213, "ctx_chars": 10850, "t_end": 1791529541.6651855, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.5343, "lo95": 1.534, "mean": 1.5353, "ev_only": 1.5352, "ref_ms": 7.28449, "cand_ms": 4.74771, "n_trials": 225, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 258.73, "compile_s": 2.96, "r_error": "", "src_len": 2454, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6676, "tout": 3565, "ts": 1791528935.5690327, "chk": "ok", "code_len": 2454}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8478, "tout": 1648, "ts": 1791529282.7244828, "chk": null, "code_len": 2454}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6676, "started": 1791528902.978525}
{"ep": "h1-00593", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1616, "speedup": 1.1616, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.0, "calls": 2, "tokens_in": 5510, "tokens_out": 5131, "ctx_chars": 0, "t_end": 1791529545.8987522, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1616, "lo95": 1.1612, "mean": 1.161, "ev_only": 1.1621, "ref_ms": 33.80056, "cand_ms": 29.09838, "n_trials": 45, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 83.99, "compile_s": 1.88, "r_error": "", "src_len": 2879, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 3605, "ts": 1791529389.5620728, "chk": "ok", "code_len": 2879}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3795, "tout": 1526, "ts": 1791529461.8688552, "chk": null, "code_len": 2879}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791529357.8639512}
{"ep": "h1-00597", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4065, "speedup": 1.4065, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 181.3, "calls": 2, "tokens_in": 13743, "tokens_out": 2343, "ctx_chars": 10210, "t_end": 1791529548.5649536, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4065, "lo95": 1.4028, "mean": 1.4062, "ev_only": 1.406, "ref_ms": 19.20978, "cand_ms": 13.65811, "n_trials": 49, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0337, "r_wall_s": 142.36, "compile_s": 3.52, "r_error": "", "src_len": 1878, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 1364, "ts": 1791529379.7170887, "chk": "ok", "code_len": 1878}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7608, "tout": 979, "ts": 1791529405.6888611, "chk": null, "code_len": 1878}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791529367.2489839}
{"ep": "h1-00435", "task": "L2_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.6028, "speedup": 1.6028, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 878.4, "calls": 5, "tokens_in": 35582, "tokens_out": 10356, "ctx_chars": 0, "t_end": 1791529568.4039342, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.6028, "lo95": 1.6023, "mean": 1.6041, "ev_only": 1.6017, "ref_ms": 36.40298, "cand_ms": 22.71204, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0252, "r_wall_s": 199.48, "compile_s": 16.56, "r_error": "", "src_len": 4039, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1763, "tout": 2134, "ts": 1791528709.2878702, "chk": "compile_error", "code_len": 4245}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5189, "tout": 1893, "ts": 1791528778.9194095, "chk": "no_custom_kernel", "code_len": 3946}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7211, "tout": 2188, "ts": 1791528934.14767, "chk": "no_custom_kernel", "code_len": 4377}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9528, "tout": 2228, "ts": 1791529172.0022814, "chk": "ok", "code_len": 4039}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11891, "tout": 1913, "ts": 1791529368.8488061, "chk": null, "code_len": 4039}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "no_custom_kernel", "no_custom_kernel", "ok", null], "first_tin": 1763, "started": 1791528690.038871}
{"ep": "h1-00576", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0979, "speedup": 1.0979, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 276.5, "calls": 2, "tokens_in": 10659, "tokens_out": 4860, "ctx_chars": 6513, "t_end": 1791529569.0022511, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0979, "lo95": 1.0974, "mean": 1.1175, "ev_only": 1.0968, "ref_ms": 10.67805, "cand_ms": 9.72584, "n_trials": 112, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 43.26, "compile_s": 3.51, "r_error": "", "src_len": 2764, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4389, "tout": 3408, "ts": 1791529322.409504, "chk": "ok", "code_len": 2764}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6270, "tout": 1452, "ts": 1791529525.7106223, "chk": null, "code_len": 2764}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4389, "started": 1791529292.4872086}
{"ep": "h1-00551", "task": "L2_073", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9848, "speedup": 0.9848, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 386.4, "calls": 2, "tokens_in": 4878, "tokens_out": 3008, "ctx_chars": 0, "t_end": 1791529571.7800252, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9848, "lo95": 0.984, "mean": 0.985, "ev_only": 0.9842, "ref_ms": 5.60615, "cand_ms": 5.69243, "n_trials": 209, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.6288, "r_wall_s": 130.9, "compile_s": 2.14, "r_error": "", "src_len": 3000, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1608, "tout": 1552, "ts": 1791529199.558386, "chk": "ok", "code_len": 3000}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3270, "tout": 1456, "ts": 1791529306.19857, "chk": null, "code_len": 3000}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1608, "started": 1791529185.342717}
{"ep": "h1-00605", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2689, "speedup": 1.2689, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.5, "calls": 2, "tokens_in": 13249, "tokens_out": 2226, "ctx_chars": 9835, "t_end": 1791529593.2271452, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2689, "lo95": 1.2666, "mean": 1.2693, "ev_only": 1.2689, "ref_ms": 17.51387, "cand_ms": 13.80235, "n_trials": 72, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0605, "r_wall_s": 79.69, "compile_s": 1.9, "r_error": "", "src_len": 1745, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5910, "tout": 1317, "ts": 1791529421.8401315, "chk": "ok", "code_len": 1745}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7339, "tout": 909, "ts": 1791529513.048443, "chk": null, "code_len": 1745}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5910, "started": 1791529410.717133}
{"ep": "h1-00529", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2147, "speedup": 0.2147, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 520.8, "calls": 2, "tokens_in": 10148, "tokens_out": 19432, "ctx_chars": 0, "t_end": 1791529593.3570995, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.2147, "lo95": 0.2137, "mean": 0.2153, "ev_only": 0.2136, "ref_ms": 5.28695, "cand_ms": 24.62972, "n_trials": 46, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.8053, "r_wall_s": 261.01, "compile_s": 3.24, "r_error": "", "src_len": 10719, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1974, "tout": 13887, "ts": 1791529191.6968203, "chk": "ok", "code_len": 10719}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8174, "tout": 5545, "ts": 1791529332.1145403, "chk": null, "code_len": 10719}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1974, "started": 1791529072.5722969}
{"ep": "h1-00509", "task": "L2_052", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3143, "speedup": 1.3143, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 628.8, "calls": 3, "tokens_in": 22975, "tokens_out": 3293, "ctx_chars": 11132, "t_end": 1791529594.698438, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3143, "lo95": 1.3126, "mean": 1.315, "ev_only": 1.3154, "ref_ms": 11.05406, "cand_ms": 8.4109, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1974, "r_wall_s": 319.56, "compile_s": 5.05, "r_error": "", "src_len": 3246, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6454, "tout": 1672, "ts": 1791528980.2276227, "chk": "ok", "code_len": 3246}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8236, "tout": 25, "ts": 1791529260.8037386, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8285, "tout": 1596, "ts": 1791529274.2980168, "chk": null, "code_len": 3246}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6454, "started": 1791528965.9126139}
{"ep": "h1-00619", "task": "L3_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "no_custom_kernel", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 89.4, "calls": 1, "tokens_in": 2190, "tokens_out": 2490, "ctx_chars": 0, "t_end": 1791529601.4150226, "error": "none of the candidate's kernels ['_gap_kernel', '_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "f_status": "no_custom_kernel", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.0, "r_wall_s": 67.21, "compile_s": 3.69, "r_error": "none of the candidate's kernels ['_gap_kernel', '_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "src_len": 3008, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2190, "tout": 2490, "ts": 1791529534.1727927, "chk": null, "code_len": 3008}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2190, "started": 1791529511.9768438}
{"ep": "h1-00611", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3925, "speedup": 1.3925, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 136.5, "calls": 2, "tokens_in": 13737, "tokens_out": 2938, "ctx_chars": 10210, "t_end": 1791529605.2305734, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3925, "lo95": 1.3887, "mean": 1.3924, "ev_only": 1.3948, "ref_ms": 19.44387, "cand_ms": 13.96359, "n_trials": 59, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0693, "r_wall_s": 87.59, "compile_s": 2.16, "r_error": "", "src_len": 1987, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 1932, "ts": 1791529485.9528558, "chk": "ok", "code_len": 1987}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7602, "tout": 1006, "ts": 1791529517.109731, "chk": null, "code_len": 1987}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791529468.6935928}
{"ep": "h1-00578", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0062, "speedup": 1.0062, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 307.1, "calls": 2, "tokens_in": 15474, "tokens_out": 4357, "ctx_chars": 11755, "t_end": 1791529605.3261569, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0062, "lo95": 1.0059, "mean": 1.0064, "ev_only": 1.0063, "ref_ms": 72.75054, "cand_ms": 72.30472, "n_trials": 18, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0083, "r_wall_s": 217.61, "compile_s": 2.25, "r_error": "", "src_len": 2036, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6940, "tout": 3212, "ts": 1791529328.0759099, "chk": "ok", "code_len": 2036}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8534, "tout": 1145, "ts": 1791529387.6678832, "chk": null, "code_len": 2036}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6940, "started": 1791529298.198087}
{"ep": "h1-00628", "task": "L2_067", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 67.0, "calls": 1, "tokens_in": 1655, "tokens_out": 1194, "ctx_chars": 0, "t_end": 1791529608.6745026, "error": "RuntimeError: Error building extension 'gelu_avgpool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_avgpool_mod -DTORCH_API_INCLUDE_EXTENSION_H -", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 55.3, "compile_s": 55.3, "r_error": "RuntimeError: Error building extension 'gelu_avgpool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_avgpool_mod -DTORCH_API_INCLUDE_EXTENSION_H -", "src_len": 2296, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1655, "tout": 1194, "ts": 1791529553.3494368, "chk": null, "code_len": 2296}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1655, "started": 1791529541.6654315}
{"ep": "h1-00572", "task": "L3_026", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4854, "speedup": 0.4854, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 348.1, "calls": 3, "tokens_in": 25587, "tokens_out": 6365, "ctx_chars": 6513, "t_end": 1791529608.706285, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.4854, "lo95": 0.4782, "mean": 0.5547, "ev_only": 0.4856, "ref_ms": 20.58161, "cand_ms": 42.4043, "n_trials": 47, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0857, "r_wall_s": 189.1, "compile_s": 3.13, "r_error": "", "src_len": 6584, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6294, "tout": 3200, "ts": 1791529286.4556012, "chk": "ok", "code_len": 6695}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9606, "tout": 57, "ts": 1791529395.1564033, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9687, "tout": 3108, "ts": 1791529419.5603278, "chk": null, "code_len": 6584}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6294, "started": 1791529260.6136491}
{"ep": "h1-00544", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.5667, "speedup": 0.5667, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 441.1, "calls": 2, "tokens_in": 8060, "tokens_out": 15601, "ctx_chars": 0, "t_end": 1791529609.480633, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.5667, "lo95": 0.5664, "mean": 0.5673, "ev_only": 0.5664, "ref_ms": 3.30667, "cand_ms": 5.83528, "n_trials": 215, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 270.32, "compile_s": 14.04, "r_error": "", "src_len": 6685, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2031, "tout": 12180, "ts": 1791529279.3239179, "chk": "ok", "code_len": 6685}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6029, "tout": 3421, "ts": 1791529338.2499273, "chk": null, "code_len": 6685}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2031, "started": 1791529168.3822434}
{"ep": "h1-00565", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0111, "speedup": 1.0111, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 374.2, "calls": 4, "tokens_in": 32404, "tokens_out": 7984, "ctx_chars": 9898, "t_end": 1791529610.7237282, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0111, "lo95": 1.01, "mean": 1.0122, "ev_only": 1.0102, "ref_ms": 8.12002, "cand_ms": 8.03055, "n_trials": 82, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0028, "r_wall_s": 227.23, "compile_s": 2.94, "r_error": "", "src_len": 907, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6120, "tout": 1648, "ts": 1791529251.608356, "chk": "incorrect", "code_len": 1087}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7219, "tout": 3484, "ts": 1791529292.6727173, "chk": "incorrect", "code_len": 2538}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9088, "tout": 2306, "ts": 1791529343.666698, "chk": "ok", "code_len": 907}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9977, "tout": 546, "ts": 1791529383.4517164, "chk": null, "code_len": 907}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6120, "started": 1791529236.5551713}
{"ep": "h1-00579", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4198, "speedup": 1.4198, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 337.2, "calls": 2, "tokens_in": 6698, "tokens_out": 7566, "ctx_chars": 0, "t_end": 1791529636.930272, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4198, "lo95": 1.4156, "mean": 1.4188, "ev_only": 1.4208, "ref_ms": 10.99351, "cand_ms": 7.74326, "n_trials": 130, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1584, "r_wall_s": 210.48, "compile_s": 16.37, "r_error": "", "src_len": 5929, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1619, "tout": 4676, "ts": 1791529336.4839349, "chk": "ok", "code_len": 5929}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5079, "tout": 2890, "ts": 1791529425.6424563, "chk": null, "code_len": 5929}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1619, "started": 1791529299.718469}
{"ep": "h1-00617", "task": "L1_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8534, "speedup": 0.8534, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 133.7, "calls": 1, "tokens_in": 6625, "tokens_out": 1081, "ctx_chars": 10864, "t_end": 1791529637.3909972, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8534, "lo95": 0.7793, "mean": 0.8358, "ev_only": 0.8511, "ref_ms": 10.05816, "cand_ms": 11.78572, "n_trials": 61, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0432, "r_wall_s": 121.7, "compile_s": 1.91, "r_error": "", "src_len": 1734, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6625, "tout": 1081, "ts": 1791529514.9076133, "chk": null, "code_len": 1734}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6625, "started": 1791529503.7076204}
{"ep": "h1-00633", "task": "L2_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 73.6, "calls": 1, "tokens_in": 1763, "tokens_out": 1931, "ctx_chars": 0, "t_end": 1791529645.4251575, "error": "RuntimeError: Error building extension 'bn_avgpool_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bn_avgpool_fused -DTORCH_API_INCLUDE_EXTENSION_H -", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 56.06, "compile_s": 56.03, "r_error": "RuntimeError: Error building extension 'bn_avgpool_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bn_avgpool_fused -DTORCH_API_INCLUDE_EXTENSION_H -", "src_len": 3679, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1763, "tout": 1931, "ts": 1791529589.3416536, "chk": null, "code_len": 3679}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1763, "started": 1791529571.7802866}
{"ep": "h1-00573", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5505, "speedup": 1.5505, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 383.5, "calls": 2, "tokens_in": 4819, "tokens_out": 4171, "ctx_chars": 0, "t_end": 1791529651.693307, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.5505, "lo95": 1.5493, "mean": 1.5783, "ev_only": 1.5489, "ref_ms": 16.18299, "cand_ms": 10.43732, "n_trials": 72, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 241.1, "compile_s": 3.57, "r_error": "", "src_len": 2209, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1550, "tout": 2983, "ts": 1791529294.261945, "chk": "ok", "code_len": 2209}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3269, "tout": 1188, "ts": 1791529410.523891, "chk": null, "code_len": 2209}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1550, "started": 1791529268.1450417}
{"ep": "h1-00550", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0051, "speedup": 1.0051, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 472.7, "calls": 2, "tokens_in": 17754, "tokens_out": 15313, "ctx_chars": 6513, "t_end": 1791529653.4625483, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0051, "lo95": 1.0003, "mean": 0.9867, "ev_only": 1.0044, "ref_ms": 20.41576, "cand_ms": 20.31296, "n_trials": 53, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2436, "r_wall_s": 227.62, "compile_s": 3.37, "r_error": "", "src_len": 9104, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6296, "tout": 10694, "ts": 1791529271.408008, "chk": "ok", "code_len": 9104}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11458, "tout": 4619, "ts": 1791529425.6530087, "chk": null, "code_len": 9104}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6296, "started": 1791529180.793711}
{"ep": "h1-00570", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3677, "speedup": 1.3677, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 404.5, "calls": 2, "tokens_in": 25579, "tokens_out": 13435, "ctx_chars": 6513, "t_end": 1791529661.0919502, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3677, "lo95": 1.3655, "mean": 1.3898, "ev_only": 1.3697, "ref_ms": 8.42818, "cand_ms": 6.16208, "n_trials": 149, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0495, "r_wall_s": 74.9, "compile_s": 3.5, "r_error": "", "src_len": 10063, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 10321, "tout": 9020, "ts": 1791529332.5543594, "chk": "ok", "code_len": 10063}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 15258, "tout": 4415, "ts": 1791529586.1673028, "chk": null, "code_len": 10063}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 10321, "started": 1791529256.5821624}
{"ep": "h1-00588", "task": "L2_056", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2153, "speedup": 0.2153, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 321.1, "calls": 3, "tokens_in": 13287, "tokens_out": 5484, "ctx_chars": 0, "t_end": 1791529662.9611316, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.2153, "lo95": 0.2152, "mean": 0.2154, "ev_only": 0.2154, "ref_ms": 16.12163, "cand_ms": 74.87876, "n_trials": 20, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 87.21, "compile_s": 1.94, "r_error": "", "src_len": 2474, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1572, "tout": 4133, "ts": 1791529377.0601475, "chk": "ok", "code_len": 2474}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5815, "tout": 61, "ts": 1791529565.3620462, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5900, "tout": 1290, "ts": 1791529575.723949, "chk": null, "code_len": 2474}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1572, "started": 1791529341.8524423}
{"ep": "h1-00603", "task": "L3_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9971, "speedup": 0.9971, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 276.4, "calls": 2, "tokens_in": 9592, "tokens_out": 1280, "ctx_chars": 6513, "t_end": 1791529672.1981306, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9971, "lo95": 0.9965, "mean": 0.9987, "ev_only": 0.9974, "ref_ms": 10.69755, "cand_ms": 10.72899, "n_trials": 116, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0017, "r_wall_s": 217.9, "compile_s": 2.57, "r_error": "", "src_len": 1190, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4387, "tout": 709, "ts": 1791529402.953121, "chk": "ok", "code_len": 1190}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5205, "tout": 571, "ts": 1791529454.268117, "chk": null, "code_len": 1190}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4387, "started": 1791529395.7873027}
{"ep": "h1-00542", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 8.0576, "speedup": 8.0576, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 527.5, "calls": 3, "tokens_in": 20345, "tokens_out": 27193, "ctx_chars": 0, "t_end": 1791529687.431951, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 8.0576, "lo95": 6.3154, "mean": 7.7831, "ev_only": 8.1228, "ref_ms": 43.46042, "cand_ms": 5.3937, "n_trials": 52, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9775, "r_wall_s": 41.18, "compile_s": 12.47, "r_error": "", "src_len": 8026, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1966, "tout": 18172, "ts": 1791529321.8443744, "chk": "no_custom_kernel", "code_len": 8049}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6902, "tout": 4693, "ts": 1791529402.0276837, "chk": "ok", "code_len": 8026}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11477, "tout": 4328, "ts": 1791529646.1271386, "chk": null, "code_len": 8026}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1966, "started": 1791529159.9079845}
{"ep": "h1-00596", "task": "L3_042", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5724, "speedup": 0.5724, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 326.2, "calls": 3, "tokens_in": 18410, "tokens_out": 1331, "ctx_chars": 8224, "t_end": 1791529691.8573456, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.5724, "lo95": 0.5011, "mean": 0.6802, "ev_only": 0.5722, "ref_ms": 62.05911, "cand_ms": 108.42255, "n_trials": 18, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0, "r_wall_s": 294.37, "compile_s": 2.1, "r_error": "", "src_len": 896, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5501, "tout": 782, "ts": 1791529374.8628466, "chk": "ok", "code_len": 896}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6392, "tout": 101, "ts": 1791529393.0805252, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6517, "tout": 448, "ts": 1791529397.4474468, "chk": null, "code_len": 896}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5501, "started": 1791529365.6608434}
{"ep": "h1-00599", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.6074, "speedup": 4.6074, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 326.5, "calls": 2, "tokens_in": 13486, "tokens_out": 3494, "ctx_chars": 9438, "t_end": 1791529700.3945854, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.6074, "lo95": 4.5948, "mean": 4.5548, "ev_only": 4.6614, "ref_ms": 7.368, "cand_ms": 1.59918, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 56.76, "compile_s": 1.91, "r_error": "", "src_len": 2209, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5861, "tout": 2201, "ts": 1791529391.9626398, "chk": "ok", "code_len": 2209}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7625, "tout": 1293, "ts": 1791529643.4210837, "chk": null, "code_len": 2209}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5861, "started": 1791529373.8492534}
{"ep": "h1-00503", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4834, "speedup": 0.4834, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 764.4, "calls": 2, "tokens_in": 15555, "tokens_out": 6055, "ctx_chars": 10864, "t_end": 1791529704.4853253, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.4834, "lo95": 0.4831, "mean": 0.4835, "ev_only": 0.4833, "ref_ms": 20.16209, "cand_ms": 41.70654, "n_trials": 35, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9999, "r_wall_s": 254.22, "compile_s": 2.28, "r_error": "", "src_len": 3533, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6632, "tout": 4261, "ts": 1791528977.3063376, "chk": "ok", "code_len": 3533}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8923, "tout": 1794, "ts": 1791529449.478475, "chk": null, "code_len": 3533}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6632, "started": 1791528940.0452545}
{"ep": "h1-00548", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4799, "speedup": 0.4799, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 536.2, "calls": 3, "tokens_in": 31744, "tokens_out": 19486, "ctx_chars": 10864, "t_end": 1791529709.15313, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.4799, "lo95": 0.4794, "mean": 0.4571, "ev_only": 0.48, "ref_ms": 10.07949, "cand_ms": 21.00466, "n_trials": 55, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 137.26, "compile_s": 11.14, "r_error": "", "src_len": 7069, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6627, "tout": 11753, "ts": 1791529275.267117, "chk": "no_custom_kernel", "code_len": 7071}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10681, "tout": 4180, "ts": 1791529341.366775, "chk": "ok", "code_len": 7069}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14436, "tout": 3553, "ts": 1791529436.5336845, "chk": null, "code_len": 7069}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6627, "started": 1791529172.9257169}
{"ep": "h1-00607", "task": "L3_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6279, "speedup": 0.6279, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 283.4, "calls": 3, "tokens_in": 21940, "tokens_out": 4431, "ctx_chars": 6513, "t_end": 1791529711.8333933, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.6279, "lo95": 0.6243, "mean": 0.6368, "ev_only": 0.6274, "ref_ms": 39.39288, "cand_ms": 62.739, "n_trials": 17, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0193, "r_wall_s": 199.71, "compile_s": 2.01, "r_error": "", "src_len": 5017, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5725, "tout": 2231, "ts": 1791529467.4416294, "chk": "ok", "code_len": 5063}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8068, "tout": 55, "ts": 1791529494.506166, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8147, "tout": 2145, "ts": 1791529512.1002214, "chk": null, "code_len": 5017}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5725, "started": 1791529448.8484044}
{"ep": "h1-00600", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0055, "speedup": 1.0055, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 337.2, "calls": 2, "tokens_in": 3991, "tokens_out": 1908, "ctx_chars": 0, "t_end": 1791529711.8572297, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0055, "lo95": 1.0052, "mean": 1.0052, "ev_only": 1.0057, "ref_ms": 7.99081, "cand_ms": 7.94728, "n_trials": 184, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0048, "r_wall_s": 208.61, "compile_s": 1.93, "r_error": "", "src_len": 868, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1520, "tout": 1372, "ts": 1791529390.9023333, "chk": "ok", "code_len": 868}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2471, "tout": 536, "ts": 1791529503.147629, "chk": null, "code_len": 868}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1520, "started": 1791529374.642749}
{"ep": "h1-00648", "task": "L2_057", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 61.8, "calls": 1, "tokens_in": 1557, "tokens_out": 837, "ctx_chars": 0, "t_end": 1791529715.2523782, "error": "RuntimeError: Error building extension 'fused_relu_hardswish': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_relu_hardswish -DTORCH_API_INCLUDE_EXTEN", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 51.98, "compile_s": 51.98, "r_error": "RuntimeError: Error building extension 'fused_relu_hardswish': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_relu_hardswish -DTORCH_API_INCLUDE_EXTEN", "src_len": 1692, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1557, "tout": 837, "ts": 1791529663.163347, "chk": null, "code_len": 1692}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1557, "started": 1791529653.4628124}
{"ep": "h1-00591", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1603, "speedup": 1.1603, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 366.3, "calls": 2, "tokens_in": 4810, "tokens_out": 4914, "ctx_chars": 0, "t_end": 1791529715.3199804, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1603, "lo95": 1.1599, "mean": 1.1608, "ev_only": 1.1651, "ref_ms": 4.44742, "cand_ms": 3.83314, "n_trials": 231, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 216.35, "compile_s": 1.95, "r_error": "", "src_len": 2363, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1532, "tout": 3563, "ts": 1791529380.6539378, "chk": "ok", "code_len": 2363}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3278, "tout": 1351, "ts": 1791529498.9338264, "chk": null, "code_len": 2363}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1532, "started": 1791529348.983266}
{"ep": "h1-00621", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.4789, "speedup": 9.4789, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.9, "calls": 2, "tokens_in": 5255, "tokens_out": 4027, "ctx_chars": 0, "t_end": 1791529715.5139763, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 9.4789, "lo95": 9.4304, "mean": 9.4134, "ev_only": 9.4632, "ref_ms": 7.99578, "cand_ms": 0.84354, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2659, "r_wall_s": 81.03, "compile_s": 1.94, "r_error": "", "src_len": 2240, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1739, "tout": 2803, "ts": 1791529551.6870685, "chk": "ok", "code_len": 2240}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3516, "tout": 1224, "ts": 1791529634.4571018, "chk": null, "code_len": 2240}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1739, "started": 1791529526.6127763}
{"ep": "h1-00521", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.178, "speedup": 1.178, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 704.3, "calls": 5, "tokens_in": 33125, "tokens_out": 20807, "ctx_chars": 2425, "t_end": 1791529720.8020382, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.178, "lo95": 1.1769, "mean": 1.1761, "ev_only": 1.1787, "ref_ms": 15.89438, "cand_ms": 13.49273, "n_trials": 86, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0295, "r_wall_s": 75.46, "compile_s": 1.95, "r_error": "", "src_len": 3081, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3753, "tout": 4392, "ts": 1791529056.255167, "chk": "incorrect", "code_len": 2911}, {"turn": 1, "action": "CHECK", "stop": null, "tin": 5840, "tout": 3395, "ts": 1791529249.7532344, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5872, "tout": 4523, "ts": 1791529290.6702418, "chk": "incorrect", "code_len": 3127}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 7811, "tout": 6826, "ts": 1791529406.1649404, "chk": "ok", "code_len": 3081}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9849, "tout": 1671, "ts": 1791529644.507152, "chk": null, "code_len": 3081}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn", null], "chk_statuses": ["incorrect", "no_code", "incorrect", "ok", null], "first_tin": 3753, "started": 1791529016.5450351}
{"ep": "h1-00646", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0005, "speedup": 1.0005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 76.5, "calls": 2, "tokens_in": 9871, "tokens_out": 2076, "ctx_chars": 6513, "t_end": 1791529721.9085004, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0005, "lo95": 1.0002, "mean": 1.0111, "ev_only": 0.9996, "ref_ms": 10.6693, "cand_ms": 10.66403, "n_trials": 98, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0017, "r_wall_s": 44.49, "compile_s": 2.22, "r_error": "", "src_len": 1286, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4389, "tout": 1395, "ts": 1791529658.4350169, "chk": "ok", "code_len": 1286}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5482, "tout": 681, "ts": 1791529677.3115132, "chk": null, "code_len": 1286}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4389, "started": 1791529645.4254155}
{"ep": "h1-00585", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.9869, "speedup": 2.9869, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 393.5, "calls": 2, "tokens_in": 8125, "tokens_out": 13169, "ctx_chars": 0, "t_end": 1791529722.0202858, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.9869, "lo95": 2.9817, "mean": 2.9677, "ev_only": 3.0034, "ref_ms": 4.75584, "cand_ms": 1.59223, "n_trials": 206, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0629, "r_wall_s": 121.88, "compile_s": 16.65, "r_error": "", "src_len": 7724, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1917, "tout": 9391, "ts": 1791529411.7470539, "chk": "ok", "code_len": 7724}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6208, "tout": 3778, "ts": 1791529599.9734213, "chk": null, "code_len": 7724}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1917, "started": 1791529328.521643}
{"ep": "h1-00629", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 59.2581, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 178.0, "calls": 2, "tokens_in": 17834, "tokens_out": 15219, "ctx_chars": 10613, "t_end": 1791529723.8662024, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 59.2581, "lo95": 58.7679, "mean": 58.3143, "ev_only": 59.2452, "ref_ms": 36.26216, "cand_ms": 0.61194, "n_trials": 34, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 36.43, "compile_s": 16.35, "r_error": "", "src_len": 8952, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6522, "tout": 11098, "ts": 1791529643.7331426, "chk": "ok", "code_len": 8952}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11312, "tout": 4121, "ts": 1791529687.3050628, "chk": null, "code_len": 8952}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6522, "started": 1791529545.8990216}
{"ep": "h1-00547", "task": "L1_077", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9889, "speedup": 0.9889, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 557.2, "calls": 4, "tokens_in": 16904, "tokens_out": 2923, "ctx_chars": 0, "t_end": 1791529729.3535452, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9889, "lo95": 0.988, "mean": 0.9889, "ev_only": 0.9896, "ref_ms": 8.66177, "cand_ms": 8.75887, "n_trials": 154, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0064, "r_wall_s": 328.2, "compile_s": 17.17, "r_error": "", "src_len": 1714, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2021, "tout": 993, "ts": 1791529203.3826325, "chk": "compile_error", "code_len": 1655}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4230, "tout": 808, "ts": 1791529265.1147897, "chk": "ok", "code_len": 1714}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5150, "tout": 329, "ts": 1791529392.3178713, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5503, "tout": 793, "ts": 1791529399.5156431, "chk": null, "code_len": 1714}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 2021, "started": 1791529192.481888}
{"ep": "h1-00483", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7801, "speedup": 0.7801, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 876.9, "calls": 4, "tokens_in": 70629, "tokens_out": 42115, "ctx_chars": 6513, "t_end": 1791529733.1082792, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7801, "lo95": 0.7777, "mean": 0.7757, "ev_only": 0.7832, "ref_ms": 3.67601, "cand_ms": 4.71245, "n_trials": 187, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0086, "r_wall_s": 241.09, "compile_s": 1.94, "r_error": "", "src_len": 3892, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5548, "tout": 21230, "ts": 1791529038.8053918, "chk": "runtime_error", "code_len": 15490}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 14336, "tout": 12016, "ts": 1791529227.3771222, "chk": "incorrect", "code_len": 18074}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 24085, "tout": 6791, "ts": 1791529384.4935665, "chk": "ok", "code_len": 3992}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 26660, "tout": 2078, "ts": 1791529491.9940734, "chk": null, "code_len": 3892}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "ok", null], "first_tin": 5548, "started": 1791528856.1709468}
{"ep": "h1-00574", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.7852, "speedup": 3.7852, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 460.5, "calls": 4, "tokens_in": 26250, "tokens_out": 13772, "ctx_chars": 2425, "t_end": 1791529734.4203732, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.7852, "lo95": 3.7818, "mean": 3.7774, "ev_only": 3.7998, "ref_ms": 11.96817, "cand_ms": 3.16187, "n_trials": 118, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0485, "r_wall_s": 225.07, "compile_s": 1.92, "r_error": "", "src_len": 3300, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 3778, "ts": 1791529308.4243238, "chk": "incorrect", "code_len": 2811}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5383, "tout": 4423, "ts": 1791529362.4276307, "chk": "incorrect", "code_len": 3482}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7562, "tout": 3837, "ts": 1791529410.552887, "chk": "ok", "code_len": 3300}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9712, "tout": 1734, "ts": 1791529509.2320356, "chk": null, "code_len": 3300}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 3593, "started": 1791529273.9678047}
{"ep": "h1-00556", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2941, "speedup": 0.2941, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 535.8, "calls": 2, "tokens_in": 20302, "tokens_out": 12679, "ctx_chars": 0, "t_end": 1791529742.4530602, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.2941, "lo95": 0.2934, "mean": 0.2955, "ev_only": 0.2939, "ref_ms": 8.39617, "cand_ms": 28.55101, "n_trials": 43, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.8009, "r_wall_s": 183.23, "compile_s": 1.91, "r_error": "", "src_len": 10483, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7618, "tout": 8159, "ts": 1791529274.5210683, "chk": "ok", "code_len": 10483}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12684, "tout": 4520, "ts": 1791529559.1911755, "chk": null, "code_len": 10483}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7618, "started": 1791529206.6482496}
{"ep": "h1-00624", "task": "L2_051", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 35.8797, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 216.1, "calls": 1, "tokens_in": 1706, "tokens_out": 1423, "ctx_chars": 0, "t_end": 1791529749.1384838, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 35.8797, "lo95": 35.8159, "mean": 35.0869, "ev_only": 37.045, "ref_ms": 15.9147, "cand_ms": 0.44356, "n_trials": 93, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.2328, "r_wall_s": 200.45, "compile_s": 3.48, "r_error": "", "src_len": 1408, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1706, "tout": 1423, "ts": 1791529548.5632064, "chk": null, "code_len": 1408}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1706, "started": 1791529533.0711703}
{"ep": "h1-00636", "task": "L2_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2597, "speedup": 1.2597, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 157.0, "calls": 1, "tokens_in": 6424, "tokens_out": 508, "ctx_chars": 11132, "t_end": 1791529751.6563044, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2597, "lo95": 1.2587, "mean": 1.2524, "ev_only": 1.259, "ref_ms": 3.64907, "cand_ms": 2.89673, "n_trials": 209, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2693, "r_wall_s": 150.81, "compile_s": 3.09, "r_error": "", "src_len": 950, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6424, "tout": 508, "ts": 1791529600.0545938, "chk": null, "code_len": 950}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6424, "started": 1791529594.6986892}
{"ep": "h1-00620", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4514, "speedup": 1.4514, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.0, "calls": 2, "tokens_in": 5213, "tokens_out": 4666, "ctx_chars": 0, "t_end": 1791529778.7533817, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4514, "lo95": 1.444, "mean": 1.4478, "ev_only": 1.4571, "ref_ms": 8.0264, "cand_ms": 5.53016, "n_trials": 172, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 152.03, "compile_s": 2.57, "r_error": "", "src_len": 3075, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1588, "tout": 3006, "ts": 1791529544.6964104, "chk": "ok", "code_len": 3075}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3625, "tout": 1660, "ts": 1791529626.6521358, "chk": null, "code_len": 3075}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1588, "started": 1791529518.7978046}
{"ep": "h1-00642", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6399, "speedup": 0.6399, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 169.3, "calls": 2, "tokens_in": 16587, "tokens_out": 5674, "ctx_chars": 13278, "t_end": 1791529778.7794418, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.6399, "lo95": 0.6376, "mean": 0.6422, "ev_only": 0.6418, "ref_ms": 5.32993, "cand_ms": 8.3297, "n_trials": 128, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 100.45, "compile_s": 2.28, "r_error": "", "src_len": 3139, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 3929, "ts": 1791529644.4855776, "chk": "ok", "code_len": 3139}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9425, "tout": 1745, "ts": 1791529677.831343, "chk": null, "code_len": 3139}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791529609.4808915}
{"ep": "h1-00608", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2149, "speedup": 1.2149, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 351.5, "calls": 2, "tokens_in": 9650, "tokens_out": 10022, "ctx_chars": 0, "t_end": 1791529780.3065567, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2149, "lo95": 1.2145, "mean": 1.215, "ev_only": 1.2154, "ref_ms": 75.34172, "cand_ms": 62.01375, "n_trials": 20, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1936, "r_wall_s": 62.91, "compile_s": 3.68, "r_error": "", "src_len": 5740, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 6894, "ts": 1791529484.3383443, "chk": "ok", "code_len": 5740}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6629, "tout": 3128, "ts": 1791529716.724474, "chk": null, "code_len": 5740}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791529428.8150241}
{"ep": "h1-00650", "task": "L2_069", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2559, "speedup": 1.2559, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 119.0, "calls": 1, "tokens_in": 7228, "tokens_out": 494, "ctx_chars": 12471, "t_end": 1791529781.9846926, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2559, "lo95": 1.2531, "mean": 1.3023, "ev_only": 1.2636, "ref_ms": 3.63869, "cand_ms": 2.8973, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2699, "r_wall_s": 113.16, "compile_s": 1.9, "r_error": "", "src_len": 906, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7228, "tout": 494, "ts": 1791529667.9968407, "chk": null, "code_len": 906}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7228, "started": 1791529662.961371}
{"ep": "h1-00612", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0321, "speedup": 1.0321, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 318.7, "calls": 2, "tokens_in": 12234, "tokens_out": 2153, "ctx_chars": 9028, "t_end": 1791529788.0660992, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0321, "lo95": 1.031, "mean": 1.0224, "ev_only": 1.0345, "ref_ms": 8.46199, "cand_ms": 8.19916, "n_trials": 130, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0052, "r_wall_s": 80.51, "compile_s": 3.12, "r_error": "", "src_len": 1197, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 1493, "ts": 1791529482.0582104, "chk": "ok", "code_len": 1197}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6696, "tout": 660, "ts": 1791529707.3517735, "chk": null, "code_len": 1197}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5538, "started": 1791529469.3741775}
{"ep": "h1-00626", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.566, "speedup": 1.566, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 247.9, "calls": 2, "tokens_in": 16785, "tokens_out": 6873, "ctx_chars": 13278, "t_end": 1791529788.4975677, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.566, "lo95": 1.5644, "mean": 1.5738, "ev_only": 1.5631, "ref_ms": 5.32041, "cand_ms": 3.39736, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9982, "r_wall_s": 162.69, "compile_s": 2.38, "r_error": "", "src_len": 3323, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 5006, "ts": 1791529584.5285146, "chk": "ok", "code_len": 3323}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9623, "tout": 1867, "ts": 1791529625.3544385, "chk": null, "code_len": 3323}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791529540.6150632}
{"ep": "h1-00638", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.0731, "speedup": 2.0731, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.9, "calls": 2, "tokens_in": 6887, "tokens_out": 4632, "ctx_chars": 0, "t_end": 1791529795.168065, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.0731, "lo95": 2.071, "mean": 2.0757, "ev_only": 2.08, "ref_ms": 12.89359, "cand_ms": 6.21962, "n_trials": 119, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4799, "r_wall_s": 92.62, "compile_s": 2.53, "r_error": "", "src_len": 2602, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2484, "tout": 3265, "ts": 1791529633.0763674, "chk": "ok", "code_len": 2602}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4403, "tout": 1367, "ts": 1791529702.327164, "chk": null, "code_len": 2602}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2484, "started": 1791529605.2308435}
{"ep": "h1-00654", "task": "L3_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 111.6, "calls": 1, "tokens_in": 1972, "tokens_out": 1432, "ctx_chars": 0, "t_end": 1791529811.9876964, "error": "RuntimeError: Error building extension 'addrelu_m': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=addrelu_m -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 77.86, "compile_s": 77.85, "r_error": "RuntimeError: Error building extension 'addrelu_m': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=addrelu_m -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "src_len": 3018, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1972, "tout": 1432, "ts": 1791529734.0838947, "chk": null, "code_len": 3018}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1972, "started": 1791529720.7455812}
{"ep": "h1-00640", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3023, "speedup": 1.3023, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 208.5, "calls": 2, "tokens_in": 5396, "tokens_out": 4801, "ctx_chars": 0, "t_end": 1791529817.1824336, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.3023, "lo95": 1.3008, "mean": 1.3092, "ev_only": 1.3024, "ref_ms": 33.67141, "cand_ms": 25.85456, "n_trials": 33, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 133.45, "compile_s": 2.44, "r_error": "", "src_len": 3018, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 3216, "ts": 1791529637.4978292, "chk": "ok", "code_len": 3018}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3681, "tout": 1585, "ts": 1791529683.6718235, "chk": null, "code_len": 3018}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791529608.674787}
{"ep": "h1-00675", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0045, "speedup": 1.0045, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 37.4, "calls": 2, "tokens_in": 12510, "tokens_out": 1216, "ctx_chars": 9890, "t_end": 1791529819.3671901, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0045, "lo95": 1.0043, "mean": 1.0487, "ev_only": 1.0055, "ref_ms": 8.01731, "cand_ms": 7.98105, "n_trials": 131, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0041, "r_wall_s": 18.28, "compile_s": 1.84, "r_error": "", "src_len": 1036, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5890, "tout": 621, "ts": 1791529787.7082367, "chk": "ok", "code_len": 1036}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6620, "tout": 595, "ts": 1791529801.01943, "chk": null, "code_len": 1036}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5890, "started": 1791529781.9849656}
{"ep": "h1-00644", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2299, "speedup": 1.2299, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.1, "calls": 2, "tokens_in": 15716, "tokens_out": 2619, "ctx_chars": 12155, "t_end": 1791529825.0251827, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2299, "lo95": 1.2287, "mean": 1.2346, "ev_only": 1.2344, "ref_ms": 12.45885, "cand_ms": 10.12982, "n_trials": 100, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0831, "r_wall_s": 117.12, "compile_s": 2.84, "r_error": "", "src_len": 1620, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7203, "tout": 1702, "ts": 1791529673.5002165, "chk": "ok", "code_len": 1620}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8513, "tout": 917, "ts": 1791529707.0560231, "chk": null, "code_len": 1620}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7203, "started": 1791529657.2747416}
{"ep": "h1-00584", "task": "L1_078", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.0177, "speedup": 0.0177, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 511.0, "calls": 3, "tokens_in": 11260, "tokens_out": 4700, "ctx_chars": 0, "t_end": 1791529831.516088, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0177, "lo95": 0.0177, "mean": 0.0177, "ev_only": 0.0177, "ref_ms": 35.50062, "cand_ms": 2004.92087, "n_trials": 13, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 262.14, "compile_s": 1.96, "r_error": "", "src_len": 2960, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1960, "tout": 1746, "ts": 1791529338.094862, "chk": "ok", "code_len": 2836}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3818, "tout": 1552, "ts": 1791529393.1685584, "chk": "ok", "code_len": 2960}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5482, "tout": 1402, "ts": 1791529568.118604, "chk": null, "code_len": 2960}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 1960, "started": 1791529320.5101864}
{"ep": "h1-00634", "task": "L2_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1648, "speedup": 1.1648, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 240.1, "calls": 4, "tokens_in": 32195, "tokens_out": 3122, "ctx_chars": 11535, "t_end": 1791529833.282306, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1648, "lo95": 1.1639, "mean": 1.1637, "ev_only": 1.1654, "ref_ms": 20.09353, "cand_ms": 17.25129, "n_trials": 67, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0258, "r_wall_s": 92.33, "compile_s": 3.28, "r_error": "", "src_len": 2463, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6865, "tout": 520, "ts": 1791529600.1756234, "chk": "forbidden", "code_len": 273}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7484, "tout": 1291, "ts": 1791529612.0141177, "chk": "ok", "code_len": 2509}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8887, "tout": 48, "ts": 1791529730.2717326, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8959, "tout": 1263, "ts": 1791529740.9034252, "chk": null, "code_len": 2463}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 6865, "started": 1791529593.2274237}
{"ep": "h1-00639", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.1141, "speedup": 4.1141, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.2, "calls": 2, "tokens_in": 18398, "tokens_out": 8729, "ctx_chars": 12352, "t_end": 1791529842.4984272, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.1141, "lo95": 4.1115, "mean": 4.1064, "ev_only": 4.1254, "ref_ms": 27.83126, "cand_ms": 6.76485, "n_trials": 53, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0865, "r_wall_s": 20.86, "compile_s": 1.92, "r_error": "", "src_len": 5417, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7394, "tout": 5861, "ts": 1791529655.9990716, "chk": "ok", "code_len": 5453}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11004, "tout": 2868, "ts": 1791529821.3546667, "chk": null, "code_len": 5417}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7394, "started": 1791529605.326361}
{"ep": "h1-00672", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.036, "speedup": 1.036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 65.9, "calls": 2, "tokens_in": 13960, "tokens_out": 1284, "ctx_chars": 10901, "t_end": 1791529844.613315, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.036, "lo95": 1.0353, "mean": 1.0358, "ev_only": 1.0364, "ref_ms": 8.2627, "cand_ms": 7.97527, "n_trials": 183, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 26.04, "compile_s": 1.96, "r_error": "", "src_len": 927, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6549, "tout": 750, "ts": 1791529806.1510305, "chk": "ok", "code_len": 927}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7411, "tout": 534, "ts": 1791529818.5029175, "chk": null, "code_len": 927}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6549, "started": 1791529799.1012552}
{"ep": "h1-00660", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0023, "speedup": 1.0023, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 131.7, "calls": 2, "tokens_in": 13705, "tokens_out": 1603, "ctx_chars": 10909, "t_end": 1791529847.068088, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0023, "lo95": 1.0019, "mean": 1.0208, "ev_only": 1.0025, "ref_ms": 16.03732, "cand_ms": 16.00117, "n_trials": 70, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0009, "r_wall_s": 31.85, "compile_s": 1.82, "r_error": "", "src_len": 938, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6428, "tout": 1079, "ts": 1791529727.4923553, "chk": "ok", "code_len": 938}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7277, "tout": 524, "ts": 1791529815.0856414, "chk": null, "code_len": 938}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6428, "started": 1791529715.3201706}
{"ep": "h1-00604", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4602, "speedup": 0.4602, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 437.4, "calls": 2, "tokens_in": 7414, "tokens_out": 11546, "ctx_chars": 0, "t_end": 1791529847.6593232, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4602, "lo95": 0.4596, "mean": 0.4595, "ev_only": 0.4604, "ref_ms": 9.96498, "cand_ms": 21.65487, "n_trials": 64, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 302.96, "compile_s": 16.24, "r_error": "", "src_len": 5824, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 8729, "ts": 1791529488.5753648, "chk": "ok", "code_len": 5824}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5411, "tout": 2817, "ts": 1791529543.9089262, "chk": null, "code_len": 5824}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791529410.3068795}
{"ep": "h1-00674", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0658, "speedup": 1.0658, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 72.0, "calls": 2, "tokens_in": 4884, "tokens_out": 2959, "ctx_chars": 0, "t_end": 1791529852.2695534, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0658, "lo95": 1.0653, "mean": 1.0671, "ev_only": 1.0669, "ref_ms": 8.46454, "cand_ms": 7.94218, "n_trials": 172, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 34.79, "compile_s": 1.97, "r_error": "", "src_len": 1850, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 1933, "ts": 1791529797.0061283, "chk": "ok", "code_len": 1850}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3169, "tout": 1026, "ts": 1791529817.3287792, "chk": null, "code_len": 1850}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791529780.3068063}
{"ep": "h1-00583", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9951, "speedup": 0.9951, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 536.3, "calls": 5, "tokens_in": 55504, "tokens_out": 16704, "ctx_chars": 6513, "t_end": 1791529854.1451304, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9951, "lo95": 0.9944, "mean": 0.9957, "ev_only": 0.9947, "ref_ms": 23.39584, "cand_ms": 23.5112, "n_trials": 56, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0262, "r_wall_s": 137.47, "compile_s": 19.55, "r_error": "", "src_len": 4542, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5439, "tout": 3614, "ts": 1791529347.400085, "chk": "incorrect", "code_len": 4809}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8352, "tout": 3797, "ts": 1791529539.5037374, "chk": "incorrect", "code_len": 5034}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11222, "tout": 3446, "ts": 1791529641.2280083, "chk": "runtime_error", "code_len": 3948}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 13961, "tout": 3472, "ts": 1791529675.1678073, "chk": "ok", "code_len": 4542}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 16530, "tout": 2375, "ts": 1791529716.6218402, "chk": null, "code_len": 4542}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "runtime_error", "ok", null], "first_tin": 5439, "started": 1791529317.8914642}
{"ep": "h1-00651", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0642, "speedup": 1.0642, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.4, "calls": 2, "tokens_in": 13787, "tokens_out": 2032, "ctx_chars": 10191, "t_end": 1791529859.5874956, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0642, "lo95": 1.0633, "mean": 1.0644, "ev_only": 1.0648, "ref_ms": 8.51448, "cand_ms": 8.00105, "n_trials": 131, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0056, "r_wall_s": 150.08, "compile_s": 3.06, "r_error": "", "src_len": 1641, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6250, "tout": 1175, "ts": 1791529682.1423945, "chk": "ok", "code_len": 1641}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7537, "tout": 857, "ts": 1791529709.4263132, "chk": null, "code_len": 1641}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6250, "started": 1791529672.1984057}
{"ep": "h1-00581", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0059, "speedup": 1.0059, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 555.2, "calls": 4, "tokens_in": 22653, "tokens_out": 13546, "ctx_chars": 0, "t_end": 1791529868.5841517, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0059, "lo95": 0.9998, "mean": 1.0073, "ev_only": 1.0062, "ref_ms": 8.13045, "cand_ms": 8.08316, "n_trials": 170, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0036, "r_wall_s": 351.62, "compile_s": 16.05, "r_error": "", "src_len": 2148, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1783, "tout": 4029, "ts": 1791529346.810248, "chk": "incorrect", "code_len": 4504}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4612, "tout": 5153, "ts": 1791529432.5346727, "chk": "incorrect", "code_len": 4778}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7366, "tout": 2430, "ts": 1791529474.4794784, "chk": "ok", "code_len": 2148}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8892, "tout": 1934, "ts": 1791529516.9348292, "chk": null, "code_len": 2148}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1783, "started": 1791529313.3859105}
{"ep": "h1-00630", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0008, "speedup": 1.0008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 332.6, "calls": 2, "tokens_in": 11844, "tokens_out": 1354, "ctx_chars": 9033, "t_end": 1791529881.1693678, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0008, "lo95": 1.0005, "mean": 1.0016, "ev_only": 1.0019, "ref_ms": 4.47043, "cand_ms": 4.46684, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0022, "r_wall_s": 32.9, "compile_s": 1.9, "r_error": "", "src_len": 1001, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5455, "tout": 825, "ts": 1791529556.4279203, "chk": "ok", "code_len": 1001}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6389, "tout": 529, "ts": 1791529848.2176046, "chk": null, "code_len": 1001}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5455, "started": 1791529548.5652065}
{"ep": "h1-00661", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.648, "speedup": 4.648, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 166.7, "calls": 2, "tokens_in": 13446, "tokens_out": 3308, "ctx_chars": 9438, "t_end": 1791529882.227263, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.648, "lo95": 4.6375, "mean": 4.6332, "ev_only": 4.6658, "ref_ms": 7.37842, "cand_ms": 1.58746, "n_trials": 206, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9713, "r_wall_s": 25.27, "compile_s": 1.91, "r_error": "", "src_len": 2214, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5861, "tout": 2004, "ts": 1791529731.8425558, "chk": "ok", "code_len": 2214}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7585, "tout": 1304, "ts": 1791529856.813547, "chk": null, "code_len": 2214}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5861, "started": 1791529715.5141735}
{"ep": "h1-00658", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.641, "speedup": 1.641, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 171.6, "calls": 2, "tokens_in": 8764, "tokens_out": 6281, "ctx_chars": 3355, "t_end": 1791529883.4187026, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.641, "lo95": 1.6401, "mean": 1.6734, "ev_only": 1.6397, "ref_ms": 20.54744, "cand_ms": 12.52102, "n_trials": 56, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 41.69, "compile_s": 2.63, "r_error": "", "src_len": 3078, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3296, "tout": 4622, "ts": 1791529753.8949802, "chk": "ok", "code_len": 3078}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5468, "tout": 1659, "ts": 1791529841.6835372, "chk": null, "code_len": 3078}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3296, "started": 1791529711.8574998}
{"ep": "h1-00623", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 13.4494, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 355.2, "calls": 2, "tokens_in": 5392, "tokens_out": 4553, "ctx_chars": 0, "t_end": 1791529884.1421533, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 13.4494, "lo95": 13.4018, "mean": 13.3446, "ev_only": 13.7145, "ref_ms": 10.08184, "cand_ms": 0.74961, "n_trials": 152, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 54.12, "compile_s": 1.88, "r_error": "", "src_len": 2813, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1642, "tout": 2994, "ts": 1791529555.1314015, "chk": "ok", "code_len": 2813}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3750, "tout": 1559, "ts": 1791529829.5150654, "chk": null, "code_len": 2813}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1642, "started": 1791529528.934709}
{"ep": "h1-00592", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.0764, "speedup": 6.0764, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 528.1, "calls": 2, "tokens_in": 14768, "tokens_out": 15511, "ctx_chars": 8224, "t_end": 1791529885.3374693, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 6.0764, "lo95": 4.4017, "mean": 5.6827, "ev_only": 6.0826, "ref_ms": 130.5698, "cand_ms": 21.48819, "n_trials": 11, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8363, "r_wall_s": 348.02, "compile_s": 17.19, "r_error": "", "src_len": 6370, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5516, "tout": 12419, "ts": 1791529491.283753, "chk": "ok", "code_len": 6370}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9252, "tout": 3092, "ts": 1791529537.2928364, "chk": null, "code_len": 6370}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5516, "started": 1791529377.5994394}
{"ep": "h1-00686", "task": "L2_053", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0139, "speedup": 1.0139, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 43.8, "calls": 1, "tokens_in": 1669, "tokens_out": 717, "ctx_chars": 0, "t_end": 1791529888.4465344, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0139, "lo95": 1.0128, "mean": 1.0186, "ev_only": 1.0136, "ref_ms": 15.93947, "cand_ms": 15.72024, "n_trials": 83, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 36.41, "compile_s": 1.87, "r_error": "", "src_len": 1299, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1669, "tout": 717, "ts": 1791529851.890598, "chk": null, "code_len": 1299}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1669, "started": 1791529844.6135669}
{"ep": "h1-00561", "task": "L2_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.184, "speedup": 1.184, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 667.8, "calls": 4, "tokens_in": 25338, "tokens_out": 7939, "ctx_chars": 0, "t_end": 1791529889.811832, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.184, "lo95": 1.181, "mean": 1.1661, "ev_only": 1.1798, "ref_ms": 4.8142, "cand_ms": 4.0661, "n_trials": 164, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4807, "r_wall_s": 371.68, "compile_s": 15.84, "r_error": "", "src_len": 5023, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1915, "tout": 2887, "ts": 1791529247.6606412, "chk": "compile_error", "code_len": 5484}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6037, "tout": 2519, "ts": 1791529321.9888241, "chk": "ok", "code_len": 5023}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8668, "tout": 26, "ts": 1791529497.604411, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8718, "tout": 2507, "ts": 1791529518.0665486, "chk": null, "code_len": 5023}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1915, "started": 1791529222.0462954}
{"ep": "h1-00625", "task": "L2_069", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2506, "speedup": 1.2506, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 350.5, "calls": 1, "tokens_in": 7228, "tokens_out": 499, "ctx_chars": 12471, "t_end": 1791529890.2661474, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2506, "lo95": 1.2495, "mean": 1.2506, "ev_only": 1.258, "ref_ms": 3.62726, "cand_ms": 2.90037, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2346, "r_wall_s": 344.24, "compile_s": 3.12, "r_error": "", "src_len": 906, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7228, "tout": 499, "ts": 1791529545.018432, "chk": null, "code_len": 906}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7228, "started": 1791529539.8017044}
{"ep": "h1-00586", "task": "L1_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6724, "speedup": 0.6724, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 563.2, "calls": 4, "tokens_in": 14340, "tokens_out": 4282, "ctx_chars": 0, "t_end": 1791529894.2924535, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.6724, "lo95": 0.6716, "mean": 0.6722, "ev_only": 0.6725, "ref_ms": 7.55884, "cand_ms": 11.24107, "n_trials": 107, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 60.09, "compile_s": 1.88, "r_error": "", "src_len": 2485, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 1546, "ts": 1791529346.4639874, "chk": "incorrect", "code_len": 2573}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3243, "tout": 1390, "ts": 1791529564.9454064, "chk": "ok", "code_len": 2485}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4742, "tout": 24, "ts": 1791529823.164981, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 4790, "tout": 1322, "ts": 1791529834.1291947, "chk": null, "code_len": 2485}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 1565, "started": 1791529331.1151278}
{"ep": "h1-00589", "task": "L1_077", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9966, "speedup": 0.9966, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 559.7, "calls": 4, "tokens_in": 17541, "tokens_out": 3080, "ctx_chars": 0, "t_end": 1791529904.3254845, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9966, "lo95": 0.9955, "mean": 0.9947, "ev_only": 0.9969, "ref_ms": 8.6257, "cand_ms": 8.65477, "n_trials": 167, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.006, "r_wall_s": 376.45, "compile_s": 24.23, "r_error": "", "src_len": 1704, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2021, "tout": 1185, "ts": 1791529357.3078346, "chk": "compile_error", "code_len": 1644}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4454, "tout": 821, "ts": 1791529425.086127, "chk": "ok", "code_len": 1704}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5387, "tout": 268, "ts": 1791529519.870011, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5679, "tout": 806, "ts": 1791529526.9790895, "chk": null, "code_len": 1704}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 2021, "started": 1791529344.5787482}
{"ep": "h1-00627", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 8.9941, "speedup": 8.9941, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 365.6, "calls": 3, "tokens_in": 15873, "tokens_out": 14320, "ctx_chars": 0, "t_end": 1791529906.6219416, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 8.9941, "lo95": 8.9796, "mean": 9.1568, "ev_only": 8.9781, "ref_ms": 5.93378, "cand_ms": 0.65974, "n_trials": 198, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 44.32, "compile_s": 14.66, "r_error": "", "src_len": 5835, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1845, "tout": 8123, "ts": 1791529612.881256, "chk": "no_custom_kernel", "code_len": 5857}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5430, "tout": 3186, "ts": 1791529761.2086558, "chk": "ok", "code_len": 5835}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8598, "tout": 3011, "ts": 1791529862.2222915, "chk": null, "code_len": 5835}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1845, "started": 1791529540.9726045}
{"ep": "h1-00645", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 8.8042, "speedup": 8.8042, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 273.5, "calls": 2, "tokens_in": 11685, "tokens_out": 7976, "ctx_chars": 6034, "t_end": 1791529910.929061, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 8.8042, "lo95": 8.7086, "mean": 9.5923, "ev_only": 8.8304, "ref_ms": 29.10627, "cand_ms": 3.30594, "n_trials": 55, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9755, "r_wall_s": 132.8, "compile_s": 21.88, "r_error": "", "src_len": 4257, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 5844, "ts": 1791529686.88265, "chk": "ok", "code_len": 4257}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7137, "tout": 2132, "ts": 1791529778.075629, "chk": null, "code_len": 4257}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4548, "started": 1791529637.3912807}
{"ep": "h1-00616", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.0521, "speedup": 5.0521, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 421.3, "calls": 3, "tokens_in": 10966, "tokens_out": 7101, "ctx_chars": 0, "t_end": 1791529913.164609, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 5.0521, "lo95": 5.0467, "mean": 5.0875, "ev_only": 5.0955, "ref_ms": 7.39168, "cand_ms": 1.4631, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 172.07, "compile_s": 3.07, "r_error": "", "src_len": 2560, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1612, "tout": 4104, "ts": 1791529550.2002823, "chk": "runtime_error", "code_len": 3286}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3907, "tout": 1640, "ts": 1791529618.3785815, "chk": "ok", "code_len": 2560}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5447, "tout": 1357, "ts": 1791529740.945379, "chk": null, "code_len": 2560}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 1612, "started": 1791529512.2263916}
{"ep": "h1-00681", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8708, "speedup": 0.8708, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 98.4, "calls": 2, "tokens_in": 5089, "tokens_out": 4265, "ctx_chars": 0, "t_end": 1791529917.7582498, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8708, "lo95": 0.8698, "mean": 0.8748, "ev_only": 0.8696, "ref_ms": 7.51848, "cand_ms": 8.63407, "n_trials": 154, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 47.52, "compile_s": 2.4, "r_error": "", "src_len": 2420, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 2877, "ts": 1791529843.0905797, "chk": "ok", "code_len": 2420}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3522, "tout": 1388, "ts": 1791529870.0780313, "chk": null, "code_len": 2420}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791529819.3674548}
{"ep": "h1-00613", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.366, "speedup": 5.366, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 446.3, "calls": 3, "tokens_in": 18343, "tokens_out": 18896, "ctx_chars": 0, "t_end": 1791529917.9090352, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.366, "lo95": 5.3344, "mean": 5.4485, "ev_only": 5.3898, "ref_ms": 32.32111, "cand_ms": 6.02326, "n_trials": 31, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9906, "r_wall_s": 31.61, "compile_s": 13.54, "r_error": "", "src_len": 7208, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1946, "tout": 11342, "ts": 1791529579.2403321, "chk": "no_custom_kernel", "code_len": 7231}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6277, "tout": 3920, "ts": 1791529756.093396, "chk": "ok", "code_len": 7208}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10120, "tout": 3634, "ts": 1791529886.2442656, "chk": null, "code_len": 7208}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1946, "started": 1791529471.5922494}
{"ep": "h1-00664", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.0327, "speedup": 4.0327, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 196.5, "calls": 2, "tokens_in": 6229, "tokens_out": 9710, "ctx_chars": 0, "t_end": 1791529918.5408137, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.0327, "lo95": 4.0284, "mean": 4.073, "ev_only": 4.0518, "ref_ms": 12.28943, "cand_ms": 3.04745, "n_trials": 130, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9985, "r_wall_s": 85.74, "compile_s": 1.92, "r_error": "", "src_len": 3763, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1778, "tout": 7763, "ts": 1791529794.2665834, "chk": "ok", "code_len": 3788}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4451, "tout": 1947, "ts": 1791529832.006826, "chk": null, "code_len": 3763}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1778, "started": 1791529722.0205145}
{"ep": "h1-00689", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0664, "speedup": 1.0664, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.1, "calls": 2, "tokens_in": 12226, "tokens_out": 2797, "ctx_chars": 8462, "t_end": 1791529925.417899, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0664, "lo95": 1.0658, "mean": 1.072, "ev_only": 1.0669, "ref_ms": 8.47265, "cand_ms": 7.94528, "n_trials": 160, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0043, "r_wall_s": 19.12, "compile_s": 1.85, "r_error": "", "src_len": 1981, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1759, "ts": 1791529867.1896174, "chk": "ok", "code_len": 1981}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6824, "tout": 1038, "ts": 1791529906.189212, "chk": null, "code_len": 1981}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791529852.2698047}
{"ep": "h1-00666", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.9033, "speedup": 1.9033, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 200.4, "calls": 2, "tokens_in": 6069, "tokens_out": 8986, "ctx_chars": 0, "t_end": 1791529929.7730436, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.9033, "lo95": 1.9019, "mean": 1.9109, "ev_only": 1.91, "ref_ms": 3.64716, "cand_ms": 1.91619, "n_trials": 213, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 97.75, "compile_s": 15.28, "r_error": "", "src_len": 4633, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1631, "tout": 6632, "ts": 1791529789.0043657, "chk": "ok", "code_len": 4633}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4438, "tout": 2354, "ts": 1791529831.158938, "chk": null, "code_len": 4633}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1631, "started": 1791529729.353802}
{"ep": "h1-00663", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7372, "speedup": 0.7372, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 221.5, "calls": 2, "tokens_in": 15255, "tokens_out": 2642, "ctx_chars": 11175, "t_end": 1791529943.429341, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7372, "lo95": 0.7364, "mean": 0.738, "ev_only": 0.7379, "ref_ms": 3.33235, "cand_ms": 4.52021, "n_trials": 203, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0006, "r_wall_s": 113.33, "compile_s": 1.99, "r_error": "", "src_len": 2294, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6880, "tout": 1597, "ts": 1791529735.2097743, "chk": "ok", "code_len": 2294}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8375, "tout": 1045, "ts": 1791529829.142893, "chk": null, "code_len": 2294}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6880, "started": 1791529721.908753}
{"ep": "h1-00676", "task": "L3_019", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.61, "speedup": 0.61, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 167.7, "calls": 5, "tokens_in": 33259, "tokens_out": 8084, "ctx_chars": 0, "t_end": 1791529955.7412305, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.61, "lo95": 0.6086, "mean": 0.6213, "ev_only": 0.6107, "ref_ms": 3.82417, "cand_ms": 6.26869, "n_trials": 110, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0771, "r_wall_s": 39.55, "compile_s": 1.91, "r_error": "", "src_len": 3996, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2378, "tout": 3029, "ts": 1791529814.3281102, "chk": "incorrect", "code_len": 3412}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 1472, "ts": 1791529839.0137532, "chk": "ok", "code_len": 2660}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7119, "tout": 1844, "ts": 1791529874.3769133, "chk": "ok", "code_len": 3996}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9072, "tout": 33, "ts": 1791529902.067925, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9152, "tout": 1706, "ts": 1791529916.1683335, "chk": null, "code_len": 3996}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", "no_code", null], "first_tin": 2378, "started": 1791529788.0663958}
{"ep": "h1-00610", "task": "L1_077", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0005, "speedup": 1.0005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 523.7, "calls": 4, "tokens_in": 16737, "tokens_out": 2767, "ctx_chars": 0, "t_end": 1791529956.0372415, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0005, "lo95": 0.9964, "mean": 0.9938, "ev_only": 0.9968, "ref_ms": 8.78105, "cand_ms": 8.77655, "n_trials": 157, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0061, "r_wall_s": 142.57, "compile_s": 10.7, "r_error": "", "src_len": 1723, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2021, "tout": 927, "ts": 1791529441.4865358, "chk": "compile_error", "code_len": 1663}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4204, "tout": 814, "ts": 1791529640.7409208, "chk": "ok", "code_len": 1723}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5130, "tout": 228, "ts": 1791529805.4620194, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5382, "tout": 798, "ts": 1791529812.6253352, "chk": null, "code_len": 1723}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 2021, "started": 1791529432.3486133}
{"ep": "h1-00691", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0657, "speedup": 1.0657, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 102.0, "calls": 2, "tokens_in": 13803, "tokens_out": 2175, "ctx_chars": 10191, "t_end": 1791529961.5410867, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0657, "lo95": 1.0655, "mean": 1.0658, "ev_only": 1.0644, "ref_ms": 8.44775, "cand_ms": 7.92659, "n_trials": 176, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0059, "r_wall_s": 42.38, "compile_s": 2.03, "r_error": "", "src_len": 1992, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6250, "tout": 1191, "ts": 1791529869.6096337, "chk": "ok", "code_len": 1992}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7553, "tout": 984, "ts": 1791529919.0888994, "chk": null, "code_len": 1992}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6250, "started": 1791529859.5877512}
{"ep": "h1-00667", "task": "L3_033", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0552, "speedup": 1.0552, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 231.5, "calls": 2, "tokens_in": 8263, "tokens_out": 2803, "ctx_chars": 3355, "t_end": 1791529964.6442652, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0552, "lo95": 1.0541, "mean": 1.1104, "ev_only": 1.055, "ref_ms": 20.48516, "cand_ms": 19.41412, "n_trials": 33, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0013, "r_wall_s": 28.25, "compile_s": 1.9, "r_error": "", "src_len": 2351, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3294, "tout": 1563, "ts": 1791529749.0112417, "chk": "ok", "code_len": 2491}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4969, "tout": 1240, "ts": 1791529936.3585255, "chk": null, "code_len": 2351}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3294, "started": 1791529733.1088426}
{"ep": "h1-00687", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1803, "speedup": 1.1803, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 118.7, "calls": 2, "tokens_in": 5083, "tokens_out": 4444, "ctx_chars": 0, "t_end": 1791529965.807661, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1803, "lo95": 1.1783, "mean": 1.1728, "ev_only": 1.1791, "ref_ms": 7.33055, "cand_ms": 6.21074, "n_trials": 212, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 45.2, "compile_s": 2.81, "r_error": "", "src_len": 2423, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 2999, "ts": 1791529873.471209, "chk": "ok", "code_len": 2423}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3519, "tout": 1445, "ts": 1791529920.5367928, "chk": null, "code_len": 2423}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791529847.068412}
{"ep": "h1-00662", "task": "L2_074", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2739, "speedup": 1.2739, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 246.1, "calls": 3, "tokens_in": 8174, "tokens_out": 2231, "ctx_chars": 0, "t_end": 1791529966.8788824, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2739, "lo95": 1.2702, "mean": 1.2628, "ev_only": 1.2751, "ref_ms": 5.98582, "cand_ms": 4.69866, "n_trials": 214, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0418, "r_wall_s": 92.67, "compile_s": 2.06, "r_error": "", "src_len": 2091, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1843, "tout": 1172, "ts": 1791529732.4337132, "chk": "ok", "code_len": 2091}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3127, "tout": 53, "ts": 1791529865.5421214, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3204, "tout": 1006, "ts": 1791529874.126389, "chk": null, "code_len": 2091}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1843, "started": 1791529720.8022501}
{"ep": "h1-00641", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9905, "speedup": 0.9905, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 358.2, "calls": 2, "tokens_in": 13254, "tokens_out": 1076, "ctx_chars": 10823, "t_end": 1791529966.9110954, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9905, "lo95": 0.9884, "mean": 0.9855, "ev_only": 0.998, "ref_ms": 8.08456, "cand_ms": 8.16214, "n_trials": 147, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 223.84, "compile_s": 3.39, "r_error": "", "src_len": 855, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6277, "tout": 591, "ts": 1791529614.7124317, "chk": "ok", "code_len": 855}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6977, "tout": 485, "ts": 1791529742.9675317, "chk": null, "code_len": 855}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6277, "started": 1791529608.7064862}
{"ep": "h1-00707", "task": "L2_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 53.5, "calls": 1, "tokens_in": 1587, "tokens_out": 751, "ctx_chars": 0, "t_end": 1791529971.4475183, "error": "RuntimeError: Error building extension 'fused_div_lrelu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_div_lrelu -DTORCH_API_INCLUDE_EXTENSION_H -I/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 45.58, "compile_s": 45.58, "r_error": "RuntimeError: Error building extension 'fused_div_lrelu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_div_lrelu -DTORCH_API_INCLUDE_EXTENSION_H -I/", "src_len": 1579, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1587, "tout": 751, "ts": 1791529925.764205, "chk": null, "code_len": 1579}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1587, "started": 1791529917.9092572}
{"ep": "h1-00632", "task": "L1_006", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8864, "speedup": 0.8864, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 405.4, "calls": 5, "tokens_in": 45627, "tokens_out": 7538, "ctx_chars": 9033, "t_end": 1791529974.4196727, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8864, "lo95": 0.8859, "mean": 0.8858, "ev_only": 0.8875, "ref_ms": 3.70314, "cand_ms": 4.17768, "n_trials": 204, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9972, "r_wall_s": 53.96, "compile_s": 1.89, "r_error": "", "src_len": 2933, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 1789, "ts": 1791529585.1159837, "chk": "incorrect", "code_len": 2861}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7410, "tout": 1713, "ts": 1791529673.2041767, "chk": "incorrect", "code_len": 2742}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9256, "tout": 2285, "ts": 1791529759.6260664, "chk": "ok", "code_len": 2933}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11650, "tout": 126, "ts": 1791529906.9523516, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11823, "tout": 1625, "ts": 1791529920.3433251, "chk": null, "code_len": 2933}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5488, "started": 1791529569.0024974}
{"ep": "h1-00680", "task": "L3_047", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9591, "speedup": 0.9591, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.3, "calls": 3, "tokens_in": 16974, "tokens_out": 5682, "ctx_chars": 0, "t_end": 1791529981.4386737, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9591, "lo95": 0.9569, "mean": 0.9466, "ev_only": 0.963, "ref_ms": 3.69719, "cand_ms": 3.85475, "n_trials": 223, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0449, "r_wall_s": 92.28, "compile_s": 2.22, "r_error": "", "src_len": 2963, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2691, "tout": 4320, "ts": 1791529858.6650589, "chk": "ok", "code_len": 2963}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7123, "tout": 13, "ts": 1791529877.450658, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7160, "tout": 1349, "ts": 1791529888.789934, "chk": null, "code_len": 2963}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2691, "started": 1791529817.182996}
{"ep": "h1-00489", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 1105.7, "calls": 5, "tokens_in": 92572, "tokens_out": 83687, "ctx_chars": 0, "t_end": 1791529982.1933618, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": 0.0, "r_wall_s": 54.46, "compile_s": 12.43, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 8947, "atts": [{"turn": 0, "action": "CHECK", "stop": "max_tokens", "tin": 2845, "tout": 32000, "ts": 1791529174.8431566, "chk": "no_code", "code_len": 0}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9809, "tout": 13480, "ts": 1791529280.6476953, "chk": "incorrect", "code_len": 14385}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 18580, "tout": 9406, "ts": 1791529385.654772, "chk": "runtime_error", "code_len": 13498}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 26633, "tout": 9025, "ts": 1791529613.853475, "chk": "runtime_error", "code_len": 13683}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 34705, "tout": 19776, "ts": 1791529927.7109509, "chk": null, "code_len": 8947}], "n_turns": 5, "n_check": 4, "max_tok_hits": 1, "stops": ["end_turn", "max_tokens"], "chk_statuses": ["no_code", "incorrect", "runtime_error", "runtime_error", null], "first_tin": 2845, "started": 1791528876.4862273}
{"ep": "h1-00637", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 13.21, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 382.0, "calls": 2, "tokens_in": 9043, "tokens_out": 4562, "ctx_chars": 4348, "t_end": 1791529983.3727372, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 13.21, "lo95": 13.0538, "mean": 12.537, "ev_only": 13.3619, "ref_ms": 10.15834, "cand_ms": 0.76899, "n_trials": 154, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 215.94, "compile_s": 3.28, "r_error": "", "src_len": 2804, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3531, "tout": 2995, "ts": 1791529626.1367223, "chk": "ok", "code_len": 2804}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5512, "tout": 1567, "ts": 1791529766.8275683, "chk": null, "code_len": 2804}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3531, "started": 1791529601.4152837}
{"ep": "h1-00677", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.033, "speedup": 1.033, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 195.5, "calls": 2, "tokens_in": 16081, "tokens_out": 12778, "ctx_chars": 6513, "t_end": 1791529983.968677, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.033, "lo95": 0.9019, "mean": 0.9843, "ev_only": 1.0333, "ref_ms": 39.02768, "cand_ms": 37.77938, "n_trials": 31, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0702, "r_wall_s": 52.85, "compile_s": 1.88, "r_error": "", "src_len": 8404, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 8738, "ts": 1791529864.94483, "chk": "ok", "code_len": 8404}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10354, "tout": 4040, "ts": 1791529931.0056322, "chk": null, "code_len": 8404}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791529788.4978662}
{"ep": "h1-00631", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.284, "speedup": 1.284, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 418.4, "calls": 2, "tokens_in": 13205, "tokens_out": 2253, "ctx_chars": 9893, "t_end": 1791529986.8124135, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.284, "lo95": 1.2831, "mean": 1.284, "ev_only": 1.2827, "ref_ms": 19.76313, "cand_ms": 15.3916, "n_trials": 77, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0406, "r_wall_s": 238.44, "compile_s": 3.47, "r_error": "", "src_len": 1579, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5991, "tout": 1467, "ts": 1791529601.9461193, "chk": "ok", "code_len": 1579}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7214, "tout": 786, "ts": 1791529747.5717404, "chk": null, "code_len": 1579}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5991, "started": 1791529588.8067174}
{"ep": "h1-00704", "task": "L1_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0004, "speedup": 1.0004, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.3, "calls": 3, "tokens_in": 20029, "tokens_out": 977, "ctx_chars": 10384, "t_end": 1791529992.242221, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0004, "lo95": 0.9999, "mean": 1.034, "ev_only": 0.999, "ref_ms": 7.32882, "cand_ms": 7.32611, "n_trials": 153, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 57.92, "compile_s": 2.02, "r_error": "", "src_len": 559, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6166, "tout": 603, "ts": 1791529918.4993176, "chk": "ok", "code_len": 646}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6878, "tout": 83, "ts": 1791529931.0126793, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6985, "tout": 291, "ts": 1791529934.252018, "chk": null, "code_len": 559}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6166, "started": 1791529910.9293854}
{"ep": "h1-00693", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0334, "speedup": 1.0334, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 115.1, "calls": 2, "tokens_in": 4366, "tokens_out": 1950, "ctx_chars": 0, "t_end": 1791529996.2643313, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0334, "lo95": 1.0327, "mean": 1.0333, "ev_only": 1.0328, "ref_ms": 30.34596, "cand_ms": 29.36475, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0131, "r_wall_s": 61.81, "compile_s": 1.95, "r_error": "", "src_len": 864, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1696, "tout": 1443, "ts": 1791529895.377316, "chk": "ok", "code_len": 864}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2670, "tout": 507, "ts": 1791529933.9742866, "chk": null, "code_len": 864}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1696, "started": 1791529881.169638}
{"ep": "h1-00601", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.1143, "speedup": 4.1143, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 624.3, "calls": 3, "tokens_in": 16235, "tokens_out": 17328, "ctx_chars": 0, "t_end": 1791530007.0075042, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.1143, "lo95": 4.1101, "mean": 4.0939, "ev_only": 4.1383, "ref_ms": 8.63053, "cand_ms": 2.09767, "n_trials": 161, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9982, "r_wall_s": 135.39, "compile_s": 12.68, "r_error": "", "src_len": 5983, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2023, "tout": 11459, "ts": 1791529489.9192824, "chk": "no_custom_kernel", "code_len": 6129}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5609, "tout": 3032, "ts": 1791529715.309576, "chk": "ok", "code_len": 5983}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8603, "tout": 2837, "ts": 1791529870.611068, "chk": null, "code_len": 5983}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2023, "started": 1791529382.703337}
{"ep": "h1-00615", "task": "L2_011", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0024, "speedup": 1.0024, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 545.4, "calls": 3, "tokens_in": 11457, "tokens_out": 5425, "ctx_chars": 0, "t_end": 1791530026.0428996, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0024, "lo95": 1.0018, "mean": 1.0419, "ev_only": 1.0026, "ref_ms": 27.87482, "cand_ms": 27.8072, "n_trials": 51, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0057, "r_wall_s": 280.84, "compile_s": 70.79, "r_error": "", "src_len": 5461, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1808, "tout": 2880, "ts": 1791529508.0769894, "chk": "ok", "code_len": 5545}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4800, "tout": 25, "ts": 1791529725.197077, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4849, "tout": 2520, "ts": 1791529745.034343, "chk": null, "code_len": 5461}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1808, "started": 1791529480.6692114}
{"ep": "h1-00606", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6902, "speedup": 0.6902, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 611.1, "calls": 2, "tokens_in": 10330, "tokens_out": 11437, "ctx_chars": 0, "t_end": 1791530028.2558484, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.6902, "lo95": 0.6858, "mean": 0.6896, "ev_only": 0.6911, "ref_ms": 16.03577, "cand_ms": 23.23213, "n_trials": 43, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0451, "r_wall_s": 309.25, "compile_s": 3.95, "r_error": "", "src_len": 7741, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 7653, "ts": 1791529481.6640615, "chk": "ok", "code_len": 7741}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7306, "tout": 3784, "ts": 1791529718.408652, "chk": null, "code_len": 7741}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791529417.1459277}
{"ep": "h1-00635", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7484, "speedup": 1.7484, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 441.6, "calls": 2, "tokens_in": 14601, "tokens_out": 3901, "ctx_chars": 10743, "t_end": 1791530035.004169, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.7484, "lo95": 1.746, "mean": 1.7493, "ev_only": 1.7503, "ref_ms": 19.53003, "cand_ms": 11.17028, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2346, "r_wall_s": 284.36, "compile_s": 4.3, "r_error": "", "src_len": 2225, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6466, "tout": 2732, "ts": 1791529617.7075899, "chk": "ok", "code_len": 2225}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8135, "tout": 1169, "ts": 1791529750.3946755, "chk": null, "code_len": 2225}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6466, "started": 1791529593.3573058}
{"ep": "h1-00665", "task": "L2_095", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "runtime_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 311.4, "calls": 1, "tokens_in": 5536, "tokens_out": 686, "ctx_chars": 9028, "t_end": 1791530035.2908561, "error": "CompilationError: at 13:8:\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    mask = offs < n\n    col = offs % N\n    v = tl.load(x_ptr ", "f_status": "runtime_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": null, "r_wall_s": 304.34, "compile_s": 3.3, "r_error": "CompilationError: at 13:8:\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    mask = offs < n\n    col = offs % N\n    v = tl.load(x_ptr ", "src_len": 1302, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5536, "tout": 686, "ts": 1791529730.8854585, "chk": null, "code_len": 1302}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5536, "started": 1791529723.8664453}
{"ep": "h1-00701", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5342, "speedup": 1.5342, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 154.1, "calls": 2, "tokens_in": 5223, "tokens_out": 4540, "ctx_chars": 0, "t_end": 1791530048.376075, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.5342, "lo95": 1.5305, "mean": 1.5313, "ev_only": 1.5359, "ref_ms": 33.95685, "cand_ms": 22.13373, "n_trials": 36, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 82.01, "compile_s": 1.93, "r_error": "", "src_len": 2530, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 3230, "ts": 1791529922.801736, "chk": "ok", "code_len": 2530}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3508, "tout": 1310, "ts": 1791529966.200611, "chk": null, "code_len": 2530}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791529894.2926924}
{"ep": "h1-00695", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2657, "speedup": 1.2657, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 165.1, "calls": 2, "tokens_in": 14281, "tokens_out": 2891, "ctx_chars": 10364, "t_end": 1791530048.5079186, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2657, "lo95": 1.2646, "mean": 1.2689, "ev_only": 1.2633, "ref_ms": 5.92333, "cand_ms": 4.6799, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.051, "r_wall_s": 49.56, "compile_s": 2.74, "r_error": "", "src_len": 2052, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6397, "tout": 1844, "ts": 1791529899.4682727, "chk": "ok", "code_len": 2052}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7884, "tout": 1047, "ts": 1791529998.834199, "chk": null, "code_len": 2052}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6397, "started": 1791529883.4189863}
{"ep": "h1-00647", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.4336, "speedup": 5.4336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 400.2, "calls": 2, "tokens_in": 5917, "tokens_out": 10607, "ctx_chars": 0, "t_end": 1791530051.897891, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.4336, "lo95": 5.422, "mean": 5.4101, "ev_only": 5.4368, "ref_ms": 72.98966, "cand_ms": 13.43313, "n_trials": 21, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9861, "r_wall_s": 164.08, "compile_s": 2.17, "r_error": "", "src_len": 3897, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1699, "tout": 8575, "ts": 1791529735.4076784, "chk": "ok", "code_len": 3897}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4218, "tout": 2032, "ts": 1791529887.7764652, "chk": null, "code_len": 3897}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1699, "started": 1791529651.6935716}
{"ep": "h1-00694", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.2625, "speedup": 0.2625, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 171.9, "calls": 2, "tokens_in": 11838, "tokens_out": 11049, "ctx_chars": 2425, "t_end": 1791530054.1768336, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.2625, "lo95": 0.2625, "mean": 0.2626, "ev_only": 0.2625, "ref_ms": 75.65115, "cand_ms": 288.14909, "n_trials": 13, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.8274, "r_wall_s": 67.62, "compile_s": 2.13, "r_error": "", "src_len": 6332, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3937, "tout": 7554, "ts": 1791529946.1621194, "chk": "ok", "code_len": 6332}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7901, "tout": 3495, "ts": 1791529986.0620959, "chk": null, "code_len": 6332}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3937, "started": 1791529882.2276359}
{"ep": "h1-00688", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.1489, "speedup": 2.1489, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 207.9, "calls": 2, "tokens_in": 6725, "tokens_out": 3741, "ctx_chars": 0, "t_end": 1791530055.5430517, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.1489, "lo95": 2.1416, "mean": 2.1713, "ev_only": 2.1601, "ref_ms": 12.68633, "cand_ms": 5.90377, "n_trials": 109, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4607, "r_wall_s": 151.37, "compile_s": 2.05, "r_error": "", "src_len": 2315, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2484, "tout": 2538, "ts": 1791529870.175556, "chk": "ok", "code_len": 2315}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4241, "tout": 1203, "ts": 1791529904.061371, "chk": null, "code_len": 2315}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2484, "started": 1791529847.6595738}
{"ep": "h1-00673", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4709, "speedup": 0.4709, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 281.3, "calls": 2, "tokens_in": 15133, "tokens_out": 15468, "ctx_chars": 6513, "t_end": 1791530060.0862432, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4709, "lo95": 0.469, "mean": 0.4776, "ev_only": 0.4696, "ref_ms": 3.87389, "cand_ms": 8.22687, "n_trials": 155, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3315, "r_wall_s": 31.47, "compile_s": 1.87, "r_error": "", "src_len": 8350, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 11056, "ts": 1791529871.9270873, "chk": "ok", "code_len": 8350}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10050, "tout": 4412, "ts": 1791530028.5926764, "chk": null, "code_len": 8350}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791529778.7796667}
{"ep": "h1-00669", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.2099, "speedup": 7.2099, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 319.3, "calls": 3, "tokens_in": 33463, "tokens_out": 20039, "ctx_chars": 11175, "t_end": 1791530061.7243977, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 7.2099, "lo95": 7.1998, "mean": 7.3335, "ev_only": 7.3622, "ref_ms": 4.37075, "cand_ms": 0.60621, "n_trials": 212, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 83.97, "compile_s": 11.45, "r_error": "", "src_len": 7864, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 11849, "ts": 1791529849.0668921, "chk": "no_custom_kernel", "code_len": 7970}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11234, "tout": 4544, "ts": 1791529935.0146036, "chk": "ok", "code_len": 7864}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15162, "tout": 3646, "ts": 1791529977.562256, "chk": null, "code_len": 7864}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 7067, "started": 1791529742.4533246}
{"ep": "h1-00598", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.8288, "speedup": 1.8288, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 700.5, "calls": 2, "tokens_in": 6309, "tokens_out": 10837, "ctx_chars": 0, "t_end": 1791530072.0382745, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.8288, "lo95": 1.8272, "mean": 1.8486, "ev_only": 1.8263, "ref_ms": 19.32667, "cand_ms": 10.56769, "n_trials": 71, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 303.77, "compile_s": 20.72, "r_error": "", "src_len": 5387, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1586, "tout": 8096, "ts": 1791529443.3486407, "chk": "ok", "code_len": 5387}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4723, "tout": 2741, "ts": 1791529768.1770873, "chk": null, "code_len": 5387}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1586, "started": 1791529371.4958172}
{"ep": "h1-00679", "task": "L1_010", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8867, "speedup": 0.8867, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 268.6, "calls": 3, "tokens_in": 7862, "tokens_out": 2742, "ctx_chars": 0, "t_end": 1791530080.5780447, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8867, "lo95": 0.877, "mean": 0.9189, "ev_only": 0.8947, "ref_ms": 2.87845, "cand_ms": 3.24625, "n_trials": 202, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 83.35, "compile_s": 3.72, "r_error": "", "src_len": 2423, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1587, "tout": 1423, "ts": 1791529825.2100282, "chk": "ok", "code_len": 2423}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3119, "tout": 13, "ts": 1791529850.4719474, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3156, "tout": 1306, "ts": 1791529861.36924, "chk": null, "code_len": 2423}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1587, "started": 1791529811.9881}
{"ep": "h1-00678", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.7849, "speedup": 2.7849, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 286.5, "calls": 2, "tokens_in": 16345, "tokens_out": 8132, "ctx_chars": 11175, "t_end": 1791530081.637564, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.7849, "lo95": 2.7804, "mean": 2.5878, "ev_only": 2.7865, "ref_ms": 10.9346, "cand_ms": 3.92639, "n_trials": 64, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1346, "r_wall_s": 189.94, "compile_s": 2.29, "r_error": "", "src_len": 3883, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6872, "tout": 6079, "ts": 1791529852.2434683, "chk": "ok", "code_len": 3883}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9473, "tout": 2053, "ts": 1791529890.7915735, "chk": null, "code_len": 3883}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6872, "started": 1791529795.1683385}
{"ep": "h1-00717", "task": "L2_058", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2309, "speedup": 1.2309, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.8, "calls": 2, "tokens_in": 14729, "tokens_out": 1845, "ctx_chars": 11393, "t_end": 1791530083.6981587, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2309, "lo95": 1.2298, "mean": 1.2326, "ev_only": 1.2307, "ref_ms": 25.11883, "cand_ms": 20.40684, "n_trials": 53, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.043, "r_wall_s": 55.38, "compile_s": 1.87, "r_error": "", "src_len": 1691, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6820, "tout": 977, "ts": 1791529976.0374868, "chk": "ok", "code_len": 1691}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7909, "tout": 868, "ts": 1791530028.0225585, "chk": null, "code_len": 1691}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6820, "started": 1791529966.879122}
{"ep": "h1-00692", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.5915, "speedup": 3.5915, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.5, "calls": 2, "tokens_in": 7469, "tokens_out": 8789, "ctx_chars": 0, "t_end": 1791530086.093693, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 3.5915, "lo95": 3.572, "mean": 3.5031, "ev_only": 3.57, "ref_ms": 2.17705, "cand_ms": 0.60618, "n_trials": 201, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9959, "r_wall_s": 93.12, "compile_s": 17.35, "r_error": "", "src_len": 6969, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1813, "tout": 5564, "ts": 1791529914.0721266, "chk": "ok", "code_len": 6969}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5656, "tout": 3225, "ts": 1791529992.9378908, "chk": null, "code_len": 6969}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1813, "started": 1791529868.5844176}
{"ep": "h1-00682", "task": "L3_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4258, "speedup": 0.4258, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.1, "calls": 4, "tokens_in": 34215, "tokens_out": 6458, "ctx_chars": 6513, "t_end": 1791530086.1439028, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4258, "lo95": 0.4229, "mean": 0.4607, "ev_only": 0.4264, "ref_ms": 15.77958, "cand_ms": 37.05643, "n_trials": 27, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0265, "r_wall_s": 35.77, "compile_s": 2.45, "r_error": "", "src_len": 4910, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5725, "tout": 2042, "ts": 1791529842.6919742, "chk": "runtime_error", "code_len": 4549}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7881, "tout": 2286, "ts": 1791529869.3758798, "chk": "ok", "code_len": 4910}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10279, "tout": 27, "ts": 1791529896.3189242, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10330, "tout": 2103, "ts": 1791529914.30358, "chk": null, "code_len": 4910}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 5725, "started": 1791529825.0254505}
{"ep": "h1-00703", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1969, "speedup": 1.1969, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 180.4, "calls": 2, "tokens_in": 9479, "tokens_out": 7455, "ctx_chars": 2425, "t_end": 1791530087.0606894, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1969, "lo95": 1.1967, "mean": 1.1967, "ev_only": 1.1973, "ref_ms": 30.7626, "cand_ms": 25.70259, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3635, "r_wall_s": 55.82, "compile_s": 1.92, "r_error": "", "src_len": 4338, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3324, "tout": 5107, "ts": 1791529949.49325, "chk": "ok", "code_len": 4338}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6155, "tout": 2348, "ts": 1791530030.8039749, "chk": null, "code_len": 4338}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3324, "started": 1791529906.6221862}
{"ep": "h1-00609", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.625, "speedup": 9.625, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 678.3, "calls": 3, "tokens_in": 15748, "tokens_out": 15087, "ctx_chars": 0, "t_end": 1791530107.857009, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 9.625, "lo95": 9.6162, "mean": 9.712, "ev_only": 9.6034, "ref_ms": 5.86432, "cand_ms": 0.60928, "n_trials": 217, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 47.13, "compile_s": 14.95, "r_error": "", "src_len": 6175, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1845, "tout": 9077, "ts": 1791529511.4434679, "chk": "no_custom_kernel", "code_len": 6197}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5422, "tout": 3136, "ts": 1791529744.8866901, "chk": "ok", "code_len": 6175}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8481, "tout": 2874, "ts": 1791530060.658986, "chk": null, "code_len": 6175}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1845, "started": 1791529429.52003}
{"ep": "h1-00652", "task": "L1_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9272, "speedup": 0.9272, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 424.2, "calls": 3, "tokens_in": 22877, "tokens_out": 2334, "ctx_chars": 10864, "t_end": 1791530111.6665382, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9272, "lo95": 0.9265, "mean": 0.9244, "ev_only": 0.9264, "ref_ms": 10.09788, "cand_ms": 10.89119, "n_trials": 109, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0628, "r_wall_s": 370.51, "compile_s": 2.58, "r_error": "", "src_len": 1714, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6625, "tout": 1204, "ts": 1791529701.4958026, "chk": "ok", "code_len": 1714}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7938, "tout": 352, "ts": 1791529733.3219352, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8314, "tout": 778, "ts": 1791529740.3006716, "chk": null, "code_len": 1714}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6625, "started": 1791529687.4321754}
{"ep": "h1-00699", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.4579, "speedup": 2.4579, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 223.8, "calls": 3, "tokens_in": 14928, "tokens_out": 14627, "ctx_chars": 0, "t_end": 1791530113.5965717, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.4579, "lo95": 2.4452, "mean": 2.418, "ev_only": 2.4595, "ref_ms": 2.39118, "cand_ms": 0.97285, "n_trials": 205, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 52.47, "compile_s": 14.72, "r_error": "", "src_len": 5651, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 8742, "ts": 1791529969.1513717, "chk": "no_custom_kernel", "code_len": 5690}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5084, "tout": 3115, "ts": 1791530026.78143, "chk": "ok", "code_len": 5651}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8093, "tout": 2770, "ts": 1791530061.0780513, "chk": null, "code_len": 5651}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1751, "started": 1791529889.8120887}
{"ep": "h1-00724", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7015, "speedup": 1.7015, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 136.9, "calls": 2, "tokens_in": 15928, "tokens_out": 4327, "ctx_chars": 11288, "t_end": 1791530120.892379, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.7015, "lo95": 1.6961, "mean": 1.6995, "ev_only": 1.7013, "ref_ms": 29.10679, "cand_ms": 17.10611, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0523, "r_wall_s": 51.86, "compile_s": 3.13, "r_error": "", "src_len": 2587, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6972, "tout": 2967, "ts": 1791530010.6339803, "chk": "ok", "code_len": 2689}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8956, "tout": 1360, "ts": 1791530068.7171896, "chk": null, "code_len": 2587}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6972, "started": 1791529983.9689395}
{"ep": "h1-00710", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.0932, "speedup": 3.0932, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 191.6, "calls": 2, "tokens_in": 14594, "tokens_out": 3574, "ctx_chars": 10362, "t_end": 1791530121.4143307, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 3.0932, "lo95": 3.0872, "mean": 2.8838, "ev_only": 3.0857, "ref_ms": 2.93059, "cand_ms": 0.94744, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 124.52, "compile_s": 2.91, "r_error": "", "src_len": 2724, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6379, "tout": 2236, "ts": 1791529948.863098, "chk": "ok", "code_len": 2724}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8215, "tout": 1338, "ts": 1791529995.7604954, "chk": null, "code_len": 2724}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6379, "started": 1791529929.773276}
{"ep": "h1-00685", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 11.8158, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 279.2, "calls": 3, "tokens_in": 16329, "tokens_out": 8986, "ctx_chars": 2425, "t_end": 1791530121.739071, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 11.8158, "lo95": 11.7757, "mean": 11.813, "ev_only": 12.0393, "ref_ms": 12.01547, "cand_ms": 1.0169, "n_trials": 132, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.7207, "r_wall_s": 137.07, "compile_s": 2.01, "r_error": "", "src_len": 2662, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 3653, "ts": 1791529896.4979773, "chk": "incorrect", "code_len": 2671}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5424, "tout": 3993, "ts": 1791529965.3074238, "chk": "ok", "code_len": 2766}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7312, "tout": 1340, "ts": 1791529984.539335, "chk": null, "code_len": 2662}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 3593, "started": 1791529862.8445885}
{"ep": "h1-00716", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5687, "speedup": 0.5687, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 159.0, "calls": 2, "tokens_in": 14921, "tokens_out": 14893, "ctx_chars": 6513, "t_end": 1791530124.792557, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.5687, "lo95": 0.5674, "mean": 0.5592, "ev_only": 0.5675, "ref_ms": 4.00571, "cand_ms": 7.04328, "n_trials": 205, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4084, "r_wall_s": 18.66, "compile_s": 2.59, "r_error": "", "src_len": 8169, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 10221, "ts": 1791530053.8337488, "chk": "ok", "code_len": 8169}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9838, "tout": 4672, "ts": 1791530106.088326, "chk": null, "code_len": 8169}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791529965.807936}
{"ep": "h1-00730", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9367, "speedup": 0.9367, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 99.1, "calls": 2, "tokens_in": 4258, "tokens_out": 2995, "ctx_chars": 0, "t_end": 1791530127.338461, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9367, "lo95": 0.9362, "mean": 0.9371, "ev_only": 0.934, "ref_ms": 3.70507, "cand_ms": 3.95534, "n_trials": 214, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0171, "r_wall_s": 27.71, "compile_s": 2.43, "r_error": "", "src_len": 1288, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 2142, "ts": 1791530049.4121485, "chk": "ok", "code_len": 1288}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2691, "tout": 853, "ts": 1791530099.5833912, "chk": null, "code_len": 1288}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791530028.256099}
{"ep": "h1-00743", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0121, "speedup": 1.0121, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 67.3, "calls": 2, "tokens_in": 4351, "tokens_out": 2018, "ctx_chars": 0, "t_end": 1791530150.9576957, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0121, "lo95": 1.0114, "mean": 1.0571, "ev_only": 1.0122, "ref_ms": 15.91843, "cand_ms": 15.72808, "n_trials": 73, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 38.44, "compile_s": 1.88, "r_error": "", "src_len": 1089, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1671, "tout": 1374, "ts": 1791530096.051343, "chk": "ok", "code_len": 1089}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2680, "tout": 644, "ts": 1791530112.2533114, "chk": null, "code_len": 1089}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1671, "started": 1791530083.6984372}
{"ep": "h1-00711", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.1581, "speedup": 4.1581, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 210.2, "calls": 2, "tokens_in": 18499, "tokens_out": 9347, "ctx_chars": 12352, "t_end": 1791530153.5960135, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.1581, "lo95": 4.1557, "mean": 4.151, "ev_only": 4.1671, "ref_ms": 27.88593, "cand_ms": 6.70635, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0847, "r_wall_s": 22.59, "compile_s": 2.11, "r_error": "", "src_len": 6169, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7394, "tout": 6119, "ts": 1791529995.4066005, "chk": "ok", "code_len": 6169}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11105, "tout": 3228, "ts": 1791530130.853439, "chk": null, "code_len": 6169}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7394, "started": 1791529943.4296067}
{"ep": "h1-00718", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5975, "speedup": 1.5975, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.2, "calls": 2, "tokens_in": 4986, "tokens_out": 4291, "ctx_chars": 0, "t_end": 1791530154.1310515, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.5975, "lo95": 1.5946, "mean": 1.5866, "ev_only": 1.5915, "ref_ms": 8.04078, "cand_ms": 5.03341, "n_trials": 179, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 36.22, "compile_s": 2.0, "r_error": "", "src_len": 2435, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 2785, "ts": 1791529990.6126676, "chk": "ok", "code_len": 2527}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3421, "tout": 1506, "ts": 1791530117.827323, "chk": null, "code_len": 2435}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791529966.9113047}
{"ep": "h1-00655", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.3449, "speedup": 2.3449, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 453.5, "calls": 2, "tokens_in": 6344, "tokens_out": 8664, "ctx_chars": 0, "t_end": 1791530157.9823103, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.3449, "lo95": 2.3414, "mean": 2.3452, "ev_only": 2.351, "ref_ms": 12.89622, "cand_ms": 5.4997, "n_trials": 115, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 56.19, "compile_s": 13.64, "r_error": "", "src_len": 5234, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1657, "tout": 6088, "ts": 1791529757.5158973, "chk": "ok", "code_len": 5234}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4687, "tout": 2576, "ts": 1791530101.7481227, "chk": null, "code_len": 5234}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1657, "started": 1791529704.4855888}
{"ep": "h1-00643", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.0472, "speedup": 2.0472, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 554.3, "calls": 3, "tokens_in": 19846, "tokens_out": 14903, "ctx_chars": 0, "t_end": 1791530165.0659714, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.0472, "lo95": 2.0393, "mean": 2.0557, "ev_only": 2.0629, "ref_ms": 4.02084, "cand_ms": 1.96409, "n_trials": 165, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4986, "r_wall_s": 94.42, "compile_s": 16.87, "r_error": "", "src_len": 6717, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 7756, "ts": 1791529674.9246392, "chk": "no_custom_kernel", "code_len": 6767}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6768, "tout": 3680, "ts": 1791529730.1489036, "chk": "ok", "code_len": 6717}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10385, "tout": 3467, "ts": 1791530070.3838818, "chk": null, "code_len": 6717}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2693, "started": 1791529610.7242963}
{"ep": "h1-00737", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3786, "speedup": 1.3786, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 111.8, "calls": 2, "tokens_in": 8523, "tokens_out": 6122, "ctx_chars": 0, "t_end": 1791530167.3099358, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.3786, "lo95": 1.3764, "mean": 1.3778, "ev_only": 1.3793, "ref_ms": 75.43522, "cand_ms": 54.71838, "n_trials": 18, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.039, "r_wall_s": 52.23, "compile_s": 2.03, "r_error": "", "src_len": 3500, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 4176, "ts": 1791530090.2506263, "chk": "ok", "code_len": 3500}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5502, "tout": 1946, "ts": 1791530114.537882, "chk": null, "code_len": 3500}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791530055.5434303}
{"ep": "h1-00657", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9812, "speedup": 0.9812, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 458.1, "calls": 2, "tokens_in": 16663, "tokens_out": 5771, "ctx_chars": 13278, "t_end": 1791530169.9197013, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9812, "lo95": 0.9803, "mean": 0.9975, "ev_only": 0.9792, "ref_ms": 5.29108, "cand_ms": 5.39227, "n_trials": 193, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9989, "r_wall_s": 89.32, "compile_s": 2.8, "r_error": "", "src_len": 3286, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 3952, "ts": 1791529748.1571643, "chk": "ok", "code_len": 3286}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9501, "tout": 1819, "ts": 1791530080.111874, "chk": null, "code_len": 3286}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791529711.833639}
{"ep": "h1-00705", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.909, "speedup": 1.909, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 259.1, "calls": 2, "tokens_in": 15962, "tokens_out": 6911, "ctx_chars": 11535, "t_end": 1791530172.22061, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.909, "lo95": 1.9078, "mean": 1.9075, "ev_only": 1.9092, "ref_ms": 20.00415, "cand_ms": 10.47903, "n_trials": 72, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9958, "r_wall_s": 108.19, "compile_s": 1.86, "r_error": "", "src_len": 3364, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6867, "tout": 5198, "ts": 1791529960.9525447, "chk": "ok", "code_len": 3364}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9095, "tout": 1713, "ts": 1791530063.9192455, "chk": null, "code_len": 3364}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6867, "started": 1791529913.1648788}
{"ep": "h1-00723", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2733, "speedup": 1.2733, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 191.7, "calls": 2, "tokens_in": 9221, "tokens_out": 10320, "ctx_chars": 0, "t_end": 1791530175.1212397, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2733, "lo95": 1.2711, "mean": 1.2663, "ev_only": 1.2827, "ref_ms": 4.06122, "cand_ms": 3.18945, "n_trials": 213, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1889, "r_wall_s": 77.55, "compile_s": 13.92, "r_error": "", "src_len": 7020, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 7034, "ts": 1791530045.3525612, "chk": "ok", "code_len": 7020}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6528, "tout": 3286, "ts": 1791530097.2130575, "chk": null, "code_len": 7020}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791529983.3733163}
{"ep": "h1-00690", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9254, "speedup": 1.9254, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 334.2, "calls": 2, "tokens_in": 14684, "tokens_out": 4238, "ctx_chars": 10743, "t_end": 1791530188.3318598, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.9254, "lo95": 1.9226, "mean": 1.9241, "ev_only": 1.9256, "ref_ms": 19.47969, "cand_ms": 10.11734, "n_trials": 88, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1708, "r_wall_s": 192.9, "compile_s": 3.04, "r_error": "", "src_len": 2412, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6466, "tout": 2969, "ts": 1791529881.194317, "chk": "ok", "code_len": 2412}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8218, "tout": 1269, "ts": 1791529995.0743845, "chk": null, "code_len": 2412}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6466, "started": 1791529854.1453779}
{"ep": "h1-00618", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 15.2478, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 684.5, "calls": 4, "tokens_in": 19757, "tokens_out": 19720, "ctx_chars": 0, "t_end": 1791530194.872071, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 15.2478, "lo95": 12.3666, "mean": 10.5972, "ev_only": 15.6853, "ref_ms": 8.01981, "cand_ms": 0.52596, "n_trials": 127, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "mixed", "own_frac": 0.9287, "r_wall_s": 67.0, "compile_s": 11.88, "r_error": "", "src_len": 5977, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1783, "tout": 2651, "ts": 1791529533.9667835, "chk": "incorrect", "code_len": 2535}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3565, "tout": 3363, "ts": 1791529907.2109184, "chk": "incorrect", "code_len": 2595}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5370, "tout": 9852, "ts": 1791530007.9388106, "chk": "ok", "code_len": 5977}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9039, "tout": 3854, "ts": 1791530127.846172, "chk": null, "code_len": 5977}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1783, "started": 1791529510.400819}
{"ep": "h1-00684", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5957, "speedup": 1.5957, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 361.9, "calls": 2, "tokens_in": 5538, "tokens_out": 4792, "ctx_chars": 0, "t_end": 1791530195.2255876, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.5957, "lo95": 1.5947, "mean": 1.5938, "ev_only": 1.5954, "ref_ms": 30.29258, "cand_ms": 18.98443, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 145.97, "compile_s": 1.9, "r_error": "", "src_len": 2808, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1696, "tout": 3177, "ts": 1791529861.9389932, "chk": "ok", "code_len": 2808}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3842, "tout": 1615, "ts": 1791530048.4186723, "chk": null, "code_len": 2808}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1696, "started": 1791529833.282558}
{"ep": "h1-00727", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.1115, "speedup": 3.1115, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 200.1, "calls": 2, "tokens_in": 7682, "tokens_out": 7971, "ctx_chars": 0, "t_end": 1791530196.3779304, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 3.1115, "lo95": 3.1075, "mean": 2.9575, "ev_only": 3.1457, "ref_ms": 2.92943, "cand_ms": 0.94149, "n_trials": 174, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 87.68, "compile_s": 13.31, "r_error": "", "src_len": 6544, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1921, "tout": 4742, "ts": 1791530034.1172864, "chk": "ok", "code_len": 6648}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5761, "tout": 3229, "ts": 1791530107.8248315, "chk": null, "code_len": 6544}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1921, "started": 1791529996.2645814}
{"ep": "h1-00670", "task": "L2_082", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9205, "speedup": 1.9205, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 456.9, "calls": 2, "tokens_in": 14070, "tokens_out": 2032, "ctx_chars": 10743, "t_end": 1791530206.0212865, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.9205, "lo95": 1.9189, "mean": 1.9236, "ev_only": 1.9295, "ref_ms": 19.51622, "cand_ms": 10.1618, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0838, "r_wall_s": 158.43, "compile_s": 1.9, "r_error": "", "src_len": 2039, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6464, "tout": 1033, "ts": 1791529759.1696484, "chk": "ok", "code_len": 2039}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7606, "tout": 999, "ts": 1791530047.2405038, "chk": null, "code_len": 2039}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6464, "started": 1791529749.1387243}
{"ep": "h1-00741", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4046, "speedup": 1.4046, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 128.2, "calls": 2, "tokens_in": 5281, "tokens_out": 4804, "ctx_chars": 0, "t_end": 1791530208.7742429, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4046, "lo95": 1.4022, "mean": 1.4009, "ev_only": 1.4064, "ref_ms": 8.08181, "cand_ms": 5.75376, "n_trials": 108, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 70.78, "compile_s": 2.14, "r_error": "", "src_len": 2706, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1588, "tout": 3228, "ts": 1791530107.5979724, "chk": "ok", "code_len": 2706}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3693, "tout": 1576, "ts": 1791530137.9001138, "chk": null, "code_len": 2706}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1588, "started": 1791530080.5782747}
{"ep": "h1-00668", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 19.0722, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 475.4, "calls": 2, "tokens_in": 6519, "tokens_out": 6794, "ctx_chars": 0, "t_end": 1791530209.774076, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 19.0722, "lo95": 18.9868, "mean": 14.8664, "ev_only": 19.7173, "ref_ms": 25.19574, "cand_ms": 1.32107, "n_trials": 63, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 145.35, "compile_s": 17.46, "r_error": "", "src_len": 4701, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1755, "tout": 4379, "ts": 1791529771.7713795, "chk": "ok", "code_len": 4701}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4764, "tout": 2415, "ts": 1791530064.2648592, "chk": null, "code_len": 4701}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1755, "started": 1791529734.4207814}
{"ep": "h1-00709", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 14.7815, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 289.1, "calls": 2, "tokens_in": 6538, "tokens_out": 7122, "ctx_chars": 0, "t_end": 1791530214.5214636, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 14.7815, "lo95": 14.7095, "mean": 14.2885, "ev_only": 14.6816, "ref_ms": 10.25354, "cand_ms": 0.69367, "n_trials": 134, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 202.86, "compile_s": 15.97, "r_error": "", "src_len": 5652, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1642, "tout": 4385, "ts": 1791529961.0526843, "chk": "ok", "code_len": 5652}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4896, "tout": 2737, "ts": 1791530011.1322763, "chk": null, "code_len": 5652}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1642, "started": 1791529925.4181373}
{"ep": "h1-00702", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2206, "speedup": 1.2206, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 310.7, "calls": 2, "tokens_in": 16719, "tokens_out": 6988, "ctx_chars": 11582, "t_end": 1791530215.0291996, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2206, "lo95": 1.219, "mean": 1.2209, "ev_only": 1.2211, "ref_ms": 35.50656, "cand_ms": 29.08841, "n_trials": 34, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 190.18, "compile_s": 2.56, "r_error": "", "src_len": 3443, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7119, "tout": 5199, "ts": 1791529971.4892673, "chk": "ok", "code_len": 3443}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9600, "tout": 1789, "ts": 1791530023.7902439, "chk": null, "code_len": 3443}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7119, "started": 1791529924.6690526}
{"ep": "h1-00726", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.173, "speedup": 2.173, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 230.5, "calls": 2, "tokens_in": 12651, "tokens_out": 1704, "ctx_chars": 9855, "t_end": 1791530222.7008035, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.173, "lo95": 2.1712, "mean": 2.175, "ev_only": 2.1736, "ref_ms": 6.28488, "cand_ms": 2.89222, "n_trials": 122, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2725, "r_wall_s": 152.28, "compile_s": 1.94, "r_error": "", "src_len": 906, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 1184, "ts": 1791530003.4264545, "chk": "ok", "code_len": 906}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6805, "tout": 520, "ts": 1791530069.5705543, "chk": null, "code_len": 906}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791529992.2424684}
{"ep": "h1-00738", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3466, "speedup": 1.3466, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.6, "calls": 2, "tokens_in": 14943, "tokens_out": 4344, "ctx_chars": 11132, "t_end": 1791530224.734664, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.3466, "lo95": 1.3451, "mean": 1.3486, "ev_only": 1.3483, "ref_ms": 11.05487, "cand_ms": 8.2096, "n_trials": 131, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1808, "r_wall_s": 81.5, "compile_s": 2.09, "r_error": "", "src_len": 3298, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6456, "tout": 2738, "ts": 1791530082.5838232, "chk": "ok", "code_len": 3298}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8487, "tout": 1606, "ts": 1791530142.461683, "chk": null, "code_len": 3298}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6456, "started": 1791530060.08652}
{"ep": "h1-00761", "task": "L3_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "no_custom_kernel", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 58.2, "calls": 1, "tokens_in": 3022, "tokens_out": 2202, "ctx_chars": 0, "t_end": 1791530228.155875, "error": "none of the candidate's kernels ['bn_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "f_status": "no_custom_kernel", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.0, "r_wall_s": 39.59, "compile_s": 2.03, "r_error": "none of the candidate's kernels ['bn_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "src_len": 4812, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3022, "tout": 2202, "ts": 1791530188.5392673, "chk": null, "code_len": 4812}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3022, "started": 1791530169.919984}
{"ep": "h1-00656", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4604, "speedup": 1.4604, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 520.6, "calls": 2, "tokens_in": 5201, "tokens_out": 5622, "ctx_chars": 0, "t_end": 1791530229.7158792, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4604, "lo95": 1.4593, "mean": 1.4581, "ev_only": 1.4604, "ref_ms": 16.03259, "cand_ms": 10.97801, "n_trials": 77, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 156.38, "compile_s": 2.7, "r_error": "", "src_len": 2258, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1690, "tout": 4349, "ts": 1791529749.9339232, "chk": "ok", "code_len": 2258}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3511, "tout": 1273, "ts": 1791530073.2239711, "chk": null, "code_len": 2258}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1690, "started": 1791529709.153395}
{"ep": "h1-00713", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0011, "speedup": 1.0011, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 274.6, "calls": 2, "tokens_in": 12786, "tokens_out": 1863, "ctx_chars": 9898, "t_end": 1791530230.6737387, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0011, "lo95": 1.0007, "mean": 1.001, "ev_only": 1.0004, "ref_ms": 16.11406, "cand_ms": 16.09571, "n_trials": 75, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0011, "r_wall_s": 226.71, "compile_s": 4.19, "r_error": "", "src_len": 996, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5911, "tout": 1243, "ts": 1791529967.319293, "chk": "ok", "code_len": 996}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6875, "tout": 620, "ts": 1791530003.93824, "chk": null, "code_len": 996}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5911, "started": 1791529956.037491}
{"ep": "h1-00715", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.0564, "speedup": 2.0564, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 266.6, "calls": 2, "tokens_in": 6758, "tokens_out": 6198, "ctx_chars": 0, "t_end": 1791530231.2465696, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.0564, "lo95": 2.0527, "mean": 2.1584, "ev_only": 2.0434, "ref_ms": 2.37685, "cand_ms": 1.15586, "n_trials": 220, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 107.36, "compile_s": 13.2, "r_error": "", "src_len": 5080, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1921, "tout": 3752, "ts": 1791530016.3176913, "chk": "ok", "code_len": 5080}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4837, "tout": 2446, "ts": 1791530122.9786022, "chk": null, "code_len": 5080}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1921, "started": 1791529984.9883792}
{"ep": "h1-00649", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6284, "speedup": 0.6284, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 570.7, "calls": 2, "tokens_in": 15083, "tokens_out": 15332, "ctx_chars": 6513, "t_end": 1791530231.8169892, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6284, "lo95": 0.6273, "mean": 0.629, "ev_only": 0.6297, "ref_ms": 3.81625, "cand_ms": 6.07298, "n_trials": 145, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3358, "r_wall_s": 160.48, "compile_s": 2.17, "r_error": "", "src_len": 8239, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 11024, "ts": 1791529755.6977227, "chk": "ok", "code_len": 8239}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10000, "tout": 4308, "ts": 1791530071.2265303, "chk": null, "code_len": 8239}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791529661.0922055}
{"ep": "h1-00731", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 14.2232, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 196.8, "calls": 2, "tokens_in": 6586, "tokens_out": 7588, "ctx_chars": 0, "t_end": 1791530231.8294182, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 14.2232, "lo95": 14.1785, "mean": 14.1114, "ev_only": 14.1507, "ref_ms": 10.17701, "cand_ms": 0.71552, "n_trials": 161, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 110.0, "compile_s": 12.66, "r_error": "", "src_len": 5717, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1642, "tout": 4806, "ts": 1791530075.0627894, "chk": "ok", "code_len": 5717}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4944, "tout": 2782, "ts": 1791530121.124644, "chk": null, "code_len": 5717}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1642, "started": 1791530035.0044403}
{"ep": "h1-00671", "task": "L3_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9998, "speedup": 0.9998, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 483.2, "calls": 4, "tokens_in": 23925, "tokens_out": 6711, "ctx_chars": 0, "t_end": 1791530234.9015641, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9998, "lo95": 0.9994, "mean": 0.9996, "ev_only": 1.0002, "ref_ms": 8.32616, "cand_ms": 8.32751, "n_trials": 154, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0012, "r_wall_s": 152.82, "compile_s": 14.91, "r_error": "", "src_len": 2814, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2190, "tout": 2008, "ts": 1791529770.235689, "chk": "compile_error", "code_len": 4090}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5411, "tout": 1845, "ts": 1791529854.9983902, "chk": "incorrect", "code_len": 4074}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7387, "tout": 1438, "ts": 1791529913.8362024, "chk": "ok", "code_len": 2814}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8937, "tout": 1420, "ts": 1791530081.9655097, "chk": null, "code_len": 2814}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "incorrect", "ok", null], "first_tin": 2190, "started": 1791529751.6565504}
{"ep": "h1-00742", "task": "L1_083", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.3227, "speedup": 2.3227, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 157.5, "calls": 3, "tokens_in": 22220, "tokens_out": 2657, "ctx_chars": 10362, "t_end": 1791530239.1530576, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.3227, "lo95": 2.3075, "mean": 2.443, "ev_only": 2.3497, "ref_ms": 2.45322, "cand_ms": 1.0562, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 115.09, "compile_s": 2.34, "r_error": "", "src_len": 2651, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6377, "tout": 1417, "ts": 1791530094.8360167, "chk": "ok", "code_len": 2651}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7903, "tout": 13, "ts": 1791530112.9210358, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7940, "tout": 1227, "ts": 1791530123.09885, "chk": null, "code_len": 2651}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6377, "started": 1791530081.6378403}
{"ep": "h1-00659", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.2512, "speedup": 3.2512, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 527.5, "calls": 3, "tokens_in": 28530, "tokens_out": 9590, "ctx_chars": 11582, "t_end": 1791530242.711849, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.2512, "lo95": 3.2454, "mean": 3.3874, "ev_only": 3.2548, "ref_ms": 35.53574, "cand_ms": 10.92996, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9992, "r_wall_s": 171.01, "compile_s": 4.69, "r_error": "", "src_len": 3516, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7119, "tout": 5277, "ts": 1791529763.4291172, "chk": "runtime_error", "code_len": 3549}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9657, "tout": 2420, "ts": 1791530035.3076713, "chk": "ok", "code_len": 3516}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11754, "tout": 1893, "ts": 1791530070.6225479, "chk": null, "code_len": 3516}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 7119, "started": 1791529715.2526233}
{"ep": "h1-00714", "task": "L2_051", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 35.7328, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 289.7, "calls": 1, "tokens_in": 1706, "tokens_out": 3081, "ctx_chars": 0, "t_end": 1791530251.21956, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 35.7328, "lo95": 35.0831, "mean": 33.7827, "ev_only": 35.8489, "ref_ms": 16.09457, "cand_ms": 0.45041, "n_trials": 71, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.2901, "r_wall_s": 261.52, "compile_s": 17.11, "r_error": "", "src_len": 1832, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1706, "tout": 3081, "ts": 1791529989.4991736, "chk": null, "code_len": 1832}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1706, "started": 1791529961.541364}
{"ep": "h1-00721", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.9339, "speedup": 4.9339, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 271.4, "calls": 3, "tokens_in": 21939, "tokens_out": 22297, "ctx_chars": 0, "t_end": 1791530252.8655734, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.9339, "lo95": 4.9107, "mean": 4.983, "ev_only": 4.9824, "ref_ms": 2.29509, "cand_ms": 0.46517, "n_trials": 218, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 57.43, "compile_s": 20.17, "r_error": "", "src_len": 9841, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 12339, "ts": 1791530089.0616226, "chk": "no_custom_kernel", "code_len": 10108}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7452, "tout": 5067, "ts": 1791530138.8602104, "chk": "ok", "code_len": 9841}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12472, "tout": 4891, "ts": 1791530195.414565, "chk": null, "code_len": 9841}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2015, "started": 1791529981.4389288}
{"ep": "h1-00725", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6539, "speedup": 0.6539, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 275.8, "calls": 2, "tokens_in": 5040, "tokens_out": 4649, "ctx_chars": 0, "t_end": 1791530262.6211755, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.6539, "lo95": 0.6534, "mean": 0.6543, "ev_only": 0.6552, "ref_ms": 7.34317, "cand_ms": 11.23029, "n_trials": 129, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 110.41, "compile_s": 2.79, "r_error": "", "src_len": 2584, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 2923, "ts": 1791530012.7609293, "chk": "ok", "code_len": 2584}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3476, "tout": 1726, "ts": 1791530152.1265137, "chk": null, "code_len": 2584}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791529986.812935}
{"ep": "h1-00757", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4285, "speedup": 1.4285, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 110.8, "calls": 2, "tokens_in": 4911, "tokens_out": 4453, "ctx_chars": 0, "t_end": 1791530264.9103467, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4285, "lo95": 1.4275, "mean": 1.4447, "ev_only": 1.4272, "ref_ms": 7.29702, "cand_ms": 5.10811, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 34.43, "compile_s": 2.54, "r_error": "", "src_len": 2152, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1572, "tout": 2953, "ts": 1791530181.3194532, "chk": "ok", "code_len": 2152}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3339, "tout": 1500, "ts": 1791530230.3325865, "chk": null, "code_len": 2152}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1572, "started": 1791530154.1313996}
{"ep": "h1-00750", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0058, "speedup": 1.0058, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 145.3, "calls": 2, "tokens_in": 13432, "tokens_out": 1483, "ctx_chars": 10823, "t_end": 1791530266.1951623, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0058, "lo95": 1.0033, "mean": 1.0059, "ev_only": 1.0052, "ref_ms": 8.05903, "cand_ms": 8.01266, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 117.84, "compile_s": 3.44, "r_error": "", "src_len": 897, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6277, "tout": 960, "ts": 1791530129.3772418, "chk": "ok", "code_len": 897}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7155, "tout": 523, "ts": 1791530148.2775981, "chk": null, "code_len": 897}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6277, "started": 1791530120.892639}
{"ep": "h1-00765", "task": "L3_029", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6493, "speedup": 0.6493, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 78.4, "calls": 1, "tokens_in": 7616, "tokens_out": 5124, "ctx_chars": 0, "t_end": 1791530273.303603, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.6493, "lo95": 0.585, "mean": 0.6836, "ev_only": 0.6486, "ref_ms": 11.57813, "cand_ms": 17.83075, "n_trials": 122, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0451, "r_wall_s": 37.73, "compile_s": 2.06, "r_error": "", "src_len": 11854, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7616, "tout": 5124, "ts": 1791530235.5302348, "chk": null, "code_len": 11854}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7616, "started": 1791530194.872454}
{"ep": "h1-00759", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0892, "speedup": 1.0892, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 109.4, "calls": 2, "tokens_in": 4997, "tokens_out": 3952, "ctx_chars": 0, "t_end": 1791530274.436253, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0892, "lo95": 1.0789, "mean": 1.1025, "ev_only": 1.1067, "ref_ms": 2.90872, "cand_ms": 2.67055, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 46.66, "compile_s": 2.12, "r_error": "", "src_len": 2310, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 2659, "ts": 1791530188.38356, "chk": "ok", "code_len": 2310}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3408, "tout": 1293, "ts": 1791530227.663063, "chk": null, "code_len": 2310}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791530165.066314}
{"ep": "h1-00700", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.6267, "speedup": 2.6267, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 385.3, "calls": 2, "tokens_in": 6817, "tokens_out": 6598, "ctx_chars": 0, "t_end": 1791530275.586388, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.6267, "lo95": 2.6222, "mean": 2.7306, "ev_only": 2.6156, "ref_ms": 2.36821, "cand_ms": 0.9016, "n_trials": 205, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 269.12, "compile_s": 18.23, "r_error": "", "src_len": 5570, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1921, "tout": 3852, "ts": 1791529921.9669437, "chk": "ok", "code_len": 5570}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4896, "tout": 2746, "ts": 1791530005.6622384, "chk": null, "code_len": 5570}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1921, "started": 1791529890.2663863}
{"ep": "h1-00749", "task": "L2_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3396, "speedup": 1.3396, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 166.5, "calls": 3, "tokens_in": 23928, "tokens_out": 2896, "ctx_chars": 11357, "t_end": 1791530280.10551, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3396, "lo95": 1.3392, "mean": 1.3394, "ev_only": 1.3373, "ref_ms": 7.4955, "cand_ms": 5.59539, "n_trials": 215, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0947, "r_wall_s": 86.36, "compile_s": 2.18, "r_error": "", "src_len": 2333, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6779, "tout": 1659, "ts": 1791530129.5245028, "chk": "ok", "code_len": 2333}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8550, "tout": 25, "ts": 1791530182.9999416, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8599, "tout": 1212, "ts": 1791530193.3576717, "chk": null, "code_len": 2333}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6779, "started": 1791530113.5968401}
{"ep": "h1-00752", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.3584, "speedup": 0.3584, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.7, "calls": 2, "tokens_in": 9157, "tokens_out": 8456, "ctx_chars": 0, "t_end": 1791530280.4045968, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.3584, "lo95": 0.3567, "mean": 0.3581, "ev_only": 0.3583, "ref_ms": 75.33903, "cand_ms": 210.1912, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.7583, "r_wall_s": 41.46, "compile_s": 2.2, "r_error": "", "src_len": 4783, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 5851, "ts": 1791530171.5912032, "chk": "ok", "code_len": 4783}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6136, "tout": 2605, "ts": 1791530238.584629, "chk": null, "code_len": 4783}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791530121.7394285}
{"ep": "h1-00698", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.4026, "speedup": 4.4026, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 392.4, "calls": 3, "tokens_in": 10127, "tokens_out": 6599, "ctx_chars": 0, "t_end": 1791530280.8022907, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.4026, "lo95": 4.3985, "mean": 4.4021, "ev_only": 4.4032, "ref_ms": 16.12131, "cand_ms": 3.66175, "n_trials": 78, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9995, "r_wall_s": 266.82, "compile_s": 3.32, "r_error": "", "src_len": 2300, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1574, "tout": 3419, "ts": 1791529920.2444897, "chk": "incorrect", "code_len": 2269}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3486, "tout": 1832, "ts": 1791529968.016858, "chk": "ok", "code_len": 2300}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5067, "tout": 1348, "ts": 1791530013.9562585, "chk": null, "code_len": 2300}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1574, "started": 1791529888.4468038}
{"ep": "h1-00683", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.4942, "speedup": 2.4942, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 455.5, "calls": 2, "tokens_in": 6409, "tokens_out": 9727, "ctx_chars": 0, "t_end": 1791530287.0564854, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.4942, "lo95": 2.4914, "mean": 2.4896, "ev_only": 2.4937, "ref_ms": 12.88747, "cand_ms": 5.16691, "n_trials": 102, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 287.59, "compile_s": 19.11, "r_error": "", "src_len": 5055, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1657, "tout": 7263, "ts": 1791529896.8324692, "chk": "ok", "code_len": 5055}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4752, "tout": 2464, "ts": 1791529999.4385254, "chk": null, "code_len": 5055}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1657, "started": 1791529831.5163252}
{"ep": "h1-00747", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2601, "speedup": 1.2601, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 183.5, "calls": 2, "tokens_in": 13777, "tokens_out": 2045, "ctx_chars": 11132, "t_end": 1791530291.3999853, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2601, "lo95": 1.2596, "mean": 1.2594, "ev_only": 1.256, "ref_ms": 3.63841, "cand_ms": 2.88749, "n_trials": 236, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4128, "r_wall_s": 143.23, "compile_s": 2.98, "r_error": "", "src_len": 961, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 1463, "ts": 1791530121.528231, "chk": "ok", "code_len": 961}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7351, "tout": 582, "ts": 1791530147.3148432, "chk": null, "code_len": 961}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6426, "started": 1791530107.85737}
{"ep": "h1-00696", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.477, "speedup": 1.477, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 408.4, "calls": 2, "tokens_in": 8259, "tokens_out": 8600, "ctx_chars": 0, "t_end": 1791530292.547698, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.477, "lo95": 1.4763, "mean": 1.4553, "ev_only": 1.4738, "ref_ms": 3.64753, "cand_ms": 2.46957, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1012, "r_wall_s": 299.62, "compile_s": 2.66, "r_error": "", "src_len": 4593, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 6287, "ts": 1791529940.8178573, "chk": "ok", "code_len": 4647}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5566, "tout": 2313, "ts": 1791529992.6920536, "chk": null, "code_len": 4593}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791529884.1426947}
{"ep": "h1-00736", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2689, "speedup": 1.2689, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 238.8, "calls": 2, "tokens_in": 5169, "tokens_out": 3735, "ctx_chars": 0, "t_end": 1791530292.9648046, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2689, "lo95": 1.266, "mean": 1.2694, "ev_only": 1.2721, "ref_ms": 17.57443, "cand_ms": 13.85064, "n_trials": 84, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0729, "r_wall_s": 153.69, "compile_s": 15.01, "r_error": "", "src_len": 2869, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1693, "tout": 2317, "ts": 1791530073.5361016, "chk": "ok", "code_len": 2869}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3476, "tout": 1418, "ts": 1791530138.8168519, "chk": null, "code_len": 2869}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1693, "started": 1791530054.1771135}
{"ep": "h1-00779", "task": "L2_020", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 64.4, "calls": 1, "tokens_in": 1749, "tokens_out": 1110, "ctx_chars": 0, "t_end": 1791530296.22298, "error": "RuntimeError: Error building extension 'fuse_l2020': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_l2020 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 53.78, "compile_s": 53.77, "r_error": "RuntimeError: Error building extension 'fuse_l2020': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_l2020 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "src_len": 2197, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1749, "tout": 1110, "ts": 1791530242.3953218, "chk": null, "code_len": 2197}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1749, "started": 1791530231.8172264}
{"ep": "h1-00745", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6146, "speedup": 0.6146, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.1, "calls": 2, "tokens_in": 10753, "tokens_out": 11655, "ctx_chars": 0, "t_end": 1791530301.206606, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.6146, "lo95": 0.612, "mean": 0.5918, "ev_only": 0.6147, "ref_ms": 15.82395, "cand_ms": 25.74726, "n_trials": 57, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0445, "r_wall_s": 108.25, "compile_s": 2.22, "r_error": "", "src_len": 8684, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 7535, "ts": 1791530148.3430705, "chk": "ok", "code_len": 8776}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7729, "tout": 4120, "ts": 1791530192.930692, "chk": null, "code_len": 8684}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791530086.1441312}
{"ep": "h1-00697", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0332, "speedup": 1.0332, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 423.5, "calls": 2, "tokens_in": 11697, "tokens_out": 16150, "ctx_chars": 0, "t_end": 1791530308.825146, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0332, "lo95": 1.0311, "mean": 1.024, "ev_only": 1.0332, "ref_ms": 38.6272, "cand_ms": 37.38756, "n_trials": 37, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0605, "r_wall_s": 16.79, "compile_s": 1.94, "r_error": "", "src_len": 10107, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 11264, "ts": 1791529982.0203125, "chk": "ok", "code_len": 10185}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8673, "tout": 4886, "ts": 1791530158.363392, "chk": null, "code_len": 10107}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791529885.3376951}
{"ep": "h1-00706", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6172, "speedup": 1.6172, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 391.9, "calls": 2, "tokens_in": 16803, "tokens_out": 5094, "ctx_chars": 11886, "t_end": 1791530309.6242645, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.6172, "lo95": 1.6162, "mean": 1.6175, "ev_only": 1.6222, "ref_ms": 4.74507, "cand_ms": 2.93407, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2429, "r_wall_s": 322.04, "compile_s": 2.54, "r_error": "", "src_len": 3465, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7269, "tout": 3227, "ts": 1791529945.5615911, "chk": "ok", "code_len": 3465}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9534, "tout": 1867, "ts": 1791529987.507348, "chk": null, "code_len": 3465}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7269, "started": 1791529917.7585106}
{"ep": "h1-00728", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7269, "speedup": 0.7269, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 304.0, "calls": 2, "tokens_in": 15157, "tokens_out": 2517, "ctx_chars": 11175, "t_end": 1791530310.9935129, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7269, "lo95": 0.7259, "mean": 0.7271, "ev_only": 0.7269, "ref_ms": 3.27618, "cand_ms": 4.50707, "n_trials": 210, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0007, "r_wall_s": 94.65, "compile_s": 1.93, "r_error": "", "src_len": 2249, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6880, "tout": 1494, "ts": 1791530019.8664305, "chk": "ok", "code_len": 2249}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8277, "tout": 1023, "ts": 1791530215.507053, "chk": null, "code_len": 2249}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6880, "started": 1791530007.0077546}
{"ep": "h1-00708", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2261, "speedup": 1.2261, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 393.8, "calls": 2, "tokens_in": 11975, "tokens_out": 7425, "ctx_chars": 6513, "t_end": 1791530312.3250856, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2261, "lo95": 1.2249, "mean": 1.2249, "ev_only": 1.2279, "ref_ms": 5.25067, "cand_ms": 4.28245, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0306, "r_wall_s": 321.22, "compile_s": 2.79, "r_error": "", "src_len": 4141, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4677, "tout": 5389, "ts": 1791529967.6450415, "chk": "ok", "code_len": 4141}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7298, "tout": 2036, "ts": 1791529990.8871188, "chk": null, "code_len": 4141}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4677, "started": 1791529918.5410674}
{"ep": "h1-00754", "task": "L2_056", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9986, "speedup": 0.9986, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 185.7, "calls": 1, "tokens_in": 1572, "tokens_out": 971, "ctx_chars": 0, "t_end": 1791530312.9971104, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9986, "lo95": 0.9983, "mean": 0.999, "ev_only": 0.9975, "ref_ms": 16.03813, "cand_ms": 16.06062, "n_trials": 109, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0047, "r_wall_s": 176.0, "compile_s": 51.53, "r_error": "", "src_len": 1616, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1572, "tout": 971, "ts": 1791530136.9720418, "chk": null, "code_len": 1616}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1572, "started": 1791530127.3387005}
{"ep": "h1-00729", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7478, "speedup": 0.7478, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 291.3, "calls": 2, "tokens_in": 11910, "tokens_out": 17216, "ctx_chars": 0, "t_end": 1791530317.3513489, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7478, "lo95": 0.745, "mean": 0.7498, "ev_only": 0.7483, "ref_ms": 6.42587, "cand_ms": 8.59264, "n_trials": 148, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.5145, "r_wall_s": 58.2, "compile_s": 2.01, "r_error": "", "src_len": 9065, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3365, "tout": 12488, "ts": 1791530156.1123865, "chk": "ok", "code_len": 9065}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8545, "tout": 4728, "ts": 1791530259.1045003, "chk": null, "code_len": 9065}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3365, "started": 1791530046.4056325}
{"ep": "h1-00739", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 53.4889, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 257.9, "calls": 2, "tokens_in": 7373, "tokens_out": 13204, "ctx_chars": 0, "t_end": 1791530319.643324, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 53.4889, "lo95": 52.342, "mean": 51.3613, "ev_only": 55.0797, "ref_ms": 36.41392, "cand_ms": 0.68077, "n_trials": 37, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.0333, "r_wall_s": 88.5, "compile_s": 15.52, "r_error": "", "src_len": 6602, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1765, "tout": 9861, "ts": 1791530152.412018, "chk": "ok", "code_len": 6602}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5608, "tout": 3343, "ts": 1791530231.05955, "chk": null, "code_len": 6602}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1765, "started": 1791530061.7246356}
{"ep": "h1-00622", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7464, "speedup": 1.7464, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 801.0, "calls": 5, "tokens_in": 47614, "tokens_out": 15801, "ctx_chars": 9898, "t_end": 1791530327.874949, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.7464, "lo95": 1.7222, "mean": 1.7561, "ev_only": 1.7569, "ref_ms": 8.05392, "cand_ms": 4.61168, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0507, "r_wall_s": 149.62, "compile_s": 2.23, "r_error": "", "src_len": 2440, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6120, "tout": 2640, "ts": 1791529549.1489818, "chk": "incorrect", "code_len": 2107}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7825, "tout": 2135, "ts": 1791529852.2556958, "chk": "incorrect", "code_len": 2161}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9334, "tout": 5371, "ts": 1791530060.1108313, "chk": "incorrect", "code_len": 2529}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 11226, "tout": 4106, "ts": 1791530133.9981909, "chk": "ok", "code_len": 2640}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13109, "tout": 1549, "ts": 1791530178.212779, "chk": null, "code_len": 2440}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 6120, "started": 1791529526.9112186}
{"ep": "h1-00722", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.099, "speedup": 2.099, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 347.4, "calls": 2, "tokens_in": 8559, "tokens_out": 4130, "ctx_chars": 2425, "t_end": 1791530329.6275318, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.099, "lo95": 2.0925, "mean": 2.0916, "ev_only": 2.098, "ref_ms": 12.6559, "cand_ms": 6.02956, "n_trials": 110, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4797, "r_wall_s": 125.36, "compile_s": 3.61, "r_error": "", "src_len": 2213, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3400, "tout": 2993, "ts": 1791530008.4584222, "chk": "ok", "code_len": 2213}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5159, "tout": 1137, "ts": 1791530204.1613889, "chk": null, "code_len": 2213}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3400, "started": 1791529982.1939676}
{"ep": "h1-00751", "task": "L1_083", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.7236, "speedup": 2.7236, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.5, "calls": 2, "tokens_in": 14265, "tokens_out": 2719, "ctx_chars": 10362, "t_end": 1791530334.9090998, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.7236, "lo95": 2.7156, "mean": 2.5073, "ev_only": 2.7549, "ref_ms": 2.92343, "cand_ms": 1.07338, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 149.26, "compile_s": 2.04, "r_error": "", "src_len": 2844, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6377, "tout": 1402, "ts": 1791530133.5092158, "chk": "ok", "code_len": 2844}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7888, "tout": 1317, "ts": 1791530184.8178837, "chk": null, "code_len": 2844}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6377, "started": 1791530121.41458}
{"ep": "h1-00719", "task": "L3_043", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1379, "speedup": 0.1379, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 366.2, "calls": 4, "tokens_in": 26513, "tokens_out": 6988, "ctx_chars": 2425, "t_end": 1791530337.62152, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.1379, "lo95": 0.1378, "mean": 0.138, "ev_only": 0.1378, "ref_ms": 30.86109, "cand_ms": 223.76159, "n_trials": 13, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.921, "r_wall_s": 66.58, "compile_s": 3.32, "r_error": "", "src_len": 4180, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3322, "tout": 2470, "ts": 1791529994.137145, "chk": "runtime_error", "code_len": 4327}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6128, "tout": 2265, "ts": 1791530211.6202586, "chk": "ok", "code_len": 4180}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8505, "tout": 29, "ts": 1791530252.5400407, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8558, "tout": 2224, "ts": 1791530270.4529703, "chk": null, "code_len": 4180}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 3322, "started": 1791529971.4478145}
{"ep": "h1-00782", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0654, "speedup": 1.0654, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 99.7, "calls": 2, "tokens_in": 14950, "tokens_out": 3701, "ctx_chars": 11062, "t_end": 1791530338.8307922, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0654, "lo95": 1.0647, "mean": 1.0829, "ev_only": 1.0676, "ref_ms": 12.81953, "cand_ms": 12.0329, "n_trials": 110, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0319, "r_wall_s": 49.17, "compile_s": 1.96, "r_error": "", "src_len": 2088, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6695, "tout": 2634, "ts": 1791530263.5379055, "chk": "ok", "code_len": 2088}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8255, "tout": 1067, "ts": 1791530289.546988, "chk": null, "code_len": 2088}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6695, "started": 1791530239.1533015}
{"ep": "h1-00775", "task": "L2_082", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9258, "speedup": 1.9258, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 121.7, "calls": 3, "tokens_in": 21733, "tokens_out": 2068, "ctx_chars": 10743, "t_end": 1791530349.8834457, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.9258, "lo95": 1.9236, "mean": 1.9041, "ev_only": 1.9319, "ref_ms": 19.58153, "cand_ms": 10.16787, "n_trials": 87, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1545, "r_wall_s": 55.25, "compile_s": 2.06, "r_error": "", "src_len": 2056, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6464, "tout": 1043, "ts": 1791530238.3323255, "chk": "ok", "code_len": 2056}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7616, "tout": 13, "ts": 1791530285.5834718, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7653, "tout": 1012, "ts": 1791530294.1655438, "chk": null, "code_len": 2056}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6464, "started": 1791530228.1561317}
{"ep": "h1-00787", "task": "L2_067", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2872, "speedup": 1.2872, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 85.2, "calls": 1, "tokens_in": 1655, "tokens_out": 651, "ctx_chars": 0, "t_end": 1791530350.1499789, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2872, "lo95": 1.2867, "mean": 1.3025, "ev_only": 1.2856, "ref_ms": 12.94309, "cand_ms": 10.05493, "n_trials": 118, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1586, "r_wall_s": 78.65, "compile_s": 3.54, "r_error": "", "src_len": 1186, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1655, "tout": 651, "ts": 1791530271.446013, "chk": null, "code_len": 1186}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1655, "started": 1791530264.910589}
{"ep": "h1-00781", "task": "L1_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 12.4719, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 115.5, "calls": 1, "tokens_in": 1640, "tokens_out": 2386, "ctx_chars": 0, "t_end": 1791530350.358986, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 12.4719, "lo95": 12.3976, "mean": 12.187, "ev_only": 12.451, "ref_ms": 10.20101, "cand_ms": 0.81792, "n_trials": 144, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.9337, "r_wall_s": 93.64, "compile_s": 2.11, "r_error": "", "src_len": 2084, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1640, "tout": 2386, "ts": 1791530256.1794217, "chk": null, "code_len": 2084}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1640, "started": 1791530234.9018123}
{"ep": "h1-00776", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3218, "speedup": 1.3218, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 124.0, "calls": 2, "tokens_in": 13620, "tokens_out": 3097, "ctx_chars": 10210, "t_end": 1791530353.7189784, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3218, "lo95": 1.317, "mean": 1.3269, "ev_only": 1.3227, "ref_ms": 19.32205, "cand_ms": 14.61852, "n_trials": 71, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1281, "r_wall_s": 56.56, "compile_s": 2.42, "r_error": "", "src_len": 1873, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 2096, "ts": 1791530249.4201665, "chk": "ok", "code_len": 1873}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7485, "tout": 1001, "ts": 1791530296.3606093, "chk": null, "code_len": 1873}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791530229.7161267}
{"ep": "h1-00770", "task": "L2_020", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4443, "speedup": 1.4443, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.0, "calls": 1, "tokens_in": 1749, "tokens_out": 2233, "ctx_chars": 0, "t_end": 1791530353.7898269, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4443, "lo95": 1.4426, "mean": 1.4391, "ev_only": 1.4423, "ref_ms": 14.22087, "cand_ms": 9.84602, "n_trials": 107, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.089, "r_wall_s": 123.88, "compile_s": 14.54, "r_error": "", "src_len": 2248, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1749, "tout": 2233, "ts": 1791530229.1141567, "chk": null, "code_len": 2248}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1749, "started": 1791530209.7743387}
{"ep": "h1-00758", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2108, "speedup": 1.2108, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 206.8, "calls": 2, "tokens_in": 7226, "tokens_out": 6224, "ctx_chars": 0, "t_end": 1791530364.7523308, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2108, "lo95": 1.2104, "mean": 1.2121, "ev_only": 1.2131, "ref_ms": 30.96363, "cand_ms": 25.57302, "n_trials": 49, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3542, "r_wall_s": 74.4, "compile_s": 1.92, "r_error": "", "src_len": 3447, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2408, "tout": 4309, "ts": 1791530194.295635, "chk": "ok", "code_len": 3447}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4818, "tout": 1915, "ts": 1791530289.9277818, "chk": null, "code_len": 3447}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2408, "started": 1791530157.9825823}
{"ep": "h1-00720", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0211, "speedup": 1.0211, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 400.9, "calls": 2, "tokens_in": 16842, "tokens_out": 15883, "ctx_chars": 6513, "t_end": 1791530375.2912884, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0211, "lo95": 1.0172, "mean": 1.0115, "ev_only": 1.021, "ref_ms": 38.90405, "cand_ms": 38.10063, "n_trials": 31, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0726, "r_wall_s": 178.38, "compile_s": 3.98, "r_error": "", "src_len": 10463, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 11028, "ts": 1791530069.8395371, "chk": "ok", "code_len": 10463}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11115, "tout": 4855, "ts": 1791530196.84514, "chk": null, "code_len": 10463}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791529974.4199328}
{"ep": "h1-00797", "task": "L3_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 83.3, "calls": 1, "tokens_in": 3022, "tokens_out": 2567, "ctx_chars": 0, "t_end": 1791530375.8184972, "error": "RuntimeError: Error building extension 'bn_relu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bn_relu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 61.7, "compile_s": 61.68, "r_error": "RuntimeError: Error building extension 'bn_relu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bn_relu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "src_len": 5840, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3022, "tout": 2567, "ts": 1791530314.0056248, "chk": null, "code_len": 5840}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3022, "started": 1791530292.5479662}
{"ep": "h1-00772", "task": "L3_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9455, "speedup": 0.9455, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 160.9, "calls": 3, "tokens_in": 15790, "tokens_out": 2211, "ctx_chars": 6513, "t_end": 1791530375.9790099, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9455, "lo95": 0.945, "mean": 0.9458, "ev_only": 0.9456, "ref_ms": 33.68864, "cand_ms": 35.62913, "n_trials": 37, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0012, "r_wall_s": 109.08, "compile_s": 1.93, "r_error": "", "src_len": 2175, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4416, "tout": 1125, "ts": 1791530224.7692063, "chk": "ok", "code_len": 2175}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5653, "tout": 44, "ts": 1791530258.0665565, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5721, "tout": 1042, "ts": 1791530266.8390648, "chk": null, "code_len": 2175}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4416, "started": 1791530215.029449}
{"ep": "h1-00768", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.8949, "speedup": 2.8949, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 170.3, "calls": 2, "tokens_in": 16795, "tokens_out": 7129, "ctx_chars": 10384, "t_end": 1791530376.30995, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.8949, "lo95": 2.8917, "mean": 2.9739, "ev_only": 2.9224, "ref_ms": 3.66293, "cand_ms": 1.26533, "n_trials": 195, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5299, "r_wall_s": 35.99, "compile_s": 1.93, "r_error": "", "src_len": 3121, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 5527, "ts": 1791530257.1964839, "chk": "ok", "code_len": 3121}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9498, "tout": 1602, "ts": 1791530340.0949664, "chk": null, "code_len": 3121}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791530206.0219}
{"ep": "h1-00764", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.0351, "speedup": 4.0351, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.6, "calls": 2, "tokens_in": 4874, "tokens_out": 4682, "ctx_chars": 0, "t_end": 1791530377.8857062, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.0351, "lo95": 4.0285, "mean": 3.9932, "ev_only": 4.0327, "ref_ms": 16.0692, "cand_ms": 3.9824, "n_trials": 77, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9994, "r_wall_s": 123.76, "compile_s": 1.93, "r_error": "", "src_len": 2006, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1574, "tout": 3538, "ts": 1791530222.4633756, "chk": "ok", "code_len": 2006}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3300, "tout": 1144, "ts": 1791530254.0874295, "chk": null, "code_len": 2006}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1574, "started": 1791530188.3321407}
{"ep": "h1-00734", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.2938, "speedup": 4.2938, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 329.6, "calls": 3, "tokens_in": 10520, "tokens_out": 8047, "ctx_chars": 0, "t_end": 1791530378.1295624, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.2938, "lo95": 4.2828, "mean": 4.2283, "ev_only": 4.3071, "ref_ms": 16.06018, "cand_ms": 3.74028, "n_trials": 105, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9934, "r_wall_s": 175.02, "compile_s": 4.11, "r_error": "", "src_len": 2400, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1574, "tout": 4352, "ts": 1791530087.9956758, "chk": "incorrect", "code_len": 2331}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3602, "tout": 1942, "ts": 1791530124.3961408, "chk": "ok", "code_len": 2472}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5344, "tout": 1753, "ts": 1791530203.082891, "chk": null, "code_len": 2400}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1574, "started": 1791530048.5081294}
{"ep": "h1-00733", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 58.9467, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 338.4, "calls": 2, "tokens_in": 7401, "tokens_out": 11006, "ctx_chars": 0, "t_end": 1791530386.8170342, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 58.9467, "lo95": 58.4628, "mean": 56.0121, "ev_only": 60.5732, "ref_ms": 36.42596, "cand_ms": 0.61795, "n_trials": 38, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.0671, "r_wall_s": 21.01, "compile_s": 11.79, "r_error": "", "src_len": 6983, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1765, "tout": 7634, "ts": 1791530117.2423573, "chk": "ok", "code_len": 7039}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5636, "tout": 3372, "ts": 1791530232.7109833, "chk": null, "code_len": 6983}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1765, "started": 1791530048.376315}
{"ep": "h1-00816", "task": "L2_053", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0114, "speedup": 1.0114, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 35.4, "calls": 1, "tokens_in": 6385, "tokens_out": 592, "ctx_chars": 10749, "t_end": 1791530389.1295242, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0114, "lo95": 1.0103, "mean": 1.0523, "ev_only": 1.0121, "ref_ms": 15.90575, "cand_ms": 15.7269, "n_trials": 75, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0056, "r_wall_s": 29.53, "compile_s": 2.08, "r_error": "", "src_len": 1182, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6385, "tout": 592, "ts": 1791530359.3845158, "chk": null, "code_len": 1182}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6385, "started": 1791530353.7192347}
{"ep": "h1-00767", "task": "L3_034", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6194, "speedup": 0.6194, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 194.3, "calls": 3, "tokens_in": 15729, "tokens_out": 1784, "ctx_chars": 6034, "t_end": 1791530390.69923, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6194, "lo95": 0.6141, "mean": 0.6262, "ev_only": 0.619, "ref_ms": 28.74166, "cand_ms": 46.3999, "n_trials": 18, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0819, "r_wall_s": 65.48, "compile_s": 6.46, "r_error": "", "src_len": 1777, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4546, "tout": 915, "ts": 1791530204.5347085, "chk": "ok", "code_len": 1777}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5573, "tout": 13, "ts": 1791530317.9641366, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5610, "tout": 856, "ts": 1791530325.1113925, "chk": null, "code_len": 1777}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4546, "started": 1791530196.3782027}
{"ep": "h1-00756", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2912, "speedup": 1.2912, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.5, "calls": 2, "tokens_in": 4893, "tokens_out": 4192, "ctx_chars": 0, "t_end": 1791530395.0831523, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2912, "lo95": 1.2903, "mean": 1.2903, "ev_only": 1.2929, "ref_ms": 7.32488, "cand_ms": 5.67276, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 25.15, "compile_s": 1.89, "r_error": "", "src_len": 2207, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 2728, "ts": 1791530177.421213, "chk": "ok", "code_len": 2207}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3329, "tout": 1464, "ts": 1791530233.432841, "chk": null, "code_len": 2207}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791530153.5963707}
{"ep": "h1-00748", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2336, "speedup": 1.2336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 290.2, "calls": 2, "tokens_in": 15722, "tokens_out": 2627, "ctx_chars": 12155, "t_end": 1791530401.8887086, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2336, "lo95": 1.2333, "mean": 1.2335, "ev_only": 1.2342, "ref_ms": 11.96525, "cand_ms": 9.6991, "n_trials": 124, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0708, "r_wall_s": 220.84, "compile_s": 2.08, "r_error": "", "src_len": 1589, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7203, "tout": 1770, "ts": 1791530126.9979904, "chk": "ok", "code_len": 1589}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8519, "tout": 857, "ts": 1791530180.1983347, "chk": null, "code_len": 1589}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7203, "started": 1791530111.6668124}
{"ep": "h1-00809", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7904, "speedup": 0.7904, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 76.2, "calls": 2, "tokens_in": 12157, "tokens_out": 2913, "ctx_chars": 9033, "t_end": 1791530405.7998679, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7904, "lo95": 0.7897, "mean": 0.7892, "ev_only": 0.7915, "ref_ms": 3.73437, "cand_ms": 4.72475, "n_trials": 180, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0074, "r_wall_s": 40.57, "compile_s": 2.22, "r_error": "", "src_len": 1134, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 1820, "ts": 1791530346.8042197, "chk": "ok", "code_len": 1134}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6667, "tout": 1093, "ts": 1791530365.2079394, "chk": null, "code_len": 1134}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791530329.6278028}
{"ep": "h1-00814", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.268, "speedup": 1.268, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 55.7, "calls": 2, "tokens_in": 14324, "tokens_out": 3053, "ctx_chars": 10364, "t_end": 1791530405.8228977, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.268, "lo95": 1.2674, "mean": 1.2676, "ev_only": 1.2703, "ref_ms": 5.9066, "cand_ms": 4.65803, "n_trials": 199, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0509, "r_wall_s": 19.45, "compile_s": 2.94, "r_error": "", "src_len": 2197, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6397, "tout": 1920, "ts": 1791530366.8370724, "chk": "ok", "code_len": 2197}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7927, "tout": 1133, "ts": 1791530385.702432, "chk": null, "code_len": 2197}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6397, "started": 1791530350.150205}
{"ep": "h1-00795", "task": "L3_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 127.9, "calls": 1, "tokens_in": 2190, "tokens_out": 2885, "ctx_chars": 0, "t_end": 1791530414.940816, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.0483, "r_wall_s": 102.18, "compile_s": 2.7, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 3333, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2190, "tout": 2885, "ts": 1791530312.645592, "chk": null, "code_len": 3333}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2190, "started": 1791530287.0567408}
{"ep": "h1-00771", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3994, "speedup": 1.3994, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.3, "calls": 2, "tokens_in": 13513, "tokens_out": 2481, "ctx_chars": 10210, "t_end": 1791530433.7981582, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3994, "lo95": 1.3963, "mean": 1.399, "ev_only": 1.4004, "ref_ms": 19.33779, "cand_ms": 13.81866, "n_trials": 71, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0546, "r_wall_s": 82.22, "compile_s": 2.73, "r_error": "", "src_len": 1754, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6135, "tout": 1565, "ts": 1791530248.9655347, "chk": "ok", "code_len": 1754}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7378, "tout": 916, "ts": 1791530350.9050467, "chk": null, "code_len": 1754}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6135, "started": 1791530234.8645296}
{"ep": "h1-00824", "task": "L3_022", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 57.2, "calls": 1, "tokens_in": 3363, "tokens_out": 5356, "ctx_chars": 0, "t_end": 1791530435.3230972, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.0819, "r_wall_s": 13.63, "compile_s": 2.07, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 6086, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3363, "tout": 5356, "ts": 1791530421.6449227, "chk": null, "code_len": 6086}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3363, "started": 1791530378.129819}
{"ep": "h1-00773", "task": "L1_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.2088, "speedup": 0.2088, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.2, "calls": 4, "tokens_in": 41237, "tokens_out": 6835, "ctx_chars": 11175, "t_end": 1791530435.8708196, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.2088, "lo95": 0.2082, "mean": 0.2208, "ev_only": 0.2081, "ref_ms": 4.46138, "cand_ms": 21.36936, "n_trials": 65, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0026, "r_wall_s": 31.65, "compile_s": 2.03, "r_error": "", "src_len": 3766, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7065, "tout": 2461, "ts": 1791530248.268893, "chk": "runtime_error", "code_len": 3973}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9668, "tout": 2410, "ts": 1791530357.6230073, "chk": "ok", "code_len": 3848}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12190, "tout": 100, "ts": 1791530388.8960528, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 12314, "tout": 1864, "ts": 1791530404.0200145, "chk": null, "code_len": 3766}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 7065, "started": 1791530222.701072}
{"ep": "h1-00798", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.4688, "speedup": 2.4688, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 157.8, "calls": 2, "tokens_in": 7945, "tokens_out": 8347, "ctx_chars": 0, "t_end": 1791530450.7324343, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.4688, "lo95": 2.4666, "mean": 2.466, "ev_only": 2.4819, "ref_ms": 4.01118, "cand_ms": 1.62476, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3929, "r_wall_s": 74.18, "compile_s": 2.37, "r_error": "", "src_len": 4028, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 6362, "ts": 1791530349.4164615, "chk": "ok", "code_len": 4028}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5252, "tout": 1985, "ts": 1791530376.2696033, "chk": null, "code_len": 4028}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791530292.965364}
{"ep": "h1-00762", "task": "L2_055", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0007, "speedup": 1.0007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 288.1, "calls": 4, "tokens_in": 16262, "tokens_out": 3181, "ctx_chars": 0, "t_end": 1791530460.2924824, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0007, "lo95": 1.0002, "mean": 1.0226, "ev_only": 0.9998, "ref_ms": 16.14193, "cand_ms": 16.13122, "n_trials": 61, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0024, "r_wall_s": 105.17, "compile_s": 12.02, "r_error": "", "src_len": 2068, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1688, "tout": 1222, "ts": 1791530184.3145864, "chk": "compile_error", "code_len": 2234}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4121, "tout": 953, "ts": 1791530256.8013082, "chk": "ok", "code_len": 2068}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5184, "tout": 61, "ts": 1791530347.0942981, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5269, "tout": 945, "ts": 1791530355.0936399, "chk": null, "code_len": 2068}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1688, "started": 1791530172.2209327}
{"ep": "h1-00800", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0335, "speedup": 1.0335, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.9, "calls": 2, "tokens_in": 4559, "tokens_out": 2746, "ctx_chars": 0, "t_end": 1791530466.1271956, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0335, "lo95": 1.0333, "mean": 1.0338, "ev_only": 1.0357, "ref_ms": 8.24822, "cand_ms": 7.98102, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0057, "r_wall_s": 100.42, "compile_s": 2.48, "r_error": "", "src_len": 1354, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1670, "tout": 1903, "ts": 1791530318.3828962, "chk": "ok", "code_len": 1354}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2889, "tout": 843, "ts": 1791530365.629856, "chk": null, "code_len": 1354}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1670, "started": 1791530301.206875}
{"ep": "h1-00819", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0365, "speedup": 1.0365, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 95.6, "calls": 2, "tokens_in": 12022, "tokens_out": 1483, "ctx_chars": 9028, "t_end": 1791530470.8438792, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0365, "lo95": 1.0346, "mean": 1.037, "ev_only": 1.0346, "ref_ms": 8.26201, "cand_ms": 7.97123, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 36.7, "compile_s": 2.1, "r_error": "", "src_len": 1046, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 834, "ts": 1791530382.7727194, "chk": "ok", "code_len": 1046}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6484, "tout": 649, "ts": 1791530434.0374088, "chk": null, "code_len": 1046}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5538, "started": 1791530375.2915747}
{"ep": "h1-00805", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.1805, "speedup": 5.1805, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.8, "calls": 2, "tokens_in": 4952, "tokens_out": 4796, "ctx_chars": 0, "t_end": 1791530471.753954, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 5.1805, "lo95": 5.178, "mean": 5.1626, "ev_only": 5.1702, "ref_ms": 7.40722, "cand_ms": 1.42982, "n_trials": 214, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 99.78, "compile_s": 3.1, "r_error": "", "src_len": 2321, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1678, "tout": 3664, "ts": 1791530348.074921, "chk": "ok", "code_len": 2321}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3274, "tout": 1132, "ts": 1791530371.841433, "chk": null, "code_len": 2321}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1678, "started": 1791530312.9973571}
{"ep": "h1-00790", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.0393, "speedup": 2.0393, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 201.3, "calls": 2, "tokens_in": 15955, "tokens_out": 6902, "ctx_chars": 11175, "t_end": 1791530475.6968799, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.0393, "lo95": 2.0386, "mean": 2.0354, "ev_only": 2.037, "ref_ms": 8.61787, "cand_ms": 4.22596, "n_trials": 193, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2011, "r_wall_s": 94.5, "compile_s": 2.03, "r_error": "", "src_len": 3068, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6872, "tout": 5217, "ts": 1791530324.518832, "chk": "ok", "code_len": 3068}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9083, "tout": 1685, "ts": 1791530380.3039503, "chk": null, "code_len": 3068}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6872, "started": 1791530274.436664}
{"ep": "h1-00794", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0062, "speedup": 1.0062, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 197.0, "calls": 2, "tokens_in": 13888, "tokens_out": 5226, "ctx_chars": 9192, "t_end": 1791530477.8314078, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0062, "lo95": 1.0057, "mean": 1.0483, "ev_only": 1.0069, "ref_ms": 8.09948, "cand_ms": 8.0495, "n_trials": 145, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0176, "r_wall_s": 24.93, "compile_s": 2.9, "r_error": "", "src_len": 3788, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5721, "tout": 3232, "ts": 1791530308.3163798, "chk": "ok", "code_len": 3788}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8167, "tout": 1994, "ts": 1791530452.8057773, "chk": null, "code_len": 3788}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5721, "started": 1791530280.8025277}
{"ep": "h1-00769", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0152, "speedup": 1.0152, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 269.9, "calls": 2, "tokens_in": 6208, "tokens_out": 6182, "ctx_chars": 0, "t_end": 1791530478.6855254, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0152, "lo95": 1.014, "mean": 1.0156, "ev_only": 1.0151, "ref_ms": 8.11749, "cand_ms": 7.99606, "n_trials": 150, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0102, "r_wall_s": 181.39, "compile_s": 3.13, "r_error": "", "src_len": 4279, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1771, "tout": 4054, "ts": 1791530244.030602, "chk": "ok", "code_len": 4279}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4437, "tout": 2128, "ts": 1791530297.1105237, "chk": null, "code_len": 4279}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1771, "started": 1791530208.7745142}
{"ep": "h1-00799", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.381, "speedup": 1.381, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 183.1, "calls": 2, "tokens_in": 5337, "tokens_out": 5402, "ctx_chars": 0, "t_end": 1791530479.2799985, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.381, "lo95": 1.3797, "mean": 1.3798, "ev_only": 1.3844, "ref_ms": 16.11433, "cand_ms": 11.66837, "n_trials": 96, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 38.18, "compile_s": 2.14, "r_error": "", "src_len": 2611, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1690, "tout": 3437, "ts": 1791530326.3058827, "chk": "ok", "code_len": 2705}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3647, "tout": 1965, "ts": 1791530441.059572, "chk": null, "code_len": 2611}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1690, "started": 1791530296.2232141}
{"ep": "h1-00817", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0986, "speedup": 1.0986, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 133.5, "calls": 2, "tokens_in": 8961, "tokens_out": 5455, "ctx_chars": 2932, "t_end": 1791530487.334612, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0986, "lo95": 1.0977, "mean": 1.0946, "ev_only": 1.0999, "ref_ms": 8.38478, "cand_ms": 7.63217, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0397, "r_wall_s": 50.14, "compile_s": 2.13, "r_error": "", "src_len": 4082, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3305, "tout": 3475, "ts": 1791530382.3071442, "chk": "ok", "code_len": 4082}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5656, "tout": 1980, "ts": 1791530437.139003, "chk": null, "code_len": 4082}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3305, "started": 1791530353.7900312}
{"ep": "h1-00777", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0824, "speedup": 1.0824, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.2, "calls": 2, "tokens_in": 9310, "tokens_out": 13398, "ctx_chars": 0, "t_end": 1791530488.828911, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0824, "lo95": 1.082, "mean": 1.0839, "ev_only": 1.0828, "ref_ms": 27.87279, "cand_ms": 25.7505, "n_trials": 42, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0193, "r_wall_s": 55.84, "compile_s": 13.41, "r_error": "", "src_len": 11021, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1810, "tout": 8182, "ts": 1791530297.1951048, "chk": "ok", "code_len": 11021}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7500, "tout": 5216, "ts": 1791530432.829143, "chk": null, "code_len": 11021}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1810, "started": 1791530230.6740036}
{"ep": "h1-00744", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0007, "speedup": 1.0007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 406.7, "calls": 4, "tokens_in": 36863, "tokens_out": 12563, "ctx_chars": 6513, "t_end": 1791530492.7852862, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0007, "lo95": 1.0, "mean": 1.0021, "ev_only": 1.0, "ref_ms": 23.3825, "cand_ms": 23.36625, "n_trials": 62, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0112, "r_wall_s": 104.42, "compile_s": 2.47, "r_error": "", "src_len": 3405, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5439, "tout": 4440, "ts": 1791530144.118373, "chk": "incorrect", "code_len": 4935}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8258, "tout": 3224, "ts": 1791530197.802618, "chk": "incorrect", "code_len": 4030}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 10563, "tout": 2784, "ts": 1791530358.7404413, "chk": "ok", "code_len": 3405}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 12603, "tout": 2115, "ts": 1791530388.322901, "chk": null, "code_len": 3405}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5439, "started": 1791530106.4490516}
{"ep": "h1-00740", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.669, "speedup": 1.669, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 428.3, "calls": 3, "tokens_in": 18183, "tokens_out": 19198, "ctx_chars": 0, "t_end": 1791530500.2921627, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.669, "lo95": 1.668, "mean": 1.6676, "ev_only": 1.67, "ref_ms": 20.11736, "cand_ms": 12.05384, "n_trials": 63, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 84.38, "compile_s": 10.67, "r_error": "", "src_len": 6818, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2008, "tout": 11697, "ts": 1791530174.3167365, "chk": "no_custom_kernel", "code_len": 6820}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6213, "tout": 4004, "ts": 1791530346.5590944, "chk": "ok", "code_len": 6818}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9962, "tout": 3497, "ts": 1791530415.1572552, "chk": null, "code_len": 6818}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2008, "started": 1791530072.0386863}
{"ep": "h1-00813", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1635, "speedup": 2.1635, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 153.9, "calls": 2, "tokens_in": 12511, "tokens_out": 1488, "ctx_chars": 9855, "t_end": 1791530503.737904, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.1635, "lo95": 2.1616, "mean": 2.1585, "ev_only": 2.1715, "ref_ms": 6.30296, "cand_ms": 2.91332, "n_trials": 226, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2372, "r_wall_s": 118.71, "compile_s": 2.95, "r_error": "", "src_len": 890, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 935, "ts": 1791530358.573716, "chk": "ok", "code_len": 890}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6665, "tout": 553, "ts": 1791530384.2031076, "chk": null, "code_len": 890}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791530349.8836884}
{"ep": "h1-00774", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3621, "speedup": 1.3621, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 279.8, "calls": 2, "tokens_in": 14974, "tokens_out": 4100, "ctx_chars": 11132, "t_end": 1791530504.552451, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3621, "lo95": 1.358, "mean": 1.4196, "ev_only": 1.3604, "ref_ms": 11.06926, "cand_ms": 8.1265, "n_trials": 80, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2445, "r_wall_s": 199.27, "compile_s": 2.93, "r_error": "", "src_len": 3093, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6456, "tout": 2554, "ts": 1791530245.7396472, "chk": "ok", "code_len": 3093}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8518, "tout": 1546, "ts": 1791530304.4326909, "chk": null, "code_len": 3093}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6456, "started": 1791530224.734944}
{"ep": "h1-00827", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.5363, "speedup": 4.5363, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.1, "calls": 2, "tokens_in": 13611, "tokens_out": 5481, "ctx_chars": 9898, "t_end": 1791530507.821211, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.5363, "lo95": 4.5307, "mean": 4.6466, "ev_only": 4.5415, "ref_ms": 16.01084, "cand_ms": 3.5295, "n_trials": 76, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9995, "r_wall_s": 45.97, "compile_s": 2.06, "r_error": "", "src_len": 2074, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5911, "tout": 4311, "ts": 1791530431.28614, "chk": "ok", "code_len": 2074}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7700, "tout": 1170, "ts": 1791530461.8235786, "chk": null, "code_len": 2074}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5911, "started": 1791530390.6994789}
{"ep": "h1-00834", "task": "L1_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9995, "speedup": 0.9995, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 79.2, "calls": 3, "tokens_in": 20808, "tokens_out": 1464, "ctx_chars": 10384, "t_end": 1791530514.5550184, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9995, "lo95": 0.999, "mean": 0.9997, "ev_only": 0.9988, "ref_ms": 7.33478, "cand_ms": 7.33862, "n_trials": 192, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0004, "r_wall_s": 47.08, "compile_s": 3.79, "r_error": "", "src_len": 741, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6166, "tout": 975, "ts": 1791530449.7991822, "chk": "ok", "code_len": 741}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7250, "tout": 118, "ts": 1791530463.0454848, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7392, "tout": 371, "ts": 1791530467.0785482, "chk": null, "code_len": 741}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6166, "started": 1791530435.3234372}
{"ep": "h1-00812", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4011, "speedup": 1.4011, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 175.9, "calls": 2, "tokens_in": 25482, "tokens_out": 13081, "ctx_chars": 6513, "t_end": 1791530514.7151606, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4011, "lo95": 1.3866, "mean": 1.5118, "ev_only": 1.3973, "ref_ms": 8.73851, "cand_ms": 6.23704, "n_trials": 96, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0467, "r_wall_s": 61.83, "compile_s": 1.89, "r_error": "", "src_len": 9749, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 10321, "tout": 8804, "ts": 1791530413.664908, "chk": "ok", "code_len": 9749}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 15161, "tout": 4277, "ts": 1791530452.858341, "chk": null, "code_len": 9749}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 10321, "started": 1791530338.8310726}
{"ep": "h1-00755", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5206, "speedup": 1.5206, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 367.8, "calls": 2, "tokens_in": 6206, "tokens_out": 6317, "ctx_chars": 0, "t_end": 1791530518.758426, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.5206, "lo95": 1.5198, "mean": 1.5203, "ev_only": 1.52, "ref_ms": 20.44127, "cand_ms": 13.44316, "n_trials": 75, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 219.46, "compile_s": 2.93, "r_error": "", "src_len": 3096, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 4681, "ts": 1791530212.4059713, "chk": "ok", "code_len": 3096}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4203, "tout": 1636, "ts": 1791530299.1720443, "chk": null, "code_len": 3096}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791530171.3048108}
{"ep": "h1-00778", "task": "L3_036", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8221, "speedup": 0.8221, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 289.0, "calls": 3, "tokens_in": 18879, "tokens_out": 1609, "ctx_chars": 8224, "t_end": 1791530520.276346, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8221, "lo95": 0.8178, "mean": 0.8486, "ev_only": 0.8225, "ref_ms": 32.45504, "cand_ms": 39.47717, "n_trials": 21, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 186.57, "compile_s": 4.73, "r_error": "", "src_len": 1050, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5508, "tout": 1007, "ts": 1791530242.2515917, "chk": "ok", "code_len": 1050}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6624, "tout": 99, "ts": 1791530328.8692203, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6747, "tout": 503, "ts": 1791530333.6032414, "chk": null, "code_len": 1050}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5508, "started": 1791530231.2468584}
{"ep": "h1-00815", "task": "L2_098", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0091, "speedup": 1.0091, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 171.9, "calls": 2, "tokens_in": 13243, "tokens_out": 2585, "ctx_chars": 9033, "t_end": 1791530522.3041828, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0091, "lo95": 1.0082, "mean": 1.0678, "ev_only": 1.0073, "ref_ms": 8.14383, "cand_ms": 8.07046, "n_trials": 135, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 136.72, "compile_s": 3.07, "r_error": "", "src_len": 1484, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5660, "tout": 1814, "ts": 1791530368.53083, "chk": "ok", "code_len": 1484}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7583, "tout": 771, "ts": 1791530385.5544431, "chk": null, "code_len": 1484}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5660, "started": 1791530350.359197}
{"ep": "h1-00792", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1404, "speedup": 1.1404, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.5, "calls": 2, "tokens_in": 9905, "tokens_out": 8644, "ctx_chars": 2932, "t_end": 1791530523.6439567, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1404, "lo95": 1.1374, "mean": 1.1363, "ev_only": 1.141, "ref_ms": 8.3703, "cand_ms": 7.33964, "n_trials": 61, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1106, "r_wall_s": 104.25, "compile_s": 1.92, "r_error": "", "src_len": 5744, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3305, "tout": 5770, "ts": 1791530329.5988123, "chk": "ok", "code_len": 5744}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6600, "tout": 2874, "ts": 1791530419.3676994, "chk": null, "code_len": 5744}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3305, "started": 1791530280.1057796}
{"ep": "h1-00653", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0093, "speedup": 1.0093, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 832.0, "calls": 4, "tokens_in": 32444, "tokens_out": 6999, "ctx_chars": 9898, "t_end": 1791530523.883755, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0093, "lo95": 1.009, "mean": 1.0096, "ev_only": 1.01, "ref_ms": 8.00258, "cand_ms": 7.92909, "n_trials": 172, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0034, "r_wall_s": 189.36, "compile_s": 4.67, "r_error": "", "src_len": 883, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6120, "tout": 2161, "ts": 1791529711.431559, "chk": "incorrect", "code_len": 1565}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7552, "tout": 1925, "ts": 1791529988.8113182, "chk": "incorrect", "code_len": 1606}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8917, "tout": 2037, "ts": 1791530272.3286574, "chk": "ok", "code_len": 883}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9855, "tout": 876, "ts": 1791530334.4184766, "chk": null, "code_len": 883}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6120, "started": 1791529691.8575854}
{"ep": "h1-00808", "task": "L2_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3913, "speedup": 1.3913, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 196.9, "calls": 2, "tokens_in": 5191, "tokens_out": 3676, "ctx_chars": 0, "t_end": 1791530524.807698, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3913, "lo95": 1.3869, "mean": 1.3905, "ev_only": 1.3924, "ref_ms": 19.40304, "cand_ms": 13.94626, "n_trials": 79, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0593, "r_wall_s": 128.58, "compile_s": 18.04, "r_error": "", "src_len": 2739, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1729, "tout": 2406, "ts": 1791530349.0092864, "chk": "ok", "code_len": 2739}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3462, "tout": 1270, "ts": 1791530395.777433, "chk": null, "code_len": 2739}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1729, "started": 1791530327.8753448}
{"ep": "h1-00818", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.3527, "speedup": 9.3527, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 160.8, "calls": 2, "tokens_in": 4654, "tokens_out": 2667, "ctx_chars": 0, "t_end": 1791530525.5355256, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 9.3527, "lo95": 9.0008, "mean": 9.3006, "ev_only": 9.4151, "ref_ms": 8.01149, "cand_ms": 0.8566, "n_trials": 127, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0073, "r_wall_s": 125.83, "compile_s": 4.22, "r_error": "", "src_len": 1560, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1739, "tout": 1758, "ts": 1791530381.0752125, "chk": "ok", "code_len": 1560}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2915, "tout": 909, "ts": 1791530399.6811674, "chk": null, "code_len": 1560}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1739, "started": 1791530364.7526023}
{"ep": "h1-00806", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2197, "speedup": 1.2197, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 208.5, "calls": 2, "tokens_in": 15625, "tokens_out": 2426, "ctx_chars": 12155, "t_end": 1791530525.8591404, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2197, "lo95": 1.2187, "mean": 1.2176, "ev_only": 1.2221, "ref_ms": 12.02086, "cand_ms": 9.85576, "n_trials": 104, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0727, "r_wall_s": 96.54, "compile_s": 1.87, "r_error": "", "src_len": 1578, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7203, "tout": 1562, "ts": 1791530330.9750361, "chk": "ok", "code_len": 1578}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8422, "tout": 864, "ts": 1791530428.199639, "chk": null, "code_len": 1578}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7203, "started": 1791530317.3516006}
{"ep": "h1-00732", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0119, "speedup": 1.0119, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 492.7, "calls": 4, "tokens_in": 22874, "tokens_out": 12213, "ctx_chars": 0, "t_end": 1791530527.9519658, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0119, "lo95": 1.0117, "mean": 1.0122, "ev_only": 1.0102, "ref_ms": 8.00045, "cand_ms": 7.90653, "n_trials": 185, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0036, "r_wall_s": 192.29, "compile_s": 19.31, "r_error": "", "src_len": 2043, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1783, "tout": 3907, "ts": 1791530068.4079206, "chk": "incorrect", "code_len": 4591}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4625, "tout": 3205, "ts": 1791530115.8630075, "chk": "incorrect", "code_len": 4821}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7430, "tout": 3350, "ts": 1791530170.542854, "chk": "ok", "code_len": 2043}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9036, "tout": 1751, "ts": 1791530335.5476565, "chk": null, "code_len": 2043}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1783, "started": 1791530035.2910912}
{"ep": "h1-00810", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 11.7134, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 193.2, "calls": 3, "tokens_in": 16827, "tokens_out": 9003, "ctx_chars": 2425, "t_end": 1791530528.0788233, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 11.7134, "lo95": 11.57, "mean": 11.4018, "ev_only": 11.8787, "ref_ms": 12.15162, "cand_ms": 1.03742, "n_trials": 112, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.7205, "r_wall_s": 75.59, "compile_s": 3.13, "r_error": "", "src_len": 2946, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 4071, "ts": 1791530373.1781387, "chk": "incorrect", "code_len": 3103}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5693, "tout": 3480, "ts": 1791530427.6800299, "chk": "ok", "code_len": 2994}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7541, "tout": 1452, "ts": 1791530452.2477086, "chk": null, "code_len": 2946}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 3593, "started": 1791530334.9093478}
{"ep": "h1-00802", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.2014, "speedup": 2.2014, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 218.5, "calls": 2, "tokens_in": 15339, "tokens_out": 2747, "ctx_chars": 11175, "t_end": 1791530528.1241302, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.2014, "lo95": 2.2, "mean": 2.1981, "ev_only": 2.2032, "ref_ms": 44.17005, "cand_ms": 20.06426, "n_trials": 27, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 141.28, "compile_s": 2.99, "r_error": "", "src_len": 2161, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6888, "tout": 1646, "ts": 1791530323.53305, "chk": "ok", "code_len": 2161}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8451, "tout": 1101, "ts": 1791530385.9751554, "chk": null, "code_len": 2161}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6888, "started": 1791530309.6245184}
{"ep": "h1-00822", "task": "L3_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9658, "speedup": 0.9658, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 152.7, "calls": 3, "tokens_in": 11134, "tokens_out": 2516, "ctx_chars": 0, "t_end": 1791530528.9813585, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9658, "lo95": 0.9651, "mean": 1.0097, "ev_only": 0.97, "ref_ms": 4.00659, "cand_ms": 4.14849, "n_trials": 198, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.049, "r_wall_s": 83.73, "compile_s": 2.37, "r_error": "", "src_len": 2374, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2691, "tout": 1400, "ts": 1791530389.9258235, "chk": "ok", "code_len": 2374}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4203, "tout": 13, "ts": 1791530435.7758322, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4240, "tout": 1103, "ts": 1791530445.0007284, "chk": null, "code_len": 2374}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2691, "started": 1791530376.3104458}
{"ep": "h1-00763", "task": "L2_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.069, "speedup": 1.069, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 372.4, "calls": 2, "tokens_in": 17013, "tokens_out": 4529, "ctx_chars": 11062, "t_end": 1791530547.5704496, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.069, "lo95": 1.0683, "mean": 1.0687, "ev_only": 1.0693, "ref_ms": 12.66815, "cand_ms": 11.85077, "n_trials": 105, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0244, "r_wall_s": 229.79, "compile_s": 2.2, "r_error": "", "src_len": 2046, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6693, "tout": 3515, "ts": 1791530207.7720592, "chk": "ok", "code_len": 2046}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10320, "tout": 1014, "ts": 1791530317.6730726, "chk": null, "code_len": 2046}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6693, "started": 1791530175.1214826}
{"ep": "h1-00712", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6714, "speedup": 0.6714, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 594.4, "calls": 2, "tokens_in": 13895, "tokens_out": 10601, "ctx_chars": 6513, "t_end": 1791530550.0975873, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6714, "lo95": 0.6704, "mean": 0.6831, "ev_only": 0.6668, "ref_ms": 3.84988, "cand_ms": 5.73411, "n_trials": 185, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.235, "r_wall_s": 131.0, "compile_s": 2.64, "r_error": "", "src_len": 6527, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 7469, "ts": 1791530019.9731202, "chk": "ok", "code_len": 6527}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8812, "tout": 3132, "ts": 1791530285.3989804, "chk": null, "code_len": 6527}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791529955.7414968}
{"ep": "h1-00804", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0011, "speedup": 1.0011, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.9, "calls": 2, "tokens_in": 12784, "tokens_out": 2026, "ctx_chars": 9898, "t_end": 1791530556.2596793, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0011, "lo95": 1.0007, "mean": 1.0011, "ev_only": 1.0003, "ref_ms": 16.00627, "cand_ms": 15.9883, "n_trials": 98, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0008, "r_wall_s": 89.08, "compile_s": 3.73, "r_error": "", "src_len": 1027, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5911, "tout": 1319, "ts": 1791530324.764889, "chk": "ok", "code_len": 1027}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6873, "tout": 707, "ts": 1791530467.1223578, "chk": null, "code_len": 1027}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5911, "started": 1791530312.3253393}
{"ep": "h1-00746", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.45, "speedup": 0.45, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 470.5, "calls": 3, "tokens_in": 51744, "tokens_out": 26560, "ctx_chars": 6513, "t_end": 1791530557.5632918, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.45, "lo95": 0.4492, "mean": 0.4528, "ev_only": 0.4501, "ref_ms": 8.67334, "cand_ms": 19.27501, "n_trials": 39, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.7648, "r_wall_s": 54.71, "compile_s": 1.95, "r_error": "", "src_len": 13554, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 10321, "tout": 12688, "ts": 1791530190.7932568, "chk": "incorrect", "code_len": 13554}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 17362, "tout": 7478, "ts": 1791530398.240032, "chk": "ok", "code_len": 13554}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 24061, "tout": 6394, "ts": 1791530502.817386, "chk": null, "code_len": 13554}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 10321, "started": 1791530087.0609708}
{"ep": "h1-00825", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0671, "speedup": 1.0671, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 171.3, "calls": 2, "tokens_in": 12302, "tokens_out": 2359, "ctx_chars": 8462, "t_end": 1791530558.1382754, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0671, "lo95": 1.0668, "mean": 1.0666, "ev_only": 1.0657, "ref_ms": 8.50052, "cand_ms": 7.96637, "n_trials": 193, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0051, "r_wall_s": 19.52, "compile_s": 2.08, "r_error": "", "src_len": 1830, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1386, "ts": 1791530398.3793337, "chk": "ok", "code_len": 1830}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6900, "tout": 973, "ts": 1791530538.5440392, "chk": null, "code_len": 1830}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791530386.817267}
{"ep": "h1-00821", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0, "speedup": 1.0, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 186.3, "calls": 2, "tokens_in": 5052, "tokens_out": 4266, "ctx_chars": 0, "t_end": 1791530562.2772532, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0, "lo95": 0.999, "mean": 0.9993, "ev_only": 1.0017, "ref_ms": 2.89798, "cand_ms": 2.89791, "n_trials": 216, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 31.42, "compile_s": 1.87, "r_error": "", "src_len": 2521, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 2676, "ts": 1791530398.7564836, "chk": "ok", "code_len": 2521}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3463, "tout": 1590, "ts": 1791530530.7621365, "chk": null, "code_len": 2521}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791530375.9793155}
{"ep": "h1-00831", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2955, "speedup": 1.2955, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 157.3, "calls": 2, "tokens_in": 5627, "tokens_out": 5174, "ctx_chars": 0, "t_end": 1791530563.1101282, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2955, "lo95": 1.2947, "mean": 1.2934, "ev_only": 1.2956, "ref_ms": 7.58127, "cand_ms": 5.85222, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1169, "r_wall_s": 98.25, "compile_s": 2.4, "r_error": "", "src_len": 3338, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1685, "tout": 3479, "ts": 1791530437.292178, "chk": "ok", "code_len": 3338}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3942, "tout": 1695, "ts": 1791530464.3765564, "chk": null, "code_len": 3338}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1685, "started": 1791530405.823104}
{"ep": "h1-00868", "task": "L2_081", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "runtime_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 13.1, "calls": 1, "tokens_in": 1704, "tokens_out": 602, "ctx_chars": 0, "t_end": 1791530569.33968, "error": "CompilationError: at 13:8:\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    mask = offs < n\n    x = tl.load(x_ptr + offs, mask=mask)\n", "f_status": "runtime_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": null, "r_wall_s": 6.78, "compile_s": 1.96, "r_error": "CompilationError: at 13:8:\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    mask = offs < n\n    x = tl.load(x_ptr + offs, mask=mask)\n", "src_len": 1062, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1704, "tout": 602, "ts": 1791530562.5282543, "chk": null, "code_len": 1062}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1704, "started": 1791530556.259943}
{"ep": "h1-00766", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4019, "speedup": 0.4019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 377.1, "calls": 3, "tokens_in": 30005, "tokens_out": 15069, "ctx_chars": 10864, "t_end": 1791530572.3138194, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.4019, "lo95": 0.4014, "mean": 0.4015, "ev_only": 0.4017, "ref_ms": 10.0844, "cand_ms": 25.0888, "n_trials": 65, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 134.04, "compile_s": 12.52, "r_error": "", "src_len": 6167, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6627, "tout": 8192, "ts": 1791530268.401057, "chk": "no_custom_kernel", "code_len": 6169}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10125, "tout": 3458, "ts": 1791530371.413638, "chk": "ok", "code_len": 6167}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13253, "tout": 3419, "ts": 1791530437.2127922, "chk": null, "code_len": 6167}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6627, "started": 1791530195.2258642}
{"ep": "h1-00788", "task": "L2_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9648, "speedup": 0.9648, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 306.6, "calls": 2, "tokens_in": 5534, "tokens_out": 3046, "ctx_chars": 0, "t_end": 1791530572.749385, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9648, "lo95": 0.9631, "mean": 0.9645, "ev_only": 0.9646, "ref_ms": 7.72433, "cand_ms": 8.00635, "n_trials": 170, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0989, "r_wall_s": 149.41, "compile_s": 48.12, "r_error": "", "src_len": 1877, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 2056, "ts": 1791530287.2305155, "chk": "ok", "code_len": 1877}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3851, "tout": 990, "ts": 1791530422.8550665, "chk": null, "code_len": 1877}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1683, "started": 1791530266.1955502}
{"ep": "h1-00753", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 6.471, "speedup": 6.471, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 452.6, "calls": 3, "tokens_in": 17341, "tokens_out": 14573, "ctx_chars": 0, "t_end": 1791530577.3957024, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.471, "lo95": 6.4413, "mean": 6.304, "ev_only": 6.3791, "ref_ms": 4.60711, "cand_ms": 0.71197, "n_trials": 235, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9934, "r_wall_s": 126.8, "compile_s": 13.8, "r_error": "", "src_len": 6124, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2218, "tout": 7651, "ts": 1791530193.263478, "chk": "no_custom_kernel", "code_len": 6146}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5879, "tout": 3784, "ts": 1791530412.0081468, "chk": "ok", "code_len": 6124}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9244, "tout": 3138, "ts": 1791530450.3705888, "chk": null, "code_len": 6124}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2218, "started": 1791530124.792859}
{"ep": "h1-00858", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0168, "speedup": 1.0168, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 70.3, "calls": 2, "tokens_in": 4213, "tokens_out": 1837, "ctx_chars": 0, "t_end": 1791530594.166957, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0168, "lo95": 1.0159, "mean": 1.0173, "ev_only": 1.0173, "ref_ms": 8.09291, "cand_ms": 7.9591, "n_trials": 150, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 41.68, "compile_s": 2.34, "r_error": "", "src_len": 870, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1670, "tout": 1266, "ts": 1791530535.5000286, "chk": "ok", "code_len": 870}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2543, "tout": 571, "ts": 1791530552.3902395, "chk": null, "code_len": 870}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1670, "started": 1791530523.8843737}
{"ep": "h1-00854", "task": "L1_013", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8785, "speedup": 0.8785, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 78.8, "calls": 1, "tokens_in": 1699, "tokens_out": 5219, "ctx_chars": 0, "t_end": 1791530597.5973928, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8785, "lo95": 0.8784, "mean": 0.8782, "ev_only": 0.8788, "ref_ms": 7.3222, "cand_ms": 8.33483, "n_trials": 159, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 36.69, "compile_s": 2.17, "r_error": "", "src_len": 2632, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1699, "tout": 5219, "ts": 1791530560.7707286, "chk": null, "code_len": 2632}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1699, "started": 1791530518.7586534}
{"ep": "h1-00837", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3901, "speedup": 1.3901, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 139.5, "calls": 2, "tokens_in": 5082, "tokens_out": 4642, "ctx_chars": 0, "t_end": 1791530599.8291192, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3901, "lo95": 1.3892, "mean": 1.3926, "ev_only": 1.3919, "ref_ms": 7.38949, "cand_ms": 5.31594, "n_trials": 224, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 53.4, "compile_s": 2.32, "r_error": "", "src_len": 2653, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 2980, "ts": 1791530491.8323684, "chk": "ok", "code_len": 2653}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3518, "tout": 1662, "ts": 1791530546.3559847, "chk": null, "code_len": 2653}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791530460.2928355}
{"ep": "h1-00793", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7921, "speedup": 0.7921, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 324.3, "calls": 2, "tokens_in": 12266, "tokens_out": 2728, "ctx_chars": 9033, "t_end": 1791530604.6657202, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7921, "lo95": 0.7914, "mean": 0.7916, "ev_only": 0.7911, "ref_ms": 3.73321, "cand_ms": 4.71276, "n_trials": 171, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0072, "r_wall_s": 64.83, "compile_s": 2.28, "r_error": "", "src_len": 1229, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 2010, "ts": 1791530299.1219618, "chk": "ok", "code_len": 1229}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6776, "tout": 718, "ts": 1791530539.8091364, "chk": null, "code_len": 1229}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791530280.4048576}
{"ep": "h1-00861", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0139, "speedup": 1.0139, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.3, "calls": 2, "tokens_in": 13540, "tokens_out": 1216, "ctx_chars": 10749, "t_end": 1791530606.1400795, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0139, "lo95": 1.012, "mean": 1.0129, "ev_only": 1.0135, "ref_ms": 15.98566, "cand_ms": 15.76622, "n_trials": 89, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 58.43, "compile_s": 2.21, "r_error": "", "src_len": 1036, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6387, "tout": 657, "ts": 1791530531.364403, "chk": "ok", "code_len": 1036}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7153, "tout": 559, "ts": 1791530547.584697, "chk": null, "code_len": 1036}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6387, "started": 1791530525.8593655}
{"ep": "h1-00780", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1836, "speedup": 1.1836, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 376.2, "calls": 5, "tokens_in": 34610, "tokens_out": 18702, "ctx_chars": 0, "t_end": 1791530607.9860213, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1836, "lo95": 1.1832, "mean": 1.1838, "ev_only": 1.1833, "ref_ms": 15.86245, "cand_ms": 13.40237, "n_trials": 95, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0299, "r_wall_s": 104.88, "compile_s": 1.98, "r_error": "", "src_len": 2986, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2837, "tout": 4542, "ts": 1791530274.9562802, "chk": "incorrect", "code_len": 2750}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4696, "tout": 3667, "ts": 1791530339.5814764, "chk": "runtime_error", "code_len": 2911}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6842, "tout": 3249, "ts": 1791530374.7539692, "chk": "incorrect", "code_len": 3374}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9034, "tout": 3947, "ts": 1791530447.54473, "chk": "incorrect", "code_len": 3199}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11201, "tout": 3297, "ts": 1791530502.3361712, "chk": null, "code_len": 2986}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "runtime_error", "incorrect", "incorrect", null], "first_tin": 2837, "started": 1791530231.8296173}
{"ep": "h1-00853", "task": "L3_022", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.3058, "speedup": 0.3058, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 94.4, "calls": 3, "tokens_in": 24424, "tokens_out": 5923, "ctx_chars": 6513, "t_end": 1791530609.1320052, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.3058, "lo95": 0.301, "mean": 0.3145, "ev_only": 0.3062, "ref_ms": 6.07055, "cand_ms": 19.85384, "n_trials": 74, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0592, "r_wall_s": 33.75, "compile_s": 3.21, "r_error": "", "src_len": 6014, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6066, "tout": 2976, "ts": 1791530538.5575247, "chk": "ok", "code_len": 6014}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9154, "tout": 26, "ts": 1791530552.5058837, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9204, "tout": 2921, "ts": 1791530575.3490798, "chk": null, "code_len": 6014}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6066, "started": 1791530514.715377}
{"ep": "h1-00760", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5618, "speedup": 1.5618, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 443.3, "calls": 2, "tokens_in": 12254, "tokens_out": 25719, "ctx_chars": 0, "t_end": 1791530610.5806396, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5618, "lo95": 1.5573, "mean": 1.5426, "ev_only": 1.5552, "ref_ms": 5.27983, "cand_ms": 3.38063, "n_trials": 206, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1321, "r_wall_s": 74.6, "compile_s": 12.13, "r_error": "", "src_len": 13800, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1974, "tout": 17883, "ts": 1791530317.7330809, "chk": "ok", "code_len": 13800}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10280, "tout": 7836, "ts": 1791530535.557829, "chk": null, "code_len": 13800}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1974, "started": 1791530167.310332}
{"ep": "h1-00840", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9932, "speedup": 0.9932, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 140.1, "calls": 2, "tokens_in": 11520, "tokens_out": 14790, "ctx_chars": 0, "t_end": 1791530611.8494196, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9932, "lo95": 0.9917, "mean": 0.9919, "ev_only": 0.9934, "ref_ms": 15.32624, "cand_ms": 15.43164, "n_trials": 82, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1175, "r_wall_s": 15.06, "compile_s": 1.83, "r_error": "", "src_len": 9814, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 9924, "ts": 1791530554.628955, "chk": "ok", "code_len": 9911}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8496, "tout": 4866, "ts": 1791530596.686155, "chk": null, "code_len": 9814}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791530471.7542005}
{"ep": "h1-00833", "task": "L2_079", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4298, "speedup": 1.4298, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 184.4, "calls": 4, "tokens_in": 22528, "tokens_out": 6563, "ctx_chars": 0, "t_end": 1791530618.1557271, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4298, "lo95": 1.4285, "mean": 1.4297, "ev_only": 1.4365, "ref_ms": 2.17639, "cand_ms": 1.52219, "n_trials": 213, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1488, "r_wall_s": 32.78, "compile_s": 11.15, "r_error": "", "src_len": 4190, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1811, "tout": 2514, "ts": 1791530458.7038102, "chk": "compile_error", "code_len": 4441}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5469, "tout": 2018, "ts": 1791530533.6669927, "chk": "ok", "code_len": 4190}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7599, "tout": 26, "ts": 1791530569.204919, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7649, "tout": 2005, "ts": 1791530585.3432996, "chk": null, "code_len": 4190}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1811, "started": 1791530433.7984328}
{"ep": "h1-00866", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0047, "speedup": 1.0047, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.8, "calls": 2, "tokens_in": 12556, "tokens_out": 1275, "ctx_chars": 9890, "t_end": 1791530621.3945253, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0047, "lo95": 1.0042, "mean": 1.0062, "ev_only": 1.0055, "ref_ms": 8.01716, "cand_ms": 7.98004, "n_trials": 80, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 51.28, "compile_s": 1.98, "r_error": "", "src_len": 1091, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5890, "tout": 667, "ts": 1791530553.7433827, "chk": "ok", "code_len": 1091}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6666, "tout": 608, "ts": 1791530570.0454757, "chk": null, "code_len": 1091}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5890, "started": 1791530547.5707088}
{"ep": "h1-00807", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4458, "speedup": 1.4458, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 306.1, "calls": 2, "tokens_in": 14016, "tokens_out": 1987, "ctx_chars": 10756, "t_end": 1791530625.7567854, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4458, "lo95": 1.4452, "mean": 1.4457, "ev_only": 1.4474, "ref_ms": 13.94194, "cand_ms": 9.64291, "n_trials": 104, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0824, "r_wall_s": 76.86, "compile_s": 2.02, "r_error": "", "src_len": 1194, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6463, "tout": 1311, "ts": 1791530331.2578971, "chk": "ok", "code_len": 1194}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7553, "tout": 676, "ts": 1791530548.10096, "chk": null, "code_len": 1194}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6463, "started": 1791530319.6435776}
{"ep": "h1-00789", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0605, "speedup": 1.0605, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 354.0, "calls": 2, "tokens_in": 7236, "tokens_out": 8566, "ctx_chars": 0, "t_end": 1791530627.3280187, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0605, "lo95": 1.0596, "mean": 1.0609, "ev_only": 1.0611, "ref_ms": 27.8445, "cand_ms": 26.2572, "n_trials": 40, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0206, "r_wall_s": 121.83, "compile_s": 13.75, "r_error": "", "src_len": 6493, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1810, "tout": 5366, "ts": 1791530318.8359663, "chk": "ok", "code_len": 6493}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5426, "tout": 3200, "ts": 1791530505.2631714, "chk": null, "code_len": 6493}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1810, "started": 1791530273.303894}
{"ep": "h1-00791", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9968, "speedup": 0.9968, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 355.2, "calls": 2, "tokens_in": 4886, "tokens_out": 4529, "ctx_chars": 0, "t_end": 1791530630.7968857, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9968, "lo95": 0.996, "mean": 0.9972, "ev_only": 0.9978, "ref_ms": 7.51384, "cand_ms": 7.53766, "n_trials": 181, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 74.56, "compile_s": 2.39, "r_error": "", "src_len": 2184, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 2952, "ts": 1791530322.9370997, "chk": "ok", "code_len": 2184}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3319, "tout": 1577, "ts": 1791530556.1480577, "chk": null, "code_len": 2184}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791530296.000813}
{"ep": "h1-00843", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1959, "speedup": 1.1959, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 153.4, "calls": 2, "tokens_in": 10218, "tokens_out": 9370, "ctx_chars": 2932, "t_end": 1791530632.0791135, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1959, "lo95": 1.1949, "mean": 1.1859, "ev_only": 1.1937, "ref_ms": 8.36192, "cand_ms": 6.99227, "n_trials": 168, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.07, "r_wall_s": 68.27, "compile_s": 2.36, "r_error": "", "src_len": 5866, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3305, "tout": 6286, "ts": 1791530531.0975904, "chk": "ok", "code_len": 5866}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6913, "tout": 3084, "ts": 1791530563.7638276, "chk": null, "code_len": 5866}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3305, "started": 1791530478.6858022}
{"ep": "h1-00823", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.98, "speedup": 0.98, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.1, "calls": 2, "tokens_in": 17202, "tokens_out": 13612, "ctx_chars": 6513, "t_end": 1791530639.0090206, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.98, "lo95": 0.9779, "mean": 0.9824, "ev_only": 0.9809, "ref_ms": 19.99099, "cand_ms": 20.39895, "n_trials": 51, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1205, "r_wall_s": 52.31, "compile_s": 2.06, "r_error": "", "src_len": 8191, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6296, "tout": 9507, "ts": 1791530459.32621, "chk": "ok", "code_len": 8191}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10906, "tout": 4105, "ts": 1791530586.6533606, "chk": null, "code_len": 8191}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6296, "started": 1791530377.8859477}
{"ep": "h1-00859", "task": "L3_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1492, "speedup": 1.1492, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 119.9, "calls": 3, "tokens_in": 18198, "tokens_out": 3880, "ctx_chars": 6513, "t_end": 1791530644.7575288, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1492, "lo95": 1.1486, "mean": 1.1488, "ev_only": 1.154, "ref_ms": 5.22642, "cand_ms": 4.54784, "n_trials": 232, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0594, "r_wall_s": 75.99, "compile_s": 2.45, "r_error": "", "src_len": 3773, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4675, "tout": 1930, "ts": 1791530541.1100292, "chk": "ok", "code_len": 3773}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6717, "tout": 65, "ts": 1791530553.2859228, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6806, "tout": 1885, "ts": 1791530568.5326006, "chk": null, "code_len": 3773}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4675, "started": 1791530524.8079603}
{"ep": "h1-00839", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1895, "speedup": 1.1895, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 175.2, "calls": 2, "tokens_in": 15907, "tokens_out": 3862, "ctx_chars": 10864, "t_end": 1791530646.0204918, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1895, "lo95": 1.1891, "mean": 1.189, "ev_only": 1.1921, "ref_ms": 3.73563, "cand_ms": 3.14059, "n_trials": 206, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 82.09, "compile_s": 2.15, "r_error": "", "src_len": 3136, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6949, "tout": 2300, "ts": 1791530488.8457434, "chk": "ok", "code_len": 3136}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8958, "tout": 1562, "ts": 1791530563.143835, "chk": null, "code_len": 3136}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6949, "started": 1791530470.8441486}
{"ep": "h1-00847", "task": "L1_080", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9646, "speedup": 0.9646, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 156.0, "calls": 1, "tokens_in": 6630, "tokens_out": 1275, "ctx_chars": 10864, "t_end": 1791530648.816207, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9646, "lo95": 0.9633, "mean": 0.9626, "ev_only": 0.9645, "ref_ms": 20.13638, "cand_ms": 20.87509, "n_trials": 67, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0364, "r_wall_s": 140.6, "compile_s": 2.06, "r_error": "", "src_len": 1693, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6630, "tout": 1275, "ts": 1791530507.4746132, "chk": null, "code_len": 1693}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6630, "started": 1791530492.7855513}
{"ep": "h1-00885", "task": "L3_042", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8019, "speedup": 0.8019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 40.7, "calls": 2, "tokens_in": 11971, "tokens_out": 1389, "ctx_chars": 8224, "t_end": 1791530652.5549774, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8019, "lo95": 0.7983, "mean": 0.8015, "ev_only": 0.8017, "ref_ms": 60.08968, "cand_ms": 74.93577, "n_trials": 18, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 14.7, "compile_s": 1.97, "r_error": "", "src_len": 882, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5501, "tout": 860, "ts": 1791530622.219558, "chk": "ok", "code_len": 882}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6470, "tout": 529, "ts": 1791530637.7501101, "chk": null, "code_len": 882}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5501, "started": 1791530611.8496974}
{"ep": "h1-00826", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 20.4201, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 264.8, "calls": 2, "tokens_in": 11667, "tokens_out": 9294, "ctx_chars": 6034, "t_end": 1791530653.9238927, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 20.4201, "lo95": 20.0801, "mean": 22.1518, "ev_only": 20.4723, "ref_ms": 29.28767, "cand_ms": 1.43426, "n_trials": 32, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.904, "r_wall_s": 130.32, "compile_s": 16.93, "r_error": "", "src_len": 4169, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 7093, "ts": 1791530454.0535345, "chk": "ok", "code_len": 4169}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7119, "tout": 2201, "ts": 1791530523.5761235, "chk": null, "code_len": 4169}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4548, "started": 1791530389.129838}
{"ep": "h1-00877", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0006, "speedup": 1.0006, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 60.7, "calls": 2, "tokens_in": 11716, "tokens_out": 1195, "ctx_chars": 9033, "t_end": 1791530654.8387916, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0006, "lo95": 1.0001, "mean": 1.0006, "ev_only": 1.0014, "ref_ms": 4.45156, "cand_ms": 4.44888, "n_trials": 129, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0021, "r_wall_s": 19.15, "compile_s": 1.86, "r_error": "", "src_len": 941, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5455, "tout": 697, "ts": 1791530620.6113117, "chk": "ok", "code_len": 941}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6261, "tout": 498, "ts": 1791530635.5725083, "chk": null, "code_len": 941}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5455, "started": 1791530614.52088}
{"ep": "h1-00820", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2988, "speedup": 0.2988, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 281.6, "calls": 3, "tokens_in": 12117, "tokens_out": 7854, "ctx_chars": 0, "t_end": 1791530657.4551566, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.2988, "lo95": 0.2966, "mean": 0.2954, "ev_only": 0.294, "ref_ms": 2.44017, "cand_ms": 8.16677, "n_trials": 173, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9994, "r_wall_s": 165.58, "compile_s": 12.74, "r_error": "", "src_len": 3630, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 3863, "ts": 1791530409.0973282, "chk": "no_custom_kernel", "code_len": 3652}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4156, "tout": 2035, "ts": 1791530438.9318912, "chk": "ok", "code_len": 3630}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6210, "tout": 1956, "ts": 1791530491.8422873, "chk": null, "code_len": 3630}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1751, "started": 1791530375.8188334}
{"ep": "h1-00860", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2759, "speedup": 0.2759, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 132.7, "calls": 2, "tokens_in": 8265, "tokens_out": 8684, "ctx_chars": 0, "t_end": 1791530658.27991, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.2759, "lo95": 0.2754, "mean": 0.2759, "ev_only": 0.2757, "ref_ms": 30.89419, "cand_ms": 111.95578, "n_trials": 10, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 41.83, "compile_s": 2.68, "r_error": "", "src_len": 5545, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2408, "tout": 5646, "ts": 1791530571.9470303, "chk": "ok", "code_len": 5545}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5857, "tout": 3038, "ts": 1791530616.0989273, "chk": null, "code_len": 5545}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2408, "started": 1791530525.5357783}
{"ep": "h1-00844", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.457, "speedup": 4.457, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.8, "calls": 2, "tokens_in": 17533, "tokens_out": 6960, "ctx_chars": 12352, "t_end": 1791530659.0332117, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.457, "lo95": 4.4509, "mean": 4.4486, "ev_only": 4.467, "ref_ms": 27.82344, "cand_ms": 6.24263, "n_trials": 49, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0799, "r_wall_s": 64.17, "compile_s": 2.12, "r_error": "", "src_len": 4155, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7394, "tout": 4781, "ts": 1791530521.8073518, "chk": "ok", "code_len": 4225}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10139, "tout": 2179, "ts": 1791530594.705608, "chk": null, "code_len": 4155}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7394, "started": 1791530479.2802427}
{"ep": "h1-00865", "task": "L1_014", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.1341, "speedup": 4.1341, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 133.3, "calls": 4, "tokens_in": 13783, "tokens_out": 3674, "ctx_chars": 0, "t_end": 1791530662.301367, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.1341, "lo95": 4.1118, "mean": 4.1073, "ev_only": 4.1418, "ref_ms": 7.37973, "cand_ms": 1.7851, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9785, "r_wall_s": 56.83, "compile_s": 2.03, "r_error": "", "src_len": 2035, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1676, "tout": 1366, "ts": 1791530541.8164976, "chk": "incorrect", "code_len": 2326}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3174, "tout": 1159, "ts": 1791530577.0226564, "chk": "ok", "code_len": 2035}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4442, "tout": 25, "ts": 1791530596.042783, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 4491, "tout": 1124, "ts": 1791530605.3561199, "chk": null, "code_len": 2035}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 1676, "started": 1791530528.9815907}
{"ep": "h1-00835", "task": "L2_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0162, "speedup": 1.0162, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 228.8, "calls": 3, "tokens_in": 18811, "tokens_out": 2179, "ctx_chars": 8462, "t_end": 1791530664.6326385, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0162, "lo95": 1.0149, "mean": 1.0151, "ev_only": 1.016, "ref_ms": 8.50258, "cand_ms": 8.3672, "n_trials": 184, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0518, "r_wall_s": 137.49, "compile_s": 3.31, "r_error": "", "src_len": 2003, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5400, "tout": 1142, "ts": 1791530451.1524463, "chk": "ok", "code_len": 2003}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6654, "tout": 79, "ts": 1791530518.909548, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6757, "tout": 958, "ts": 1791530527.062059, "chk": null, "code_len": 2003}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5400, "started": 1791530435.8710754}
{"ep": "h1-00845", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 37.2087, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 177.6, "calls": 2, "tokens_in": 12061, "tokens_out": 2881, "ctx_chars": 8570, "t_end": 1791530664.9458117, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 37.2087, "lo95": 36.4016, "mean": 35.65, "ev_only": 38.7084, "ref_ms": 16.03507, "cand_ms": 0.43095, "n_trials": 111, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.3583, "r_wall_s": 66.08, "compile_s": 1.92, "r_error": "", "src_len": 1514, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5372, "tout": 2068, "ts": 1791530507.5315516, "chk": "ok", "code_len": 1514}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6689, "tout": 813, "ts": 1791530598.7403576, "chk": null, "code_len": 1514}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5372, "started": 1791530487.3348968}
{"ep": "h1-00829", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.1314, "speedup": 0.1314, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 263.3, "calls": 2, "tokens_in": 7228, "tokens_out": 5828, "ctx_chars": 0, "t_end": 1791530665.2156746, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.1314, "lo95": 0.1313, "mean": 0.1316, "ev_only": 0.1313, "ref_ms": 30.79982, "cand_ms": 234.44157, "n_trials": 10, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9304, "r_wall_s": 137.68, "compile_s": 6.64, "r_error": "", "src_len": 3423, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2408, "tout": 3948, "ts": 1791530457.0478737, "chk": "ok", "code_len": 3423}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4820, "tout": 1880, "ts": 1791530527.2069468, "chk": null, "code_len": 3423}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2408, "started": 1791530422.2305124}
{"ep": "h1-00803", "task": "L1_006", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.0288, "speedup": 0.0288, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 371.4, "calls": 5, "tokens_in": 42380, "tokens_out": 5684, "ctx_chars": 9033, "t_end": 1791530682.366612, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0288, "lo95": 0.0287, "mean": 0.0304, "ev_only": 0.0287, "ref_ms": 3.73002, "cand_ms": 129.40813, "n_trials": 14, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 232.03, "compile_s": 2.03, "r_error": "", "src_len": 2297, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 1651, "ts": 1791530328.537832, "chk": "incorrect", "code_len": 2592}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7272, "tout": 1442, "ts": 1791530403.0394316, "chk": "ok", "code_len": 2295}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8823, "tout": 1416, "ts": 1791530425.259587, "chk": "ok", "code_len": 2297}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10349, "tout": 52, "ts": 1791530440.9666896, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 10448, "tout": 1123, "ts": 1791530450.316802, "chk": null, "code_len": 2297}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", "no_code", null], "first_tin": 5488, "started": 1791530310.9937916}
{"ep": "h1-00841", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2808, "speedup": 1.2808, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 216.0, "calls": 2, "tokens_in": 13130, "tokens_out": 2278, "ctx_chars": 9893, "t_end": 1791530691.652394, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2808, "lo95": 1.2792, "mean": 1.2793, "ev_only": 1.2821, "ref_ms": 19.79224, "cand_ms": 15.45329, "n_trials": 72, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0405, "r_wall_s": 94.45, "compile_s": 2.02, "r_error": "", "src_len": 1581, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5991, "tout": 1462, "ts": 1791530489.145875, "chk": "ok", "code_len": 1581}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7139, "tout": 816, "ts": 1791530596.345231, "chk": null, "code_len": 1581}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5991, "started": 1791530475.6971595}
{"ep": "h1-00871", "task": "L3_004", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.96, "speedup": 0.96, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 141.2, "calls": 3, "tokens_in": 13003, "tokens_out": 6517, "ctx_chars": 0, "t_end": 1791530703.4314966, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.96, "lo95": 0.9582, "mean": 1.0138, "ev_only": 0.9666, "ref_ms": 2.36452, "cand_ms": 2.46313, "n_trials": 181, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0697, "r_wall_s": 47.64, "compile_s": 1.91, "r_error": "", "src_len": 2930, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2013, "tout": 1671, "ts": 1791530576.9680495, "chk": "incorrect", "code_len": 2906}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3818, "tout": 3242, "ts": 1791530632.8376095, "chk": "ok", "code_len": 2930}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7172, "tout": 1604, "ts": 1791530655.7633426, "chk": null, "code_len": 2930}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2013, "started": 1791530562.2774837}
{"ep": "h1-00862", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.4763, "speedup": 9.4763, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 175.6, "calls": 2, "tokens_in": 5038, "tokens_out": 3493, "ctx_chars": 0, "t_end": 1791530703.5529716, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 9.4763, "lo95": 9.4158, "mean": 9.2424, "ev_only": 9.4698, "ref_ms": 8.0256, "cand_ms": 0.84691, "n_trials": 159, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.306, "r_wall_s": 72.88, "compile_s": 2.31, "r_error": "", "src_len": 2073, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1739, "tout": 2290, "ts": 1791530578.6715822, "chk": "ok", "code_len": 2073}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3299, "tout": 1203, "ts": 1791530630.6288373, "chk": null, "code_len": 2073}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1739, "started": 1791530548.2974882}
{"ep": "h1-00863", "task": "L2_051", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 27.5898, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.1, "calls": 2, "tokens_in": 5820, "tokens_out": 5217, "ctx_chars": 0, "t_end": 1791530717.1701634, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 27.5898, "lo95": 27.0614, "mean": 19.9844, "ev_only": 29.7455, "ref_ms": 16.21037, "cand_ms": 0.58755, "n_trials": 79, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 57.69, "compile_s": 1.96, "r_error": "", "src_len": 3298, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1708, "tout": 3450, "ts": 1791530558.9659963, "chk": "ok", "code_len": 3298}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4112, "tout": 1767, "ts": 1791530659.2736592, "chk": null, "code_len": 3298}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1708, "started": 1791530528.0790687}
{"ep": "h1-00848", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2526, "speedup": 1.2526, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.1, "calls": 2, "tokens_in": 8339, "tokens_out": 12623, "ctx_chars": 0, "t_end": 1791530717.3943777, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2526, "lo95": 1.2479, "mean": 1.0904, "ev_only": 1.2497, "ref_ms": 5.25794, "cand_ms": 4.19758, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1749, "r_wall_s": 52.84, "compile_s": 2.63, "r_error": "", "src_len": 7355, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1974, "tout": 8834, "ts": 1791530578.233942, "chk": "ok", "code_len": 7355}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6365, "tout": 3789, "ts": 1791530664.0130227, "chk": null, "code_len": 7355}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1974, "started": 1791530500.2924283}
{"ep": "h1-00783", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 8.1065, "speedup": 8.1065, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 484.0, "calls": 3, "tokens_in": 29826, "tokens_out": 22612, "ctx_chars": 8224, "t_end": 1791530726.7375348, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 8.1065, "lo95": 7.3602, "mean": 8.2743, "ev_only": 8.1466, "ref_ms": 38.01078, "cand_ms": 4.68892, "n_trials": 40, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 31.87, "compile_s": 13.02, "r_error": "", "src_len": 8283, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 13844, "ts": 1791530365.7899253, "chk": "no_custom_kernel", "code_len": 8332}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10063, "tout": 4582, "ts": 1791530514.3466053, "chk": "ok", "code_len": 8283}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14273, "tout": 4186, "ts": 1791530694.8248622, "chk": null, "code_len": 8283}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791530242.7121005}
{"ep": "h1-00881", "task": "L1_014", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5432, "speedup": 1.5432, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.2, "calls": 5, "tokens_in": 24922, "tokens_out": 6251, "ctx_chars": 0, "t_end": 1791530728.3871565, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.5432, "lo95": 1.5405, "mean": 1.5441, "ev_only": 1.5403, "ref_ms": 7.36767, "cand_ms": 4.77443, "n_trials": 214, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9903, "r_wall_s": 23.47, "compile_s": 2.48, "r_error": "", "src_len": 2165, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1676, "tout": 1525, "ts": 1791530620.7712955, "chk": "incorrect", "code_len": 2543}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3333, "tout": 2216, "ts": 1791530655.4695733, "chk": "incorrect", "code_len": 2147}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5681, "tout": 1290, "ts": 1791530676.8299417, "chk": "ok", "code_len": 2165}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7080, "tout": 25, "ts": 1791530686.700017, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7152, "tout": 1195, "ts": 1791530704.727634, "chk": null, "code_len": 2165}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 1676, "started": 1791530606.1403234}
{"ep": "h1-00903", "task": "L2_074", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 64.6, "calls": 1, "tokens_in": 1843, "tokens_out": 1478, "ctx_chars": 0, "t_end": 1791530729.2005868, "error": "RuntimeError: Error building extension 'fused_lrelu_pool': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_lrelu_pool -DTORCH_API_INCLUDE_EXTENSION_H -", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 49.96, "compile_s": 49.95, "r_error": "RuntimeError: Error building extension 'fused_lrelu_pool': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_lrelu_pool -DTORCH_API_INCLUDE_EXTENSION_H -", "src_len": 2935, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1843, "tout": 1478, "ts": 1791530679.2163472, "chk": null, "code_len": 2935}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1843, "started": 1791530664.6329257}
{"ep": "h1-00884", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.6694, "speedup": 4.6694, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 125.0, "calls": 2, "tokens_in": 5015, "tokens_out": 4251, "ctx_chars": 0, "t_end": 1791530735.5631986, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.6694, "lo95": 4.66, "mean": 4.6257, "ev_only": 4.7213, "ref_ms": 7.38995, "cand_ms": 1.58264, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 46.33, "compile_s": 1.96, "r_error": "", "src_len": 2525, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1678, "tout": 3025, "ts": 1791530638.4001746, "chk": "ok", "code_len": 2525}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3337, "tout": 1226, "ts": 1791530689.0441663, "chk": null, "code_len": 2525}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1678, "started": 1791530610.5809216}
{"ep": "h1-00842", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1955, "speedup": 1.1955, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 259.2, "calls": 2, "tokens_in": 7984, "tokens_out": 8791, "ctx_chars": 0, "t_end": 1791530736.9889762, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1955, "lo95": 1.195, "mean": 1.1953, "ev_only": 1.1965, "ref_ms": 8.33583, "cand_ms": 6.97295, "n_trials": 151, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0701, "r_wall_s": 14.42, "compile_s": 1.81, "r_error": "", "src_len": 5468, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2192, "tout": 5770, "ts": 1791530526.2097876, "chk": "ok", "code_len": 5468}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5792, "tout": 3021, "ts": 1791530722.459177, "chk": null, "code_len": 5468}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2192, "started": 1791530477.8316495}
{"ep": "h1-00811", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.0726, "speedup": 2.0726, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 405.1, "calls": 2, "tokens_in": 17471, "tokens_out": 10997, "ctx_chars": 10384, "t_end": 1791530742.7691844, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.0726, "lo95": 2.0538, "mean": 2.0449, "ev_only": 2.073, "ref_ms": 4.07353, "cand_ms": 1.96542, "n_trials": 199, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4995, "r_wall_s": 275.24, "compile_s": 3.83, "r_error": "", "src_len": 4440, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 8758, "ts": 1791530440.0786178, "chk": "ok", "code_len": 4442}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10174, "tout": 2239, "ts": 1791530467.304009, "chk": null, "code_len": 4440}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791530358.0041938}
{"ep": "h1-00869", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6577, "speedup": 1.6577, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 185.8, "calls": 2, "tokens_in": 14073, "tokens_out": 6472, "ctx_chars": 9590, "t_end": 1791530743.3232348, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.6577, "lo95": 1.6562, "mean": 1.658, "ev_only": 1.6585, "ref_ms": 5.6359, "cand_ms": 3.39989, "n_trials": 206, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3318, "r_wall_s": 115.1, "compile_s": 2.09, "r_error": "", "src_len": 4152, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5717, "tout": 4289, "ts": 1791530594.3322818, "chk": "ok", "code_len": 4152}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8356, "tout": 2183, "ts": 1791530627.0993884, "chk": null, "code_len": 4152}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5717, "started": 1791530557.563568}
{"ep": "h1-00784", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4734, "speedup": 0.4734, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 507.0, "calls": 3, "tokens_in": 15322, "tokens_out": 11841, "ctx_chars": 0, "t_end": 1791530758.2372036, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4734, "lo95": 0.4732, "mean": 0.4735, "ev_only": 0.4729, "ref_ms": 3.29643, "cand_ms": 6.96401, "n_trials": 225, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 229.68, "compile_s": 19.69, "r_error": "", "src_len": 5389, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2031, "tout": 6123, "ts": 1791530305.8461826, "chk": "no_custom_kernel", "code_len": 5524}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5255, "tout": 3047, "ts": 1791530456.66828, "chk": "ok", "code_len": 5389}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8036, "tout": 2671, "ts": 1791530527.7618518, "chk": null, "code_len": 5389}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2031, "started": 1791530251.2198308}
{"ep": "h1-00856", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.0683, "speedup": 0.0683, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.9, "calls": 2, "tokens_in": 15047, "tokens_out": 7638, "ctx_chars": 11023, "t_end": 1791530766.1739419, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0683, "lo95": 0.068, "mean": 0.0687, "ev_only": 0.068, "ref_ms": 12.96705, "cand_ms": 189.96976, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 137.79, "compile_s": 2.2, "r_error": "", "src_len": 3233, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6480, "tout": 5946, "ts": 1791530576.7465703, "chk": "ok", "code_len": 3233}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8567, "tout": 1692, "ts": 1791530628.3354247, "chk": null, "code_len": 3233}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6480, "started": 1791530522.3044388}
{"ep": "h1-00909", "task": "L2_095", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.042, "speedup": 1.042, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 67.3, "calls": 1, "tokens_in": 1668, "tokens_out": 746, "ctx_chars": 0, "t_end": 1791530770.850091, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.042, "lo95": 1.0419, "mean": 1.0646, "ev_only": 1.0408, "ref_ms": 8.23445, "cand_ms": 7.90218, "n_trials": 193, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 59.8, "compile_s": 2.07, "r_error": "", "src_len": 1309, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1668, "tout": 746, "ts": 1791530710.9714923, "chk": null, "code_len": 1309}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1668, "started": 1791530703.553197}
{"ep": "h1-00910", "task": "L1_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 56.4, "calls": 1, "tokens_in": 1562, "tokens_out": 721, "ctx_chars": 0, "t_end": 1791530773.5866191, "error": "RuntimeError: Error building extension 'gelu_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 28.62, "compile_s": 28.61, "r_error": "RuntimeError: Error building extension 'gelu_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gelu_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-p", "src_len": 1439, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1562, "tout": 721, "ts": 1791530744.7174551, "chk": null, "code_len": 1439}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1562, "started": 1791530737.5198977}
{"ep": "h1-00896", "task": "L3_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5748, "speedup": 0.5748, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 127.9, "calls": 3, "tokens_in": 22079, "tokens_out": 4594, "ctx_chars": 6513, "t_end": 1791530780.4427934, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.5748, "lo95": 0.4825, "mean": 0.4778, "ev_only": 0.574, "ref_ms": 21.17017, "cand_ms": 36.83276, "n_trials": 40, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0263, "r_wall_s": 37.98, "compile_s": 2.21, "r_error": "", "src_len": 5297, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5725, "tout": 2315, "ts": 1791530671.766939, "chk": "ok", "code_len": 5297}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8152, "tout": 26, "ts": 1791530724.3837297, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8202, "tout": 2253, "ts": 1791530742.4234855, "chk": null, "code_len": 5297}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5725, "started": 1791530652.5552225}
{"ep": "h1-00890", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0179, "speedup": 1.0179, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 150.3, "calls": 2, "tokens_in": 4219, "tokens_out": 1605, "ctx_chars": 0, "t_end": 1791530781.0700257, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0179, "lo95": 1.0167, "mean": 1.0174, "ev_only": 1.0175, "ref_ms": 8.13224, "cand_ms": 7.98941, "n_trials": 71, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0049, "r_wall_s": 64.85, "compile_s": 2.08, "r_error": "", "src_len": 870, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1670, "tout": 1102, "ts": 1791530641.1186562, "chk": "ok", "code_len": 870}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2549, "tout": 503, "ts": 1791530716.1234088, "chk": null, "code_len": 870}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1670, "started": 1791530630.797133}
{"ep": "h1-00864", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.6511, "speedup": 1.6511, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.8, "calls": 2, "tokens_in": 6431, "tokens_out": 6388, "ctx_chars": 0, "t_end": 1791530783.9538696, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.6511, "lo95": 1.6488, "mean": 1.6548, "ev_only": 1.6486, "ref_ms": 20.78944, "cand_ms": 12.59113, "n_trials": 56, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 111.09, "compile_s": 3.15, "r_error": "", "src_len": 3392, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 4556, "ts": 1791530568.3437312, "chk": "ok", "code_len": 3392}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4428, "tout": 1832, "ts": 1791530672.8122098, "chk": null, "code_len": 3392}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791530528.124405}
{"ep": "h1-00828", "task": "L3_044", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3806, "speedup": 1.3806, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 393.9, "calls": 4, "tokens_in": 26622, "tokens_out": 8462, "ctx_chars": 0, "t_end": 1791530789.0196118, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3806, "lo95": 1.3787, "mean": 1.3804, "ev_only": 1.3803, "ref_ms": 75.39625, "cand_ms": 54.61077, "n_trials": 17, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0322, "r_wall_s": 79.74, "compile_s": 2.37, "r_error": "", "src_len": 3605, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3019, "tout": 2372, "ts": 1791530416.8060248, "chk": "runtime_error", "code_len": 3827}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5687, "tout": 2023, "ts": 1791530440.3287756, "chk": "ok", "code_len": 3733}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7822, "tout": 2160, "ts": 1791530475.5054688, "chk": "ok", "code_len": 3605}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10094, "tout": 1907, "ts": 1791530708.9466221, "chk": null, "code_len": 3605}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "ok", null], "first_tin": 3019, "started": 1791530395.0835073}
{"ep": "h1-00893", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.333, "speedup": 1.333, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 148.3, "calls": 2, "tokens_in": 15486, "tokens_out": 4581, "ctx_chars": 11357, "t_end": 1791530793.03236, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.333, "lo95": 1.3325, "mean": 1.3332, "ev_only": 1.3309, "ref_ms": 7.51563, "cand_ms": 5.63833, "n_trials": 176, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.105, "r_wall_s": 47.69, "compile_s": 3.33, "r_error": "", "src_len": 2742, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6781, "tout": 3169, "ts": 1791530674.2864263, "chk": "ok", "code_len": 2742}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8705, "tout": 1412, "ts": 1791530744.6614385, "chk": null, "code_len": 2742}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6781, "started": 1791530644.7577834}
{"ep": "h1-00874", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.0355, "speedup": 3.0355, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 220.9, "calls": 3, "tokens_in": 17512, "tokens_out": 15898, "ctx_chars": 0, "t_end": 1791530793.2101555, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.0355, "lo95": 3.0075, "mean": 3.655, "ev_only": 3.0358, "ref_ms": 60.38409, "cand_ms": 19.89265, "n_trials": 11, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8743, "r_wall_s": 56.58, "compile_s": 16.94, "r_error": "", "src_len": 6736, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1959, "tout": 9002, "ts": 1791530652.6578994, "chk": "no_custom_kernel", "code_len": 6758}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6039, "tout": 3563, "ts": 1791530692.8423698, "chk": "ok", "code_len": 6736}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9514, "tout": 3333, "ts": 1791530736.5551176, "chk": null, "code_len": 6736}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1959, "started": 1791530572.314125}
{"ep": "h1-00882", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.466, "speedup": 1.466, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 185.9, "calls": 2, "tokens_in": 12871, "tokens_out": 4651, "ctx_chars": 9033, "t_end": 1791530793.8929517, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.466, "lo95": 1.4638, "mean": 1.4604, "ev_only": 1.468, "ref_ms": 7.54881, "cand_ms": 5.14921, "n_trials": 199, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 59.84, "compile_s": 1.86, "r_error": "", "src_len": 2664, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 2933, "ts": 1791530633.2131495, "chk": "ok", "code_len": 2664}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7381, "tout": 1718, "ts": 1791530733.8943186, "chk": null, "code_len": 2664}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791530607.986278}
{"ep": "h1-00873", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0458, "speedup": 1.0458, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 229.5, "calls": 2, "tokens_in": 15857, "tokens_out": 3800, "ctx_chars": 10864, "t_end": 1791530798.7951925, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0458, "lo95": 1.0448, "mean": 1.0706, "ev_only": 1.0432, "ref_ms": 3.74164, "cand_ms": 3.57782, "n_trials": 203, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 151.88, "compile_s": 2.79, "r_error": "", "src_len": 3181, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6949, "tout": 2183, "ts": 1791530586.4592993, "chk": "ok", "code_len": 3181}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8908, "tout": 1617, "ts": 1791530646.1261141, "chk": null, "code_len": 3181}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6949, "started": 1791530569.3399403}
{"ep": "h1-00849", "task": "L1_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.0741, "speedup": 0.0741, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 303.1, "calls": 2, "tokens_in": 15819, "tokens_out": 2496, "ctx_chars": 13278, "t_end": 1791530806.84045, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0741, "lo95": 0.0737, "mean": 0.0798, "ev_only": 0.0733, "ref_ms": 5.49103, "cand_ms": 74.12927, "n_trials": 18, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 116.86, "compile_s": 3.04, "r_error": "", "src_len": 2326, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7160, "tout": 1390, "ts": 1791530517.933178, "chk": "ok", "code_len": 2326}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8659, "tout": 1106, "ts": 1791530689.2460117, "chk": null, "code_len": 2326}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7160, "started": 1791530503.7381546}
{"ep": "h1-00857", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.1495, "speedup": 3.1495, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 287.7, "calls": 2, "tokens_in": 8073, "tokens_out": 7813, "ctx_chars": 0, "t_end": 1791530811.3371048, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 3.1495, "lo95": 3.1477, "mean": 3.1367, "ev_only": 3.1459, "ref_ms": 3.74413, "cand_ms": 1.18882, "n_trials": 209, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 150.23, "compile_s": 60.43, "r_error": "", "src_len": 5954, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2325, "tout": 4871, "ts": 1791530566.7942054, "chk": "ok", "code_len": 5954}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5748, "tout": 2942, "ts": 1791530660.289178, "chk": null, "code_len": 5954}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2325, "started": 1791530523.6441867}
{"ep": "h1-00796", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7002, "speedup": 0.7002, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 526.6, "calls": 2, "tokens_in": 14301, "tokens_out": 27160, "ctx_chars": 0, "t_end": 1791530818.010793, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7002, "lo95": 0.699, "mean": 0.7026, "ev_only": 0.7004, "ref_ms": 20.11004, "cand_ms": 28.72187, "n_trials": 54, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.7903, "r_wall_s": 61.01, "compile_s": 2.28, "r_error": "", "src_len": 12806, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 20599, "ts": 1791530474.8145428, "chk": "ok", "code_len": 12806}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10708, "tout": 6561, "ts": 1791530756.8456385, "chk": null, "code_len": 12806}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3593, "started": 1791530291.4002283}
{"ep": "h1-00830", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.8219, "speedup": 1.8219, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 412.7, "calls": 3, "tokens_in": 13790, "tokens_out": 11556, "ctx_chars": 0, "t_end": 1791530818.5047455, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.8219, "lo95": 1.8192, "mean": 1.8152, "ev_only": 1.8249, "ref_ms": 19.17033, "cand_ms": 10.52203, "n_trials": 74, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 112.94, "compile_s": 14.14, "r_error": "", "src_len": 5028, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1586, "tout": 6107, "ts": 1791530459.200126, "chk": "no_custom_kernel", "code_len": 5027}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4729, "tout": 2815, "ts": 1791530513.494866, "chk": "ok", "code_len": 5028}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7475, "tout": 2634, "ts": 1791530705.4892876, "chk": null, "code_len": 5028}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1586, "started": 1791530405.8001368}
{"ep": "h1-00880", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2345, "speedup": 1.2345, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.2, "calls": 2, "tokens_in": 16206, "tokens_out": 3884, "ctx_chars": 12471, "t_end": 1791530819.8485248, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2345, "lo95": 1.2332, "mean": 1.2385, "ev_only": 1.237, "ref_ms": 3.63707, "cand_ms": 2.94609, "n_trials": 178, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 76.2, "compile_s": 1.87, "r_error": "", "src_len": 2399, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7230, "tout": 2638, "ts": 1791530629.282021, "chk": "ok", "code_len": 2399}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8976, "tout": 1246, "ts": 1791530742.8197913, "chk": null, "code_len": 2399}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7230, "started": 1791530604.666247}
{"ep": "h1-00867", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.9851, "speedup": 3.9851, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 270.3, "calls": 2, "tokens_in": 7443, "tokens_out": 12056, "ctx_chars": 0, "t_end": 1791530820.4128985, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.9851, "lo95": 3.9832, "mean": 3.9813, "ev_only": 3.9871, "ref_ms": 20.00483, "cand_ms": 5.01993, "n_trials": 76, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 67.46, "compile_s": 11.97, "r_error": "", "src_len": 6615, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1729, "tout": 8852, "ts": 1791530630.503986, "chk": "ok", "code_len": 6712}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5714, "tout": 3204, "ts": 1791530752.8466837, "chk": null, "code_len": 6615}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1729, "started": 1791530550.0980651}
{"ep": "h1-00801", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.0392, "speedup": 9.0392, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 512.5, "calls": 3, "tokens_in": 14742, "tokens_out": 13521, "ctx_chars": 0, "t_end": 1791530821.2949238, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 9.0392, "lo95": 8.9094, "mean": 8.6042, "ev_only": 9.2144, "ref_ms": 5.98077, "cand_ms": 0.66165, "n_trials": 214, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.988, "r_wall_s": 106.43, "compile_s": 12.67, "r_error": "", "src_len": 5435, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1845, "tout": 7968, "ts": 1791530380.9053226, "chk": "no_custom_kernel", "code_len": 5455}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5043, "tout": 2861, "ts": 1791530468.4474502, "chk": "ok", "code_len": 5435}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7854, "tout": 2692, "ts": 1791530714.793614, "chk": null, "code_len": 5435}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1845, "started": 1791530308.8254073}
{"ep": "h1-00875", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7556, "speedup": 0.7556, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.3, "calls": 2, "tokens_in": 17712, "tokens_out": 13232, "ctx_chars": 6513, "t_end": 1791530828.0795188, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7556, "lo95": 0.7539, "mean": 0.7557, "ev_only": 0.7551, "ref_ms": 19.96321, "cand_ms": 26.41994, "n_trials": 47, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2038, "r_wall_s": 127.32, "compile_s": 5.51, "r_error": "", "src_len": 9356, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6296, "tout": 8547, "ts": 1791530642.8977878, "chk": "ok", "code_len": 9356}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11416, "tout": 4685, "ts": 1791530700.73277, "chk": null, "code_len": 9356}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6296, "started": 1791530572.749805}
{"ep": "h1-00892", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3863, "speedup": 1.3863, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 199.6, "calls": 2, "tokens_in": 7005, "tokens_out": 8288, "ctx_chars": 0, "t_end": 1791530838.58998, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3863, "lo95": 1.3836, "mean": 1.3854, "ev_only": 1.3856, "ref_ms": 11.06674, "cand_ms": 7.9831, "n_trials": 88, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1693, "r_wall_s": 111.5, "compile_s": 15.38, "r_error": "", "src_len": 6627, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1619, "tout": 5082, "ts": 1791530679.8841553, "chk": "ok", "code_len": 6627}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5386, "tout": 3206, "ts": 1791530726.314804, "chk": null, "code_len": 6627}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1619, "started": 1791530639.0092602}
{"ep": "h1-00887", "task": "L1_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7216, "speedup": 0.7216, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.3, "calls": 2, "tokens_in": 15253, "tokens_out": 2651, "ctx_chars": 11175, "t_end": 1791530838.6946936, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7216, "lo95": 0.7163, "mean": 0.7327, "ev_only": 0.7273, "ref_ms": 3.36932, "cand_ms": 4.66928, "n_trials": 173, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0007, "r_wall_s": 106.68, "compile_s": 1.99, "r_error": "", "src_len": 2275, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6880, "tout": 1586, "ts": 1791530635.0345805, "chk": "ok", "code_len": 2275}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8373, "tout": 1065, "ts": 1791530730.8324938, "chk": null, "code_len": 2275}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6880, "started": 1791530621.3947902}
{"ep": "h1-00922", "task": "L3_042", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 66.2, "calls": 1, "tokens_in": 1957, "tokens_out": 921, "ctx_chars": 0, "t_end": 1791530839.812633, "error": "RuntimeError: Error building extension 'gru_copy_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gru_copy_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 56.53, "compile_s": 56.53, "r_error": "RuntimeError: Error building extension 'gru_copy_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gru_copy_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 1444, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1957, "tout": 921, "ts": 1791530783.257924, "chk": null, "code_len": 1444}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1957, "started": 1791530773.5869405}
{"ep": "h1-00838", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 8.1903, "speedup": 8.1903, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 377.1, "calls": 3, "tokens_in": 32736, "tokens_out": 24519, "ctx_chars": 8224, "t_end": 1791530843.1934211, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 8.1903, "lo95": 6.207, "mean": 7.6972, "ev_only": 8.245, "ref_ms": 45.42376, "cand_ms": 5.54607, "n_trials": 52, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 59.64, "compile_s": 12.2, "r_error": "", "src_len": 9910, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5510, "tout": 13770, "ts": 1791530605.486663, "chk": "no_custom_kernel", "code_len": 9812}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10967, "tout": 5864, "ts": 1791530666.9709387, "chk": "ok", "code_len": 9910}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16259, "tout": 4885, "ts": 1791530783.526491, "chk": null, "code_len": 9910}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5510, "started": 1791530486.4847772}
{"ep": "h1-00883", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2356, "speedup": 1.2356, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 263.9, "calls": 2, "tokens_in": 4787, "tokens_out": 3823, "ctx_chars": 0, "t_end": 1791530872.9845886, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2356, "lo95": 1.233, "mean": 1.2297, "ev_only": 1.2333, "ref_ms": 2.87841, "cand_ms": 2.32962, "n_trials": 225, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 66.46, "compile_s": 2.52, "r_error": "", "src_len": 2217, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 2383, "ts": 1791530629.4544654, "chk": "ok", "code_len": 2217}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3198, "tout": 1440, "ts": 1791530806.421462, "chk": null, "code_len": 2217}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791530609.1323433}
{"ep": "h1-00879", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.8056, "speedup": 2.8056, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 275.2, "calls": 2, "tokens_in": 12769, "tokens_out": 1906, "ctx_chars": 9855, "t_end": 1791530875.0616663, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.8056, "lo95": 2.8024, "mean": 2.7133, "ev_only": 2.8094, "ref_ms": 6.29829, "cand_ms": 2.2449, "n_trials": 206, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4122, "r_wall_s": 80.74, "compile_s": 2.77, "r_error": "", "src_len": 1118, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 1289, "ts": 1791530611.8431146, "chk": "ok", "code_len": 1118}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6923, "tout": 617, "ts": 1791530793.3899028, "chk": null, "code_len": 1118}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791530599.8293502}
{"ep": "h1-00936", "task": "L2_081", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0291, "speedup": 1.0291, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 55.2, "calls": 1, "tokens_in": 6547, "tokens_out": 526, "ctx_chars": 10901, "t_end": 1791530875.606466, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0291, "lo95": 1.0268, "mean": 1.0332, "ev_only": 1.0329, "ref_ms": 8.33946, "cand_ms": 8.10346, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0022, "r_wall_s": 50.04, "compile_s": 2.32, "r_error": "", "src_len": 971, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6547, "tout": 526, "ts": 1791530825.4894297, "chk": null, "code_len": 971}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6547, "started": 1791530820.4131324}
{"ep": "h1-00855", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0109, "speedup": 1.0109, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 357.7, "calls": 2, "tokens_in": 3860, "tokens_out": 2321, "ctx_chars": 0, "t_end": 1791530877.9802806, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0109, "lo95": 1.0065, "mean": 1.0094, "ev_only": 1.0092, "ref_ms": 8.04889, "cand_ms": 7.96195, "n_trials": 174, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0042, "r_wall_s": 79.1, "compile_s": 3.16, "r_error": "", "src_len": 873, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1520, "tout": 1773, "ts": 1791530538.1656294, "chk": "ok", "code_len": 873}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2340, "tout": 548, "ts": 1791530798.8053863, "chk": null, "code_len": 873}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1520, "started": 1791530520.2767448}
{"ep": "h1-00913", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1697, "speedup": 1.1697, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 151.6, "calls": 2, "tokens_in": 8104, "tokens_out": 11377, "ctx_chars": 0, "t_end": 1791530880.0369864, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1697, "lo95": 1.1687, "mean": 1.1851, "ev_only": 1.1714, "ref_ms": 5.24093, "cand_ms": 4.4807, "n_trials": 203, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1754, "r_wall_s": 32.49, "compile_s": 1.82, "r_error": "", "src_len": 7065, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1974, "tout": 7726, "ts": 1791530794.4181979, "chk": "ok", "code_len": 7065}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6130, "tout": 3651, "ts": 1791530847.2735238, "chk": null, "code_len": 7065}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1974, "started": 1791530728.3874252}
{"ep": "h1-00832", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 22.9987, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 466.6, "calls": 3, "tokens_in": 15416, "tokens_out": 11827, "ctx_chars": 0, "t_end": 1791530881.580276, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 22.9987, "lo95": 22.0686, "mean": 22.4224, "ev_only": 22.9658, "ref_ms": 25.14847, "cand_ms": 1.09347, "n_trials": 66, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 164.58, "compile_s": 17.79, "r_error": "", "src_len": 5524, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1755, "tout": 5810, "ts": 1791530464.5796745, "chk": "no_custom_kernel", "code_len": 5539}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5309, "tout": 3066, "ts": 1791530523.1938212, "chk": "ok", "code_len": 5524}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8352, "tout": 2951, "ts": 1791530716.8255513, "chk": null, "code_len": 5524}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1755, "started": 1791530414.9410686}
{"ep": "h1-00897", "task": "L2_084", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9784, "speedup": 0.9784, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 228.9, "calls": 3, "tokens_in": 20606, "tokens_out": 2998, "ctx_chars": 9192, "t_end": 1791530882.7991016, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9784, "lo95": 0.9775, "mean": 1.0248, "ev_only": 0.9801, "ref_ms": 8.17773, "cand_ms": 8.35867, "n_trials": 141, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0183, "r_wall_s": 33.12, "compile_s": 2.04, "r_error": "", "src_len": 2677, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5719, "tout": 1569, "ts": 1791530668.4953907, "chk": "ok", "code_len": 2677}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7400, "tout": 63, "ts": 1791530838.2189236, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7487, "tout": 1366, "ts": 1791530849.576608, "chk": null, "code_len": 2677}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5719, "started": 1791530653.9241302}
{"ep": "h1-00925", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0162, "speedup": 1.0162, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 99.3, "calls": 2, "tokens_in": 12025, "tokens_out": 1208, "ctx_chars": 9220, "t_end": 1791530883.240971, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0162, "lo95": 1.0151, "mean": 1.0144, "ev_only": 1.016, "ref_ms": 8.076, "cand_ms": 7.94701, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0042, "r_wall_s": 74.57, "compile_s": 3.27, "r_error": "", "src_len": 913, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5602, "tout": 709, "ts": 1791530790.231955, "chk": "ok", "code_len": 913}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6423, "tout": 499, "ts": 1791530808.5978353, "chk": null, "code_len": 913}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5602, "started": 1791530783.9541185}
{"ep": "h1-00852", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0661, "speedup": 1.0661, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 368.8, "calls": 2, "tokens_in": 13683, "tokens_out": 1938, "ctx_chars": 10191, "t_end": 1791530883.3924158, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0661, "lo95": 1.0618, "mean": 1.0657, "ev_only": 1.0664, "ref_ms": 8.6546, "cand_ms": 8.11774, "n_trials": 168, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0056, "r_wall_s": 197.34, "compile_s": 2.87, "r_error": "", "src_len": 1621, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6250, "tout": 1071, "ts": 1791530523.9009564, "chk": "ok", "code_len": 1621}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7433, "tout": 867, "ts": 1791530685.982833, "chk": null, "code_len": 1621}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6250, "started": 1791530514.5552497}
{"ep": "h1-00908", "task": "L1_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9862, "speedup": 0.9862, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.3, "calls": 2, "tokens_in": 12899, "tokens_out": 3374, "ctx_chars": 9033, "t_end": 1791530892.7141616, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9862, "lo95": 0.9821, "mean": 1.0073, "ev_only": 0.9864, "ref_ms": 8.05016, "cand_ms": 8.16258, "n_trials": 150, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 114.66, "compile_s": 2.22, "r_error": "", "src_len": 2783, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 1817, "ts": 1791530720.795911, "chk": "ok", "code_len": 2861}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7413, "tout": 1557, "ts": 1791530777.8720179, "chk": null, "code_len": 2783}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5486, "started": 1791530703.4317448}
{"ep": "h1-00937", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0299, "speedup": 1.0299, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.7, "calls": 2, "tokens_in": 5663, "tokens_out": 5532, "ctx_chars": 0, "t_end": 1791530894.9675214, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0299, "lo95": 1.0296, "mean": 1.0457, "ev_only": 1.0306, "ref_ms": 8.21855, "cand_ms": 7.98013, "n_trials": 162, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.011, "r_wall_s": 17.24, "compile_s": 1.88, "r_error": "", "src_len": 3533, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1730, "tout": 3764, "ts": 1791530855.6057224, "chk": "ok", "code_len": 3604}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3933, "tout": 1768, "ts": 1791530877.6520176, "chk": null, "code_len": 3533}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1730, "started": 1791530821.2951677}
{"ep": "h1-00888", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.136, "speedup": 3.136, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 278.3, "calls": 2, "tokens_in": 14628, "tokens_out": 3704, "ctx_chars": 10362, "t_end": 1791530904.009591, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.136, "lo95": 3.1325, "mean": 2.9224, "ev_only": 3.177, "ref_ms": 2.92645, "cand_ms": 0.93317, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 142.92, "compile_s": 2.89, "r_error": "", "src_len": 2801, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6379, "tout": 2277, "ts": 1791530646.4469938, "chk": "ok", "code_len": 2801}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8249, "tout": 1427, "ts": 1791530760.0579247, "chk": null, "code_len": 2801}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6379, "started": 1791530625.7570496}
{"ep": "h1-00894", "task": "L2_003", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2101, "speedup": 1.2101, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.4, "calls": 1, "tokens_in": 1900, "tokens_out": 1869, "ctx_chars": 0, "t_end": 1791530904.3899028, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2101, "lo95": 1.2084, "mean": 1.2143, "ev_only": 1.2125, "ref_ms": 28.94979, "cand_ms": 23.92398, "n_trials": 48, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1882, "r_wall_s": 238.29, "compile_s": 3.08, "r_error": "", "src_len": 1690, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1900, "tout": 1869, "ts": 1791530665.7189643, "chk": null, "code_len": 1690}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1900, "started": 1791530646.0207214}
{"ep": "h1-00939", "task": "L2_097", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9911, "speedup": 0.9911, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 66.3, "calls": 3, "tokens_in": 19801, "tokens_out": 3102, "ctx_chars": 8449, "t_end": 1791530904.8748362, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9911, "lo95": 0.9903, "mean": 1.0272, "ev_only": 0.993, "ref_ms": 8.27362, "cand_ms": 8.34832, "n_trials": 154, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0161, "r_wall_s": 26.82, "compile_s": 2.09, "r_error": "", "src_len": 2702, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5357, "tout": 1728, "ts": 1791530856.1218975, "chk": "ok", "code_len": 2702}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7197, "tout": 26, "ts": 1791530866.9423983, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7247, "tout": 1348, "ts": 1791530877.9567149, "chk": null, "code_len": 2702}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5357, "started": 1791530838.5902145}
{"ep": "h1-00900", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6007, "speedup": 1.6007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 253.6, "calls": 2, "tokens_in": 8673, "tokens_out": 6176, "ctx_chars": 3355, "t_end": 1791530911.8934693, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.6007, "lo95": 1.6001, "mean": 1.6003, "ev_only": 1.5993, "ref_ms": 20.43413, "cand_ms": 12.76565, "n_trials": 66, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 74.64, "compile_s": 2.02, "r_error": "", "src_len": 3069, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3296, "tout": 4535, "ts": 1791530699.1790204, "chk": "ok", "code_len": 3069}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5377, "tout": 1641, "ts": 1791530837.2209961, "chk": null, "code_len": 3069}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3296, "started": 1791530658.2801898}
{"ep": "h1-00924", "task": "L3_019", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.296, "speedup": 0.296, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 132.7, "calls": 1, "tokens_in": 5081, "tokens_out": 1843, "ctx_chars": 6513, "t_end": 1791530913.733676, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.296, "lo95": 0.2952, "mean": 0.3, "ev_only": 0.2962, "ref_ms": 3.79339, "cand_ms": 12.81376, "n_trials": 96, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.05, "r_wall_s": 117.15, "compile_s": 2.79, "r_error": "", "src_len": 3805, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5081, "tout": 1843, "ts": 1791530796.562509, "chk": null, "code_len": 3805}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5081, "started": 1791530781.070267}
{"ep": "h1-00916", "task": "L1_085", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9071, "speedup": 1.9071, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 177.4, "calls": 1, "tokens_in": 6947, "tokens_out": 1588, "ctx_chars": 10864, "t_end": 1791530914.3723252, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.9071, "lo95": 1.8841, "mean": 2.0016, "ev_only": 1.8977, "ref_ms": 3.76774, "cand_ms": 1.97565, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 163.11, "compile_s": 3.26, "r_error": "", "src_len": 3410, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6947, "tout": 1588, "ts": 1791530750.3989146, "chk": null, "code_len": 3410}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6947, "started": 1791530736.98922}
{"ep": "h1-00735", "task": "L3_048", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9523, "speedup": 0.9523, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 864.1, "calls": 4, "tokens_in": 89328, "tokens_out": 43318, "ctx_chars": 0, "t_end": 1791530916.0363486, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9523, "lo95": 0.9521, "mean": 0.9523, "ev_only": 0.9526, "ref_ms": 15.89263, "cand_ms": 16.68886, "n_trials": 86, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0704, "r_wall_s": 226.35, "compile_s": 3.37, "r_error": "", "src_len": 3031, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2835, "tout": 12878, "ts": 1791530182.4324672, "chk": "incorrect", "code_len": 6171}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 15850, "tout": 16349, "ts": 1791530449.257601, "chk": "incorrect", "code_len": 6836}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 32335, "tout": 5864, "ts": 1791530563.8317795, "chk": "ok", "code_len": 3069}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 38308, "tout": 8227, "ts": 1791530688.8387241, "chk": null, "code_len": 3031}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2835, "started": 1791530051.8981304}
{"ep": "h1-00850", "task": "L2_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0097, "speedup": 1.0097, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 412.6, "calls": 5, "tokens_in": 51260, "tokens_out": 7790, "ctx_chars": 9898, "t_end": 1791530917.115734, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0097, "lo95": 1.0093, "mean": 1.0305, "ev_only": 1.0104, "ref_ms": 8.03059, "cand_ms": 7.95338, "n_trials": 164, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0028, "r_wall_s": 23.73, "compile_s": 2.2, "r_error": "", "src_len": 854, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6118, "tout": 2175, "ts": 1791530526.6879158, "chk": "incorrect", "code_len": 1090}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8427, "tout": 1749, "ts": 1791530699.3543704, "chk": "incorrect", "code_len": 1168}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 10310, "tout": 1998, "ts": 1791530857.4956858, "chk": "incorrect", "code_len": 1214}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 12442, "tout": 1386, "ts": 1791530880.5510247, "chk": "ok", "code_len": 854}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13963, "tout": 482, "ts": 1791530893.3620234, "chk": null, "code_len": 854}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 6118, "started": 1791530504.552694}
{"ep": "h1-00905", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8071, "speedup": 1.8071, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 254.3, "calls": 2, "tokens_in": 8897, "tokens_out": 4511, "ctx_chars": 2425, "t_end": 1791530919.5294497, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.8071, "lo95": 1.7968, "mean": 1.7878, "ev_only": 1.8058, "ref_ms": 12.72356, "cand_ms": 7.04097, "n_trials": 132, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5525, "r_wall_s": 144.41, "compile_s": 1.96, "r_error": "", "src_len": 2814, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3400, "tout": 2988, "ts": 1791530691.186574, "chk": "ok", "code_len": 2814}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5497, "tout": 1523, "ts": 1791530774.9284337, "chk": null, "code_len": 2814}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3400, "started": 1791530665.2159436}
{"ep": "h1-00914", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.6051, "speedup": 4.6051, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 192.4, "calls": 2, "tokens_in": 4922, "tokens_out": 3973, "ctx_chars": 0, "t_end": 1791530921.5849762, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.6051, "lo95": 4.6041, "mean": 4.5957, "ev_only": 4.6349, "ref_ms": 7.34985, "cand_ms": 1.59602, "n_trials": 198, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 99.73, "compile_s": 3.59, "r_error": "", "src_len": 2436, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1678, "tout": 2806, "ts": 1791530755.128685, "chk": "ok", "code_len": 2436}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3244, "tout": 1167, "ts": 1791530821.118477, "chk": null, "code_len": 2436}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1678, "started": 1791530729.200861}
{"ep": "h1-00836", "task": "L2_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.991, "speedup": 0.991, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 471.4, "calls": 4, "tokens_in": 31902, "tokens_out": 4131, "ctx_chars": 9898, "t_end": 1791530922.149168, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.991, "lo95": 0.9881, "mean": 0.9859, "ev_only": 0.9908, "ref_ms": 8.03941, "cand_ms": 8.11264, "n_trials": 199, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0029, "r_wall_s": 80.28, "compile_s": 3.67, "r_error": "", "src_len": 978, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6118, "tout": 567, "ts": 1791530457.3875933, "chk": "incorrect", "code_len": 918}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6819, "tout": 2047, "ts": 1791530515.8464153, "chk": "incorrect", "code_len": 1062}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9000, "tout": 853, "ts": 1791530684.8133926, "chk": "ok", "code_len": 978}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9965, "tout": 664, "ts": 1791530841.8469603, "chk": null, "code_len": 978}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6118, "started": 1791530450.7327178}
{"ep": "h1-00891", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4479, "speedup": 1.4479, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 290.2, "calls": 3, "tokens_in": 10087, "tokens_out": 7063, "ctx_chars": 0, "t_end": 1791530922.27679, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4479, "lo95": 1.4452, "mean": 1.4542, "ev_only": 1.4595, "ref_ms": 7.57771, "cand_ms": 5.23362, "n_trials": 184, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 155.35, "compile_s": 2.14, "r_error": "", "src_len": 1933, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 3672, "ts": 1791530665.5287127, "chk": "incorrect", "code_len": 2320}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3516, "tout": 2198, "ts": 1791530746.2667453, "chk": "ok", "code_len": 1933}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5004, "tout": 1193, "ts": 1791530766.8308644, "chk": null, "code_len": 1933}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1567, "started": 1791530632.0793774}
{"ep": "h1-00906", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.3405, "speedup": 0.3405, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.2, "calls": 2, "tokens_in": 6518, "tokens_out": 6395, "ctx_chars": 0, "t_end": 1791530923.6004717, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.3405, "lo95": 0.34, "mean": 0.3416, "ev_only": 0.3409, "ref_ms": 9.98389, "cand_ms": 29.32012, "n_trials": 48, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 167.61, "compile_s": 2.92, "r_error": "", "src_len": 3964, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 4384, "ts": 1791530720.8940074, "chk": "ok", "code_len": 4009}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4515, "tout": 2011, "ts": 1791530755.175947, "chk": null, "code_len": 3964}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791530682.3668957}
{"ep": "h1-00947", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0012, "speedup": 1.0012, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 46.4, "calls": 2, "tokens_in": 12564, "tokens_out": 1266, "ctx_chars": 9890, "t_end": 1791530926.4094012, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0012, "lo95": 1.0008, "mean": 1.0288, "ev_only": 1.0028, "ref_ms": 8.04492, "cand_ms": 8.03525, "n_trials": 195, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0048, "r_wall_s": 26.96, "compile_s": 2.06, "r_error": "", "src_len": 1091, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5890, "tout": 675, "ts": 1791530886.25722, "chk": "ok", "code_len": 1091}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6674, "tout": 591, "ts": 1791530899.3522773, "chk": null, "code_len": 1091}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5890, "started": 1791530880.0372307}
{"ep": "h1-00926", "task": "L2_079", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 139.1, "calls": 1, "tokens_in": 1811, "tokens_out": 2668, "ctx_chars": 0, "t_end": 1791530928.0737154, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.4706, "r_wall_s": 114.0, "compile_s": 3.02, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1902, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1811, "tout": 2668, "ts": 1791530814.0401313, "chk": null, "code_len": 1902}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1811, "started": 1791530789.019896}
{"ep": "h1-00950", "task": "L2_056", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 62.6, "calls": 1, "tokens_in": 1572, "tokens_out": 1084, "ctx_chars": 0, "t_end": 1791530945.8863902, "error": "RuntimeError: Error building extension 'sigsum_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=sigsum_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 52.01, "compile_s": 52.0, "r_error": "RuntimeError: Error building extension 'sigsum_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=sigsum_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/", "src_len": 1914, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1572, "tout": 1084, "ts": 1791530893.8533802, "chk": null, "code_len": 1914}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1572, "started": 1791530883.2412207}
{"ep": "h1-00785", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 8.018, "speedup": 8.018, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 693.3, "calls": 3, "tokens_in": 16977, "tokens_out": 15515, "ctx_chars": 0, "t_end": 1791530946.1550264, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 8.018, "lo95": 8.0075, "mean": 7.9715, "ev_only": 8.2151, "ref_ms": 4.38355, "cand_ms": 0.54671, "n_trials": 192, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 257.04, "compile_s": 14.25, "r_error": "", "src_len": 5967, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2218, "tout": 9303, "ts": 1791530335.9375753, "chk": "no_custom_kernel", "code_len": 5987}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5829, "tout": 3270, "ts": 1791530508.5647922, "chk": "ok", "code_len": 5967}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8930, "tout": 2942, "ts": 1791530688.9123511, "chk": null, "code_len": 5967}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2218, "started": 1791530252.8658414}
{"ep": "h1-00902", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.9175, "speedup": 3.9175, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 287.6, "calls": 2, "tokens_in": 7867, "tokens_out": 13315, "ctx_chars": 0, "t_end": 1791530949.8690603, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.9175, "lo95": 3.9144, "mean": 4.0406, "ev_only": 3.9343, "ref_ms": 12.66194, "cand_ms": 3.23216, "n_trials": 112, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9993, "r_wall_s": 130.13, "compile_s": 14.31, "r_error": "", "src_len": 7277, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1863, "tout": 9759, "ts": 1791530748.5605083, "chk": "ok", "code_len": 7294}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6004, "tout": 3556, "ts": 1791530819.4983108, "chk": null, "code_len": 7277}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1863, "started": 1791530662.3016167}
{"ep": "h1-00949", "task": "L2_068", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9843, "speedup": 0.9843, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 67.8, "calls": 1, "tokens_in": 1530, "tokens_out": 822, "ctx_chars": 0, "t_end": 1791530950.6139371, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9843, "lo95": 0.9825, "mean": 1.018, "ev_only": 0.9864, "ref_ms": 4.50571, "cand_ms": 4.57755, "n_trials": 211, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.003, "r_wall_s": 59.77, "compile_s": 45.48, "r_error": "", "src_len": 1702, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1530, "tout": 822, "ts": 1791530890.792291, "chk": null, "code_len": 1702}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1530, "started": 1791530882.79934}
{"ep": "h1-00915", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7544, "speedup": 0.7544, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.0, "calls": 2, "tokens_in": 13032, "tokens_out": 5434, "ctx_chars": 8224, "t_end": 1791530954.5451157, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7544, "lo95": 0.5952, "mean": 0.7402, "ev_only": 0.7538, "ref_ms": 102.12621, "cand_ms": 135.36672, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0, "r_wall_s": 45.4, "compile_s": 2.93, "r_error": "", "src_len": 2656, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5516, "tout": 4003, "ts": 1791530772.3060398, "chk": "ok", "code_len": 2717}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7516, "tout": 1431, "ts": 1791530909.102342, "chk": null, "code_len": 2656}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5516, "started": 1791530735.563495}
{"ep": "h1-00940", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9934, "speedup": 0.9934, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.6, "calls": 2, "tokens_in": 5114, "tokens_out": 4221, "ctx_chars": 0, "t_end": 1791530956.296871, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9934, "lo95": 0.9913, "mean": 0.9841, "ev_only": 0.9904, "ref_ms": 2.88708, "cand_ms": 2.90631, "n_trials": 197, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 53.36, "compile_s": 2.07, "r_error": "", "src_len": 2412, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 2837, "ts": 1791530864.1491368, "chk": "ok", "code_len": 2412}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3525, "tout": 1384, "ts": 1791530902.793219, "chk": null, "code_len": 2412}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791530838.6950443}
{"ep": "h1-00901", "task": "L3_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8773, "speedup": 1.8773, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 298.3, "calls": 2, "tokens_in": 8905, "tokens_out": 3749, "ctx_chars": 2425, "t_end": 1791530957.376905, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.8773, "lo95": 1.8766, "mean": 1.8765, "ev_only": 1.8818, "ref_ms": 12.6215, "cand_ms": 6.72336, "n_trials": 119, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4836, "r_wall_s": 147.4, "compile_s": 2.85, "r_error": "", "src_len": 3424, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3398, "tout": 2000, "ts": 1791530676.502865, "chk": "ok", "code_len": 3570}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5507, "tout": 1749, "ts": 1791530809.8730145, "chk": null, "code_len": 3424}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3398, "started": 1791530659.0334675}
{"ep": "h1-00889", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.9063, "speedup": 2.9063, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 330.4, "calls": 2, "tokens_in": 7132, "tokens_out": 11384, "ctx_chars": 0, "t_end": 1791530957.7318847, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.9063, "lo95": 2.9052, "mean": 2.9045, "ev_only": 2.9134, "ref_ms": 19.40852, "cand_ms": 6.67814, "n_trials": 74, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 39.52, "compile_s": 15.22, "r_error": "", "src_len": 6079, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1782, "tout": 8426, "ts": 1791530702.4693723, "chk": "ok", "code_len": 6079}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5350, "tout": 2958, "ts": 1791530918.0014257, "chk": null, "code_len": 6079}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1782, "started": 1791530627.3282475}
{"ep": "h1-00895", "task": "L2_052", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3087, "speedup": 1.3087, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 313.0, "calls": 3, "tokens_in": 23034, "tokens_out": 3320, "ctx_chars": 11132, "t_end": 1791530961.7763755, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3087, "lo95": 1.3071, "mean": 1.31, "ev_only": 1.3101, "ref_ms": 11.04055, "cand_ms": 8.43633, "n_trials": 149, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1926, "r_wall_s": 252.98, "compile_s": 4.17, "r_error": "", "src_len": 3246, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6454, "tout": 1700, "ts": 1791530663.5879757, "chk": "ok", "code_len": 3246}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8266, "tout": 24, "ts": 1791530693.996873, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8314, "tout": 1596, "ts": 1791530708.0055506, "chk": null, "code_len": 3246}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6454, "started": 1791530648.81646}
{"ep": "h1-00934", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2099, "speedup": 1.2099, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.6, "calls": 2, "tokens_in": 16223, "tokens_out": 4150, "ctx_chars": 12471, "t_end": 1791530977.101044, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2099, "lo95": 1.2088, "mean": 1.2091, "ev_only": 1.2159, "ref_ms": 3.62982, "cand_ms": 3.00017, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 89.44, "compile_s": 2.02, "r_error": "", "src_len": 2519, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7230, "tout": 2809, "ts": 1791530843.6242843, "chk": "ok", "code_len": 2519}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8993, "tout": 1341, "ts": 1791530886.813991, "chk": null, "code_len": 2519}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7230, "started": 1791530818.5050488}
{"ep": "h1-00945", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.016, "speedup": 1.016, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 104.7, "calls": 3, "tokens_in": 24436, "tokens_out": 7786, "ctx_chars": 9192, "t_end": 1791530980.336555, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.016, "lo95": 1.0153, "mean": 1.0567, "ev_only": 1.0143, "ref_ms": 8.11124, "cand_ms": 7.98338, "n_trials": 88, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0092, "r_wall_s": 31.84, "compile_s": 2.11, "r_error": "", "src_len": 3781, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5721, "tout": 3474, "ts": 1791530904.515401, "chk": "forbidden", "code_len": 3773}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8252, "tout": 2208, "ts": 1791530920.062967, "chk": "ok", "code_len": 3781}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10463, "tout": 2104, "ts": 1791530948.4032047, "chk": null, "code_len": 3781}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", null], "first_tin": 5721, "started": 1791530875.606715}
{"ep": "h1-00946", "task": "L1_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8779, "speedup": 0.8779, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 109.0, "calls": 3, "tokens_in": 8147, "tokens_out": 3037, "ctx_chars": 0, "t_end": 1791530987.0269415, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8779, "lo95": 0.8773, "mean": 0.8744, "ev_only": 0.8795, "ref_ms": 7.29508, "cand_ms": 8.30988, "n_trials": 185, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 54.75, "compile_s": 1.9, "r_error": "", "src_len": 2622, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1570, "tout": 1591, "ts": 1791530892.876867, "chk": "ok", "code_len": 2622}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3270, "tout": 13, "ts": 1791530920.7369285, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3307, "tout": 1433, "ts": 1791530932.122772, "chk": null, "code_len": 2622}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1570, "started": 1791530877.980642}
{"ep": "h1-00948", "task": "L1_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9105, "speedup": 0.9105, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 111.5, "calls": 2, "tokens_in": 14509, "tokens_out": 3986, "ctx_chars": 10384, "t_end": 1791530993.1184783, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9105, "lo95": 0.91, "mean": 0.9158, "ev_only": 0.9103, "ref_ms": 7.32198, "cand_ms": 8.04187, "n_trials": 177, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 47.31, "compile_s": 2.69, "r_error": "", "src_len": 3214, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6166, "tout": 2067, "ts": 1791530899.796312, "chk": "ok", "code_len": 3214}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8343, "tout": 1919, "ts": 1791530945.6060064, "chk": null, "code_len": 3214}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6166, "started": 1791530881.5806005}
{"ep": "h1-00967", "task": "L1_013", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8996, "speedup": 0.8996, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 67.6, "calls": 1, "tokens_in": 1699, "tokens_out": 1805, "ctx_chars": 0, "t_end": 1791530993.9937477, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8996, "lo95": 0.8973, "mean": 0.8953, "ev_only": 0.8981, "ref_ms": 7.35982, "cand_ms": 8.18147, "n_trials": 190, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 51.32, "compile_s": 2.62, "r_error": "", "src_len": 2867, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1699, "tout": 1805, "ts": 1791530942.454653, "chk": null, "code_len": 2867}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1699, "started": 1791530926.4096386}
{"ep": "h1-00943", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.976, "speedup": 4.976, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 124.2, "calls": 2, "tokens_in": 5235, "tokens_out": 5693, "ctx_chars": 0, "t_end": 1791530997.1392717, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.976, "lo95": 4.9504, "mean": 4.8985, "ev_only": 4.9859, "ref_ms": 7.36218, "cand_ms": 1.47952, "n_trials": 65, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 56.24, "compile_s": 2.74, "r_error": "", "src_len": 2918, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1612, "tout": 4118, "ts": 1791530910.5525577, "chk": "ok", "code_len": 2918}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3623, "tout": 1575, "ts": 1791530940.6970825, "chk": null, "code_len": 2918}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1612, "started": 1791530872.9848409}
{"ep": "h1-00912", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3986, "speedup": 1.3986, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 273.4, "calls": 2, "tokens_in": 5483, "tokens_out": 4531, "ctx_chars": 0, "t_end": 1791531000.137951, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3986, "lo95": 1.3954, "mean": 1.4038, "ev_only": 1.4089, "ref_ms": 8.22506, "cand_ms": 5.88091, "n_trials": 183, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 168.26, "compile_s": 2.17, "r_error": "", "src_len": 2986, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1670, "tout": 2865, "ts": 1791530751.724252, "chk": "ok", "code_len": 2986}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3813, "tout": 1666, "ts": 1791530831.7996943, "chk": null, "code_len": 2986}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1670, "started": 1791530726.7378051}
{"ep": "h1-00970", "task": "L2_059", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 65.3, "calls": 1, "tokens_in": 1548, "tokens_out": 811, "ctx_chars": 0, "t_end": 1791531011.4564042, "error": "RuntimeError: Error building extension 'swish_scale_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=swish_scale_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 57.05, "compile_s": 57.05, "r_error": "RuntimeError: Error building extension 'swish_scale_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=swish_scale_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/", "src_len": 1733, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1548, "tout": 811, "ts": 1791530954.35717, "chk": null, "code_len": 1733}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1548, "started": 1791530946.155569}
{"ep": "h1-00870", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.3936, "speedup": 3.3936, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 458.5, "calls": 2, "tokens_in": 6840, "tokens_out": 11283, "ctx_chars": 0, "t_end": 1791531016.6110795, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.3936, "lo95": 3.3882, "mean": 3.3907, "ev_only": 3.3893, "ref_ms": 19.52051, "cand_ms": 5.75216, "n_trials": 77, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 224.0, "compile_s": 15.35, "r_error": "", "src_len": 5490, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1782, "tout": 8557, "ts": 1791530633.73105, "chk": "ok", "code_len": 5490}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5058, "tout": 2726, "ts": 1791530792.3198278, "chk": null, "code_len": 5490}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1782, "started": 1791530558.138522}
{"ep": "h1-00935", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.5093, "speedup": 4.5093, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 198.0, "calls": 3, "tokens_in": 14575, "tokens_out": 9943, "ctx_chars": 0, "t_end": 1791531017.8457086, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.5093, "lo95": 4.503, "mean": 4.6063, "ev_only": 4.6113, "ref_ms": 2.29357, "cand_ms": 0.50863, "n_trials": 219, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.796, "r_wall_s": 76.7, "compile_s": 17.82, "r_error": "", "src_len": 5115, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 4830, "ts": 1791530860.2319708, "chk": "no_custom_kernel", "code_len": 5137}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4956, "tout": 2589, "ts": 1791530902.990663, "chk": "ok", "code_len": 5115}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7604, "tout": 2524, "ts": 1791530941.0379074, "chk": null, "code_len": 5115}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2015, "started": 1791530819.848795}
{"ep": "h1-00904", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1665, "speedup": 2.1665, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 353.6, "calls": 2, "tokens_in": 12511, "tokens_out": 1583, "ctx_chars": 9855, "t_end": 1791531018.5165095, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.1665, "lo95": 2.1656, "mean": 2.1807, "ev_only": 2.1752, "ref_ms": 6.2976, "cand_ms": 2.90683, "n_trials": 180, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2381, "r_wall_s": 102.36, "compile_s": 3.59, "r_error": "", "src_len": 890, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 1071, "ts": 1791530674.5203216, "chk": "ok", "code_len": 890}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6665, "tout": 512, "ts": 1791530915.3645718, "chk": null, "code_len": 890}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791530664.9460683}
{"ep": "h1-00954", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0016, "speedup": 1.0016, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 124.3, "calls": 2, "tokens_in": 4947, "tokens_out": 4409, "ctx_chars": 0, "t_end": 1791531028.2751431, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0016, "lo95": 1.0008, "mean": 1.0022, "ev_only": 1.0029, "ref_ms": 2.90159, "cand_ms": 2.89685, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 43.97, "compile_s": 1.98, "r_error": "", "src_len": 2431, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 2972, "ts": 1791530950.6300201, "chk": "ok", "code_len": 2431}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3358, "tout": 1437, "ts": 1791530983.92605, "chk": null, "code_len": 2431}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791530924.3986938}
{"ep": "h1-00951", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8881, "speedup": 0.8881, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 145.5, "calls": 2, "tokens_in": 11033, "tokens_out": 10524, "ctx_chars": 0, "t_end": 1791531028.8957357, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8881, "lo95": 0.8022, "mean": 0.6916, "ev_only": 0.8896, "ref_ms": 8.96851, "cand_ms": 10.09869, "n_trials": 181, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3464, "r_wall_s": 48.96, "compile_s": 1.92, "r_error": "", "src_len": 7223, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3365, "tout": 6707, "ts": 1791530938.850822, "chk": "ok", "code_len": 7223}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7668, "tout": 3817, "ts": 1791530979.90435, "chk": null, "code_len": 7223}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3365, "started": 1791530883.3926554}
{"ep": "h1-00886", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3505, "speedup": 1.3505, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 410.9, "calls": 2, "tokens_in": 14927, "tokens_out": 3990, "ctx_chars": 11132, "t_end": 1791531029.0115068, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3505, "lo95": 1.3489, "mean": 1.3515, "ev_only": 1.3514, "ref_ms": 11.02342, "cand_ms": 8.16266, "n_trials": 133, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1857, "r_wall_s": 229.3, "compile_s": 3.08, "r_error": "", "src_len": 2990, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6456, "tout": 2455, "ts": 1791530638.437366, "chk": "ok", "code_len": 2990}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8471, "tout": 1535, "ts": 1791530798.9668875, "chk": null, "code_len": 2990}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6456, "started": 1791530618.1559927}
{"ep": "h1-00846", "task": "L1_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6729, "speedup": 0.6729, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 545.0, "calls": 4, "tokens_in": 14901, "tokens_out": 4608, "ctx_chars": 0, "t_end": 1791531033.86094, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.6729, "lo95": 0.6727, "mean": 0.6728, "ev_only": 0.672, "ref_ms": 7.51236, "cand_ms": 11.16461, "n_trials": 137, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 209.05, "compile_s": 2.4, "r_error": "", "src_len": 2624, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 1667, "ts": 1791530504.472725, "chk": "incorrect", "code_len": 2825}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3364, "tout": 1463, "ts": 1791530683.750139, "chk": "ok", "code_len": 2624}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4936, "tout": 76, "ts": 1791530813.3614535, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5036, "tout": 1402, "ts": 1791530824.7317889, "chk": null, "code_len": 2624}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 1565, "started": 1791530488.829167}
{"ep": "h1-00938", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.214, "speedup": 0.214, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 209.5, "calls": 3, "tokens_in": 12537, "tokens_out": 8524, "ctx_chars": 0, "t_end": 1791531037.5759583, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.214, "lo95": 0.212, "mean": 0.2144, "ev_only": 0.2144, "ref_ms": 2.37418, "cand_ms": 11.09329, "n_trials": 100, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 90.14, "compile_s": 18.9, "r_error": "", "src_len": 3776, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 4358, "ts": 1791530866.241314, "chk": "no_custom_kernel", "code_len": 3798}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4311, "tout": 2202, "ts": 1791530905.482227, "chk": "ok", "code_len": 3776}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6475, "tout": 1964, "ts": 1791530947.3738024, "chk": null, "code_len": 3776}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1751, "started": 1791530828.079809}
{"ep": "h1-00786", "task": "L3_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7951, "speedup": 0.7951, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 776.4, "calls": 5, "tokens_in": 53719, "tokens_out": 14801, "ctx_chars": 0, "t_end": 1791531038.9857283, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7951, "lo95": 0.7903, "mean": 0.791, "ev_only": 0.795, "ref_ms": 3.50347, "cand_ms": 4.40617, "n_trials": 173, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0035, "r_wall_s": 224.21, "compile_s": 2.95, "r_error": "", "src_len": 3069, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2843, "tout": 5397, "ts": 1791530307.7369318, "chk": "runtime_error", "code_len": 5729}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8339, "tout": 3310, "ts": 1791530439.6471417, "chk": "incorrect", "code_len": 5603}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11780, "tout": 2193, "ts": 1791530468.6921537, "chk": "incorrect", "code_len": 3987}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 14104, "tout": 2417, "ts": 1791530714.1207166, "chk": "ok", "code_len": 3069}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 16653, "tout": 1484, "ts": 1791530814.6658428, "chk": null, "code_len": 3069}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "incorrect", "ok", null], "first_tin": 2843, "started": 1791530262.6214097}
{"ep": "h1-00980", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0111, "speedup": 1.0111, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 55.2, "calls": 2, "tokens_in": 4274, "tokens_out": 1817, "ctx_chars": 0, "t_end": 1791531042.1989405, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0111, "lo95": 1.0109, "mean": 1.0599, "ev_only": 1.0124, "ref_ms": 15.8721, "cand_ms": 15.69729, "n_trials": 67, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 25.35, "compile_s": 1.95, "r_error": "", "src_len": 1101, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1671, "tout": 1207, "ts": 1791530997.8949175, "chk": "ok", "code_len": 1101}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2603, "tout": 610, "ts": 1791531016.6686864, "chk": null, "code_len": 1101}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1671, "started": 1791530987.0271704}
{"ep": "h1-00941", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.256, "speedup": 1.256, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 202.5, "calls": 2, "tokens_in": 10354, "tokens_out": 18067, "ctx_chars": 0, "t_end": 1791531042.307773, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.256, "lo95": 1.2526, "mean": 1.2607, "ev_only": 1.2524, "ref_ms": 4.10024, "cand_ms": 3.26454, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9928, "r_wall_s": 32.6, "compile_s": 2.31, "r_error": "", "src_len": 9854, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2380, "tout": 13004, "ts": 1791530950.8316607, "chk": "ok", "code_len": 9854}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7974, "tout": 5063, "ts": 1791531009.6646888, "chk": null, "code_len": 9854}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2380, "started": 1791530839.8128886}
{"ep": "h1-00921", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5553, "speedup": 1.5553, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 274.7, "calls": 2, "tokens_in": 5580, "tokens_out": 4592, "ctx_chars": 0, "t_end": 1791531045.5415413, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.5553, "lo95": 1.5513, "mean": 1.5475, "ev_only": 1.5542, "ref_ms": 28.82915, "cand_ms": 18.53563, "n_trials": 42, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0498, "r_wall_s": 217.11, "compile_s": 2.41, "r_error": "", "src_len": 2486, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1902, "tout": 3077, "ts": 1791530798.8056233, "chk": "ok", "code_len": 2486}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3678, "tout": 1515, "ts": 1791530828.2048786, "chk": null, "code_len": 2486}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1902, "started": 1791530770.8503373}
{"ep": "h1-00972", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0624, "speedup": 1.0624, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 97.1, "calls": 2, "tokens_in": 5033, "tokens_out": 2995, "ctx_chars": 0, "t_end": 1791531047.6864324, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0624, "lo95": 1.0617, "mean": 1.0623, "ev_only": 1.0623, "ref_ms": 8.51778, "cand_ms": 8.01731, "n_trials": 148, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 38.23, "compile_s": 2.33, "r_error": "", "src_len": 2073, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1791, "tout": 1866, "ts": 1791530966.4327276, "chk": "ok", "code_len": 2073}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3242, "tout": 1129, "ts": 1791531009.3596916, "chk": null, "code_len": 2073}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1791, "started": 1791530950.6141808}
{"ep": "h1-00876", "task": "L3_045", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0064, "speedup": 1.0064, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 476.6, "calls": 5, "tokens_in": 53712, "tokens_out": 11667, "ctx_chars": 6513, "t_end": 1791531054.0160518, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0064, "lo95": 1.006, "mean": 1.0064, "ev_only": 1.0066, "ref_ms": 23.32972, "cand_ms": 23.18232, "n_trials": 66, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 239.18, "compile_s": 2.88, "r_error": "", "src_len": 3859, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5437, "tout": 2397, "ts": 1791530597.8254092, "chk": "incorrect", "code_len": 4678}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7967, "tout": 3227, "ts": 1791530654.0749404, "chk": "incorrect", "code_len": 4306}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11327, "tout": 1842, "ts": 1791530695.3840678, "chk": "incorrect", "code_len": 3676}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 13302, "tout": 2245, "ts": 1791530761.8154285, "chk": "ok", "code_len": 3859}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 15679, "tout": 1956, "ts": 1791530814.8025556, "chk": null, "code_len": 3859}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 5437, "started": 1791530577.3959875}
{"ep": "h1-00878", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.7237, "speedup": 4.7237, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 458.9, "calls": 3, "tokens_in": 15057, "tokens_out": 12977, "ctx_chars": 0, "t_end": 1791531056.4873579, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 4.7237, "lo95": 4.722, "mean": 4.7205, "ev_only": 4.7186, "ref_ms": 12.66605, "cand_ms": 2.68141, "n_trials": 112, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9938, "r_wall_s": 230.09, "compile_s": 12.24, "r_error": "", "src_len": 5511, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1863, "tout": 7296, "ts": 1791530664.5184798, "chk": "no_custom_kernel", "code_len": 5510}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5172, "tout": 2976, "ts": 1791530766.31857, "chk": "ok", "code_len": 5511}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8022, "tout": 2705, "ts": 1791530826.3701646, "chk": null, "code_len": 5511}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1863, "started": 1791530597.5976543}
{"ep": "h1-00956", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2332, "speedup": 1.2332, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 154.6, "calls": 2, "tokens_in": 15690, "tokens_out": 2519, "ctx_chars": 12155, "t_end": 1791531059.4458046, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2332, "lo95": 1.2328, "mean": 1.2336, "ev_only": 1.233, "ref_ms": 12.01472, "cand_ms": 9.74253, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0832, "r_wall_s": 78.83, "compile_s": 1.93, "r_error": "", "src_len": 1552, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7203, "tout": 1649, "ts": 1791530918.9929917, "chk": "ok", "code_len": 1552}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8487, "tout": 870, "ts": 1791530979.7865496, "chk": null, "code_len": 1552}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7203, "started": 1791530904.8750753}
{"ep": "h1-00923", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9199, "speedup": 0.9199, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 283.0, "calls": 2, "tokens_in": 4967, "tokens_out": 4670, "ctx_chars": 0, "t_end": 1791531063.4548988, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9199, "lo95": 0.9193, "mean": 0.9478, "ev_only": 0.9193, "ref_ms": 7.3468, "cand_ms": 7.98666, "n_trials": 186, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 32.39, "compile_s": 2.13, "r_error": "", "src_len": 2354, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 3130, "ts": 1791530828.5723004, "chk": "ok", "code_len": 2354}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3403, "tout": 1540, "ts": 1791531030.9872618, "chk": null, "code_len": 2354}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791530800.7856681}
{"ep": "h1-00971", "task": "L3_004", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9786, "speedup": 0.9786, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 123.0, "calls": 2, "tokens_in": 11229, "tokens_out": 3278, "ctx_chars": 6513, "t_end": 1791531072.8795855, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9786, "lo95": 0.978, "mean": 0.9782, "ev_only": 0.974, "ref_ms": 2.30003, "cand_ms": 2.35026, "n_trials": 216, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0627, "r_wall_s": 42.48, "compile_s": 3.04, "r_error": "", "src_len": 3166, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4716, "tout": 1685, "ts": 1791530964.9092042, "chk": "ok", "code_len": 3166}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6513, "tout": 1593, "ts": 1791531030.372301, "chk": null, "code_len": 3166}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4716, "started": 1791530949.8693042}
{"ep": "h1-00928", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1674, "speedup": 1.1674, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 282.2, "calls": 2, "tokens_in": 14610, "tokens_out": 4154, "ctx_chars": 11132, "t_end": 1791531075.458092, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1674, "lo95": 1.1669, "mean": 1.167, "ev_only": 1.1636, "ref_ms": 3.63775, "cand_ms": 3.11619, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 117.86, "compile_s": 4.97, "r_error": "", "src_len": 2286, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 2941, "ts": 1791530818.6211607, "chk": "ok", "code_len": 2286}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8184, "tout": 1213, "ts": 1791530956.432684, "chk": null, "code_len": 2286}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6426, "started": 1791530793.2103922}
{"ep": "h1-00931", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0125, "speedup": 1.0125, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 273.2, "calls": 2, "tokens_in": 13708, "tokens_out": 1460, "ctx_chars": 10749, "t_end": 1791531080.0052776, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0125, "lo95": 1.0118, "mean": 1.0127, "ev_only": 1.0122, "ref_ms": 15.91979, "cand_ms": 15.72392, "n_trials": 56, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 23.46, "compile_s": 2.16, "r_error": "", "src_len": 1127, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6387, "tout": 825, "ts": 1791530814.332768, "chk": "ok", "code_len": 1127}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7321, "tout": 635, "ts": 1791531056.2793667, "chk": null, "code_len": 1127}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6387, "started": 1791530806.8406985}
{"ep": "h1-00982", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5319, "speedup": 1.5319, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 86.6, "calls": 2, "tokens_in": 12867, "tokens_out": 4301, "ctx_chars": 9033, "t_end": 1791531080.5506954, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.5319, "lo95": 1.5279, "mean": 1.538, "ev_only": 1.5398, "ref_ms": 8.01979, "cand_ms": 5.2352, "n_trials": 86, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 26.07, "compile_s": 1.87, "r_error": "", "src_len": 2397, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 2772, "ts": 1791531018.0461152, "chk": "ok", "code_len": 2487}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7379, "tout": 1529, "ts": 1791531054.2964504, "chk": null, "code_len": 2397}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5488, "started": 1791530993.9940274}
{"ep": "h1-00992", "task": "L3_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0007, "speedup": 1.0007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 47.0, "calls": 1, "tokens_in": 1684, "tokens_out": 802, "ctx_chars": 0, "t_end": 1791531080.8646274, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0007, "lo95": 0.9969, "mean": 0.9842, "ev_only": 1.0006, "ref_ms": 10.80447, "cand_ms": 10.79673, "n_trials": 107, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0016, "r_wall_s": 38.15, "compile_s": 1.88, "r_error": "", "src_len": 1374, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1684, "tout": 802, "ts": 1791531042.596262, "chk": null, "code_len": 1374}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1684, "started": 1791531033.861192}
{"ep": "h1-00960", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.9545, "speedup": 6.9545, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 165.5, "calls": 2, "tokens_in": 12954, "tokens_out": 3418, "ctx_chars": 9033, "t_end": 1791531081.5310152, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.9545, "lo95": 6.9261, "mean": 7.2768, "ev_only": 7.0986, "ref_ms": 7.99347, "cand_ms": 1.14939, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2342, "r_wall_s": 128.15, "compile_s": 4.5, "r_error": "", "src_len": 2029, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5662, "tout": 2341, "ts": 1791530936.6859465, "chk": "ok", "code_len": 2029}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7292, "tout": 1077, "ts": 1791530953.3391366, "chk": null, "code_len": 2029}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5662, "started": 1791530916.036785}
{"ep": "h1-00899", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 16.7402, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 425.3, "calls": 2, "tokens_in": 6870, "tokens_out": 6947, "ctx_chars": 0, "t_end": 1791531082.7861135, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 16.7402, "lo95": 16.6117, "mean": 17.7396, "ev_only": 16.8875, "ref_ms": 28.76675, "cand_ms": 1.71843, "n_trials": 47, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9213, "r_wall_s": 274.74, "compile_s": 17.19, "r_error": "", "src_len": 4352, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2037, "tout": 4852, "ts": 1791530698.5506837, "chk": "ok", "code_len": 4352}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4833, "tout": 2095, "ts": 1791530808.0126977, "chk": null, "code_len": 4352}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2037, "started": 1791530657.455443}
{"ep": "h1-00961", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.6638, "speedup": 7.6638, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 166.6, "calls": 2, "tokens_in": 12589, "tokens_out": 2585, "ctx_chars": 9033, "t_end": 1791531083.749082, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.6638, "lo95": 7.6576, "mean": 7.6535, "ev_only": 7.6681, "ref_ms": 7.94527, "cand_ms": 1.03672, "n_trials": 170, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 129.7, "compile_s": 4.27, "r_error": "", "src_len": 1455, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5662, "tout": 1782, "ts": 1791530933.668887, "chk": "ok", "code_len": 1455}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6927, "tout": 803, "ts": 1791530953.9998834, "chk": null, "code_len": 1455}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5662, "started": 1791530917.1160421}
{"ep": "h1-00933", "task": "L3_047", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9533, "speedup": 0.9533, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 266.8, "calls": 4, "tokens_in": 26634, "tokens_out": 6835, "ctx_chars": 0, "t_end": 1791531084.7882214, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9533, "lo95": 0.953, "mean": 0.9529, "ev_only": 0.9534, "ref_ms": 3.6341, "cand_ms": 3.81219, "n_trials": 226, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0489, "r_wall_s": 102.17, "compile_s": 13.37, "r_error": "", "src_len": 4940, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2691, "tout": 2435, "ts": 1791530840.8175328, "chk": "compile_error", "code_len": 5336}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6425, "tout": 2174, "ts": 1791530915.3619483, "chk": "ok", "code_len": 4940}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8711, "tout": 72, "ts": 1791530964.5972447, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8807, "tout": 2154, "ts": 1791530982.3280983, "chk": null, "code_len": 4940}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 2691, "started": 1791530818.0113635}
{"ep": "h1-00872", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0075, "speedup": 1.0075, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 523.4, "calls": 4, "tokens_in": 39969, "tokens_out": 16111, "ctx_chars": 6513, "t_end": 1791531086.4822257, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0075, "lo95": 1.0067, "mean": 1.0079, "ev_only": 1.0073, "ref_ms": 23.35507, "cand_ms": 23.18131, "n_trials": 64, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0077, "r_wall_s": 282.36, "compile_s": 2.39, "r_error": "", "src_len": 4111, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5439, "tout": 5217, "ts": 1791530607.8470974, "chk": "incorrect", "code_len": 5592}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8603, "tout": 3844, "ts": 1791530648.0472226, "chk": "incorrect", "code_len": 5638}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11641, "tout": 4788, "ts": 1791530705.2536688, "chk": "ok", "code_len": 4111}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14286, "tout": 2262, "ts": 1791530804.0879216, "chk": null, "code_len": 4111}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5439, "started": 1791530563.1103802}
{"ep": "h1-00990", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0616, "speedup": 1.0616, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 60.6, "calls": 2, "tokens_in": 13725, "tokens_out": 2048, "ctx_chars": 10191, "t_end": 1791531089.4843328, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0616, "lo95": 1.0595, "mean": 1.0588, "ev_only": 1.0654, "ref_ms": 8.52727, "cand_ms": 8.03213, "n_trials": 161, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0055, "r_wall_s": 33.49, "compile_s": 2.2, "r_error": "", "src_len": 1858, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6250, "tout": 1113, "ts": 1791531038.2996843, "chk": "ok", "code_len": 1858}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7475, "tout": 935, "ts": 1791531055.78267, "chk": null, "code_len": 1858}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6250, "started": 1791531028.896015}
{"ep": "h1-00958", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4148, "speedup": 1.4148, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 176.4, "calls": 2, "tokens_in": 4562, "tokens_out": 1983, "ctx_chars": 0, "t_end": 1791531090.0868194, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4148, "lo95": 1.413, "mean": 1.4226, "ev_only": 1.4234, "ref_ms": 14.03504, "cand_ms": 9.92032, "n_trials": 92, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0826, "r_wall_s": 125.15, "compile_s": 2.41, "r_error": "", "src_len": 1296, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 1329, "ts": 1791530929.3195443, "chk": "ok", "code_len": 1296}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2811, "tout": 654, "ts": 1791530964.1038246, "chk": null, "code_len": 1296}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1751, "started": 1791530913.7339737}
{"ep": "h1-00962", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8956, "speedup": 1.8956, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 171.0, "calls": 2, "tokens_in": 14789, "tokens_out": 4474, "ctx_chars": 10743, "t_end": 1791531090.5048437, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.8956, "lo95": 1.8934, "mean": 1.907, "ev_only": 1.9132, "ref_ms": 19.54689, "cand_ms": 10.31168, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1521, "r_wall_s": 68.27, "compile_s": 3.7, "r_error": "", "src_len": 2624, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6466, "tout": 3183, "ts": 1791530949.661236, "chk": "ok", "code_len": 2624}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8323, "tout": 1291, "ts": 1791531021.9851665, "chk": null, "code_len": 2624}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6466, "started": 1791530919.529839}
{"ep": "h1-00917", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.0258, "speedup": 3.0258, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.7, "calls": 2, "tokens_in": 18285, "tokens_out": 13966, "ctx_chars": 11582, "t_end": 1791531092.4955013, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 3.0258, "lo95": 3.0241, "mean": 3.0247, "ev_only": 3.0306, "ref_ms": 35.86781, "cand_ms": 11.85397, "n_trials": 35, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 98.34, "compile_s": 11.92, "r_error": "", "src_len": 6766, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7119, "tout": 10491, "ts": 1791530833.071388, "chk": "ok", "code_len": 6766}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11166, "tout": 3475, "ts": 1791530993.3056567, "chk": null, "code_len": 6766}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7119, "started": 1791530742.7694252}
{"ep": "h1-00898", "task": "L1_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.6701, "speedup": 3.6701, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 441.0, "calls": 4, "tokens_in": 20788, "tokens_out": 5926, "ctx_chars": 0, "t_end": 1791531095.8260362, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.6701, "lo95": 3.6594, "mean": 3.6719, "ev_only": 3.7109, "ref_ms": 7.38462, "cand_ms": 2.01211, "n_trials": 180, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 275.61, "compile_s": 14.07, "r_error": "", "src_len": 3920, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 2236, "ts": 1791530696.1150408, "chk": "compile_error", "code_len": 4669}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5078, "tout": 1827, "ts": 1791530775.233979, "chk": "ok", "code_len": 3920}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7014, "tout": 48, "ts": 1791530805.4194107, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7086, "tout": 1815, "ts": 1791530820.046936, "chk": null, "code_len": 3920}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1610, "started": 1791530675.179481}
{"ep": "h1-00918", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0436, "speedup": 1.0436, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 352.6, "calls": 2, "tokens_in": 4346, "tokens_out": 1890, "ctx_chars": 0, "t_end": 1791531095.9369984, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0436, "lo95": 1.0431, "mean": 1.0433, "ev_only": 1.0437, "ref_ms": 30.33127, "cand_ms": 29.06382, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 286.78, "compile_s": 3.03, "r_error": "", "src_len": 895, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1696, "tout": 1387, "ts": 1791530756.381661, "chk": "ok", "code_len": 895}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2650, "tout": 503, "ts": 1791530808.4163597, "chk": null, "code_len": 895}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1696, "started": 1791530743.3234901}
{"ep": "h1-00965", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3925, "speedup": 1.3925, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 176.4, "calls": 2, "tokens_in": 5587, "tokens_out": 6125, "ctx_chars": 0, "t_end": 1791531098.6574497, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3925, "lo95": 1.3835, "mean": 1.3604, "ev_only": 1.3977, "ref_ms": 7.51019, "cand_ms": 5.39315, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1105, "r_wall_s": 85.43, "compile_s": 1.93, "r_error": "", "src_len": 3001, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1685, "tout": 4581, "ts": 1791530966.2716198, "chk": "ok", "code_len": 3001}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3902, "tout": 1544, "ts": 1791531012.81341, "chk": null, "code_len": 3001}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1685, "started": 1791530922.2770555}
{"ep": "h1-00991", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0065, "speedup": 1.0065, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 77.1, "calls": 1, "tokens_in": 1532, "tokens_out": 1391, "ctx_chars": 0, "t_end": 1791531106.1195378, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0065, "lo95": 1.0052, "mean": 1.0106, "ev_only": 1.0034, "ref_ms": 4.48366, "cand_ms": 4.45451, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0023, "r_wall_s": 63.71, "compile_s": 2.11, "r_error": "", "src_len": 901, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1532, "tout": 1391, "ts": 1791531042.3794122, "chk": null, "code_len": 901}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1532, "started": 1791531029.0117223}
{"ep": "h1-01002", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1099, "speedup": 1.1099, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 55.8, "calls": 2, "tokens_in": 4515, "tokens_out": 2582, "ctx_chars": 0, "t_end": 1791531119.3014593, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1099, "lo95": 1.1083, "mean": 1.1209, "ev_only": 1.1103, "ref_ms": 31.40067, "cand_ms": 28.29132, "n_trials": 45, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0471, "r_wall_s": 19.63, "compile_s": 1.85, "r_error": "", "src_len": 1296, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 1925, "ts": 1791531080.9526393, "chk": "ok", "code_len": 1296}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2832, "tout": 657, "ts": 1791531099.6249614, "chk": null, "code_len": 1296}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1683, "started": 1791531063.455139}
{"ep": "h1-00963", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.4661, "speedup": 2.4661, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 206.3, "calls": 2, "tokens_in": 7285, "tokens_out": 12627, "ctx_chars": 0, "t_end": 1791531127.9121978, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.4661, "lo95": 2.4641, "mean": 2.5191, "ev_only": 2.4612, "ref_ms": 5.6012, "cand_ms": 2.27125, "n_trials": 226, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.3617, "r_wall_s": 69.57, "compile_s": 13.28, "r_error": "", "src_len": 7479, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 9046, "ts": 1791531000.251511, "chk": "ok", "code_len": 7479}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5675, "tout": 3581, "ts": 1791531057.5179248, "chk": null, "code_len": 7479}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1610, "started": 1791530921.5852325}
{"ep": "h1-00975", "task": "L2_097", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0069, "speedup": 1.0069, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 177.3, "calls": 4, "tokens_in": 23234, "tokens_out": 7321, "ctx_chars": 0, "t_end": 1791531134.6944172, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0069, "lo95": 1.0067, "mean": 1.0548, "ev_only": 1.0072, "ref_ms": 8.20547, "cand_ms": 8.14909, "n_trials": 140, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.017, "r_wall_s": 32.91, "compile_s": 11.35, "r_error": "", "src_len": 5563, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1728, "tout": 2512, "ts": 1791530980.301211, "chk": "compile_error", "code_len": 5611}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5474, "tout": 2386, "ts": 1791531057.6907225, "chk": "ok", "code_len": 5563}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7972, "tout": 64, "ts": 1791531082.6105726, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8060, "tout": 2359, "ts": 1791531101.70898, "chk": null, "code_len": 5563}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1728, "started": 1791530957.3771632}
{"ep": "h1-00994", "task": "L2_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8457, "speedup": 0.8457, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 106.3, "calls": 3, "tokens_in": 9022, "tokens_out": 2646, "ctx_chars": 0, "t_end": 1791531145.2688155, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8457, "lo95": 0.8447, "mean": 0.8483, "ev_only": 0.8454, "ref_ms": 2.37003, "cand_ms": 2.8023, "n_trials": 196, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2562, "r_wall_s": 69.47, "compile_s": 2.46, "r_error": "", "src_len": 1723, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1749, "tout": 1757, "ts": 1791531055.2463841, "chk": "ok", "code_len": 1723}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3618, "tout": 13, "ts": 1791531068.323673, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3655, "tout": 876, "ts": 1791531075.6649582, "chk": null, "code_len": 1723}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1749, "started": 1791531038.9864948}
{"ep": "h1-01016", "task": "L2_012", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 63.7, "calls": 1, "tokens_in": 1586, "tokens_out": 929, "ctx_chars": 0, "t_end": 1791531156.1584647, "error": "RuntimeError: Error building extension 'gemm_mult_lrelu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemm_mult_lrelu -DTORCH_API_INCLUDE_EXTENSION_H -I/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 53.66, "compile_s": 53.65, "r_error": "RuntimeError: Error building extension 'gemm_mult_lrelu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemm_mult_lrelu -DTORCH_API_INCLUDE_EXTENSION_H -I/", "src_len": 2025, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1586, "tout": 929, "ts": 1791531102.4596815, "chk": null, "code_len": 2025}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1586, "started": 1791531092.4957795}
{"ep": "h1-00988", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.5215, "speedup": 4.5215, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 139.0, "calls": 2, "tokens_in": 4962, "tokens_out": 5716, "ctx_chars": 0, "t_end": 1791531157.5033128, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.5215, "lo95": 4.5118, "mean": 4.6598, "ev_only": 4.536, "ref_ms": 16.13183, "cand_ms": 3.56778, "n_trials": 70, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9994, "r_wall_s": 35.28, "compile_s": 2.35, "r_error": "", "src_len": 1931, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1574, "tout": 4561, "ts": 1791531061.1017349, "chk": "ok", "code_len": 1931}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3388, "tout": 1155, "ts": 1791531122.1804695, "chk": null, "code_len": 1931}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1574, "started": 1791531018.5167398}
{"ep": "h1-00919", "task": "L3_026", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6779, "speedup": 0.6779, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 400.3, "calls": 4, "tokens_in": 42598, "tokens_out": 9867, "ctx_chars": 6513, "t_end": 1791531158.5256784, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6779, "lo95": 0.6752, "mean": 0.6719, "ev_only": 0.6779, "ref_ms": 20.22627, "cand_ms": 29.83809, "n_trials": 39, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0732, "r_wall_s": 34.91, "compile_s": 1.88, "r_error": "", "src_len": 6710, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6294, "tout": 3330, "ts": 1791530786.0155385, "chk": "incorrect", "code_len": 6962}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9756, "tout": 3380, "ts": 1791530821.450347, "chk": "ok", "code_len": 6763}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13248, "tout": 28, "ts": 1791531098.6962473, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13300, "tout": 3129, "ts": 1791531123.593481, "chk": null, "code_len": 6710}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 6294, "started": 1791530758.2374594}
{"ep": "h1-01015", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0034, "speedup": 1.0034, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 70.7, "calls": 2, "tokens_in": 13070, "tokens_out": 2233, "ctx_chars": 9898, "t_end": 1791531161.198259, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0034, "lo95": 1.0027, "mean": 1.0033, "ev_only": 1.0022, "ref_ms": 16.10946, "cand_ms": 16.05525, "n_trials": 75, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.001, "r_wall_s": 33.11, "compile_s": 2.64, "r_error": "", "src_len": 1410, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6027, "tout": 1315, "ts": 1791531102.4294834, "chk": "ok", "code_len": 1410}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7043, "tout": 918, "ts": 1791531128.039082, "chk": null, "code_len": 1410}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6027, "started": 1791531090.5050874}
{"ep": "h1-00966", "task": "L1_010", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2625, "speedup": 1.2625, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 239.7, "calls": 2, "tokens_in": 5046, "tokens_out": 4154, "ctx_chars": 0, "t_end": 1791531163.342395, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2625, "lo95": 1.2614, "mean": 1.2626, "ev_only": 1.2663, "ref_ms": 2.89365, "cand_ms": 2.29198, "n_trials": 223, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 47.91, "compile_s": 2.13, "r_error": "", "src_len": 2376, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1589, "tout": 2621, "ts": 1791530946.5326595, "chk": "ok", "code_len": 2376}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3457, "tout": 1533, "ts": 1791530980.5756254, "chk": null, "code_len": 2376}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1589, "started": 1791530923.6008315}
{"ep": "h1-00968", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.2508, "speedup": 3.2508, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 240.7, "calls": 3, "tokens_in": 16183, "tokens_out": 14448, "ctx_chars": 0, "t_end": 1791531168.7877977, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 3.2508, "lo95": 3.2281, "mean": 3.8192, "ev_only": 3.2658, "ref_ms": 61.23997, "cand_ms": 18.8386, "n_trials": 22, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8604, "r_wall_s": 55.33, "compile_s": 12.48, "r_error": "", "src_len": 6159, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1959, "tout": 8133, "ts": 1791530999.3859851, "chk": "no_custom_kernel", "code_len": 6181}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5498, "tout": 3260, "ts": 1791531060.0387707, "chk": "ok", "code_len": 6159}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8726, "tout": 3055, "ts": 1791531113.4145977, "chk": null, "code_len": 6159}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1959, "started": 1791530928.074022}
{"ep": "h1-01013", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9379, "speedup": 1.9379, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 82.9, "calls": 2, "tokens_in": 8749, "tokens_out": 4259, "ctx_chars": 2425, "t_end": 1791531172.344164, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.9379, "lo95": 1.9358, "mean": 1.9389, "ev_only": 1.9397, "ref_ms": 12.62721, "cand_ms": 6.51608, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.522, "r_wall_s": 26.83, "compile_s": 1.97, "r_error": "", "src_len": 2697, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3400, "tout": 2856, "ts": 1791531115.2564723, "chk": "ok", "code_len": 2697}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5349, "tout": 1403, "ts": 1791531145.412861, "chk": null, "code_len": 2697}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3400, "started": 1791531089.4845874}
{"ep": "h1-00977", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0417, "speedup": 1.0417, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 211.1, "calls": 2, "tokens_in": 12125, "tokens_out": 2286, "ctx_chars": 8989, "t_end": 1791531172.88463, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0417, "lo95": 1.041, "mean": 1.0419, "ev_only": 1.0418, "ref_ms": 30.53974, "cand_ms": 29.31784, "n_trials": 58, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 40.76, "compile_s": 1.88, "r_error": "", "src_len": 921, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5552, "tout": 1725, "ts": 1791530978.6149774, "chk": "ok", "code_len": 921}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6573, "tout": 561, "ts": 1791530995.4024122, "chk": null, "code_len": 921}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5552, "started": 1791530961.7766135}
{"ep": "h1-01017", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5318, "speedup": 1.5318, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 79.0, "calls": 2, "tokens_in": 4961, "tokens_out": 4436, "ctx_chars": 0, "t_end": 1791531174.8749125, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.5318, "lo95": 1.5286, "mean": 1.5194, "ev_only": 1.5292, "ref_ms": 8.03463, "cand_ms": 5.24527, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 29.33, "compile_s": 2.03, "r_error": "", "src_len": 2293, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 3192, "ts": 1791531124.500889, "chk": "ok", "code_len": 2293}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3396, "tout": 1244, "ts": 1791531145.4679394, "chk": null, "code_len": 2293}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791531095.826276}
{"ep": "h1-00978", "task": "L2_037", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2801, "speedup": 1.2801, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 203.7, "calls": 2, "tokens_in": 4943, "tokens_out": 3466, "ctx_chars": 0, "t_end": 1791531180.8429, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2801, "lo95": 1.2796, "mean": 1.2798, "ev_only": 1.2787, "ref_ms": 19.69474, "cand_ms": 15.38477, "n_trials": 70, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0551, "r_wall_s": 96.91, "compile_s": 5.2, "r_error": "", "src_len": 1929, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1709, "tout": 2446, "ts": 1791531018.243474, "chk": "ok", "code_len": 1929}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3234, "tout": 1020, "ts": 1791531083.043176, "chk": null, "code_len": 1929}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1709, "started": 1791530997.524611}
{"ep": "h1-01005", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2722, "speedup": 1.2722, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 101.2, "calls": 2, "tokens_in": 14954, "tokens_out": 4482, "ctx_chars": 10850, "t_end": 1791531181.1994498, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2722, "lo95": 1.2719, "mean": 1.2707, "ev_only": 1.274, "ref_ms": 7.28725, "cand_ms": 5.72788, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 45.31, "compile_s": 1.87, "r_error": "", "src_len": 2244, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6676, "tout": 2902, "ts": 1791531108.4552994, "chk": "ok", "code_len": 2244}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8278, "tout": 1580, "ts": 1791531135.7656124, "chk": null, "code_len": 2244}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6676, "started": 1791531080.0055149}
{"ep": "h1-01000", "task": "L2_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0188, "speedup": 1.0188, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 128.7, "calls": 3, "tokens_in": 7722, "tokens_out": 2104, "ctx_chars": 0, "t_end": 1791531185.1817026, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0188, "lo95": 1.0182, "mean": 1.0468, "ev_only": 1.0201, "ref_ms": 8.49259, "cand_ms": 8.33586, "n_trials": 147, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0482, "r_wall_s": 22.32, "compile_s": 1.87, "r_error": "", "src_len": 1845, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1713, "tout": 1147, "ts": 1791531067.615906, "chk": "ok", "code_len": 1845}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2972, "tout": 41, "ts": 1791531154.9263992, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3037, "tout": 916, "ts": 1791531162.7898152, "chk": null, "code_len": 1845}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1713, "started": 1791531056.4875758}
{"ep": "h1-01007", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 13.2066, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 105.1, "calls": 2, "tokens_in": 8997, "tokens_out": 4095, "ctx_chars": 4348, "t_end": 1791531185.9242494, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 13.2066, "lo95": 13.0601, "mean": 12.6427, "ev_only": 13.1582, "ref_ms": 10.20795, "cand_ms": 0.77294, "n_trials": 140, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 59.53, "compile_s": 2.71, "r_error": "", "src_len": 2682, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3531, "tout": 2633, "ts": 1791531103.6971233, "chk": "ok", "code_len": 2682}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5466, "tout": 1462, "ts": 1791531125.9052927, "chk": null, "code_len": 2682}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3531, "started": 1791531080.864885}
{"ep": "h1-00911", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 6.8761, "speedup": 6.8761, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 468.9, "calls": 3, "tokens_in": 34788, "tokens_out": 24726, "ctx_chars": 11175, "t_end": 1791531186.3443108, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.8761, "lo95": 6.8656, "mean": 6.856, "ev_only": 7.0339, "ref_ms": 4.40096, "cand_ms": 0.64004, "n_trials": 201, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 79.0, "compile_s": 1.79, "r_error": "", "src_len": 8664, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 16235, "ts": 1791530865.931247, "chk": "no_custom_kernel", "code_len": 8780}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11701, "tout": 4418, "ts": 1791530928.5468364, "chk": "ok", "code_len": 8664}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16020, "tout": 4073, "ts": 1791530974.7120724, "chk": null, "code_len": 8664}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 7067, "started": 1791530717.3946226}
{"ep": "h1-00974", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 6.515, "speedup": 6.515, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 235.2, "calls": 3, "tokens_in": 16001, "tokens_out": 14190, "ctx_chars": 0, "t_end": 1791531191.4982016, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.515, "lo95": 6.5072, "mean": 6.6615, "ev_only": 6.617, "ref_ms": 5.92781, "cand_ms": 0.90987, "n_trials": 186, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 39.15, "compile_s": 12.35, "r_error": "", "src_len": 6263, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1845, "tout": 7913, "ts": 1791531027.8392787, "chk": "no_custom_kernel", "code_len": 6315}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5474, "tout": 3265, "ts": 1791531112.2224898, "chk": "ok", "code_len": 6263}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8682, "tout": 3012, "ts": 1791531152.2469726, "chk": null, "code_len": 6263}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1845, "started": 1791530956.2971387}
{"ep": "h1-00985", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.353, "speedup": 2.353, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.1, "calls": 2, "tokens_in": 6043, "tokens_out": 8683, "ctx_chars": 0, "t_end": 1791531198.574581, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.353, "lo95": 2.3524, "mean": 2.3698, "ev_only": 2.3569, "ref_ms": 12.83628, "cand_ms": 5.45522, "n_trials": 124, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 33.31, "compile_s": 12.3, "r_error": "", "src_len": 4661, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1657, "tout": 6451, "ts": 1791531068.3641195, "chk": "ok", "code_len": 4661}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4386, "tout": 2232, "ts": 1791531165.2356274, "chk": null, "code_len": 4661}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1657, "started": 1791531011.4566472}
{"ep": "h1-00957", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.6798, "speedup": 9.6798, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 293.2, "calls": 3, "tokens_in": 14077, "tokens_out": 13013, "ctx_chars": 0, "t_end": 1791531205.064398, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 9.6798, "lo95": 9.6144, "mean": 9.2917, "ev_only": 9.6177, "ref_ms": 6.0148, "cand_ms": 0.62138, "n_trials": 193, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 124.84, "compile_s": 17.17, "r_error": "", "src_len": 4886, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1845, "tout": 7884, "ts": 1791530986.6231258, "chk": "no_custom_kernel", "code_len": 4908}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4822, "tout": 2630, "ts": 1791531022.7649808, "chk": "ok", "code_len": 4886}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7410, "tout": 2499, "ts": 1791531080.0326147, "chk": null, "code_len": 4886}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1845, "started": 1791530911.8937001}
{"ep": "h1-00929", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.4381, "speedup": 0.4381, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 412.4, "calls": 3, "tokens_in": 30797, "tokens_out": 17014, "ctx_chars": 10864, "t_end": 1791531206.3121912, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.4381, "lo95": 0.4375, "mean": 0.4383, "ev_only": 0.4379, "ref_ms": 10.0519, "cand_ms": 22.94481, "n_trials": 59, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 105.44, "compile_s": 10.86, "r_error": "", "src_len": 6428, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6627, "tout": 10323, "ts": 1791530888.938628, "chk": "no_custom_kernel", "code_len": 6398}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10398, "tout": 3597, "ts": 1791530940.7576168, "chk": "ok", "code_len": 6428}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13772, "tout": 3094, "ts": 1791531099.9271967, "chk": null, "code_len": 6428}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6627, "started": 1791530793.8931851}
{"ep": "h1-01018", "task": "L2_084", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0086, "speedup": 1.0086, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 118.0, "calls": 2, "tokens_in": 17878, "tokens_out": 7947, "ctx_chars": 9192, "t_end": 1791531213.932624, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0086, "lo95": 1.0082, "mean": 1.0221, "ev_only": 1.0091, "ref_ms": 8.11247, "cand_ms": 8.0435, "n_trials": 140, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0118, "r_wall_s": 32.45, "compile_s": 2.65, "r_error": "", "src_len": 3159, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5719, "tout": 6328, "ts": 1791531150.0814157, "chk": "ok", "code_len": 3159}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12159, "tout": 1619, "ts": 1791531181.4095845, "chk": null, "code_len": 3159}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5719, "started": 1791531095.9372015}
{"ep": "h1-00973", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3863, "speedup": 1.3863, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.8, "calls": 2, "tokens_in": 11000, "tokens_out": 7330, "ctx_chars": 2425, "t_end": 1791531215.3082037, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3863, "lo95": 1.386, "mean": 1.3873, "ev_only": 1.3867, "ref_ms": 75.2771, "cand_ms": 54.30057, "n_trials": 15, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0343, "r_wall_s": 150.67, "compile_s": 2.35, "r_error": "", "src_len": 4630, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3937, "tout": 4775, "ts": 1791530995.100836, "chk": "ok", "code_len": 4630}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7063, "tout": 2555, "ts": 1791531064.1397026, "chk": null, "code_len": 4630}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3937, "started": 1791530954.54546}
{"ep": "h1-01012", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0586, "speedup": 1.0586, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 135.9, "calls": 2, "tokens_in": 15108, "tokens_out": 4144, "ctx_chars": 11062, "t_end": 1791531222.4255176, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0586, "lo95": 1.0578, "mean": 1.0595, "ev_only": 1.0622, "ref_ms": 12.70235, "cand_ms": 11.99972, "n_trials": 54, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0169, "r_wall_s": 91.66, "compile_s": 2.75, "r_error": "", "src_len": 2320, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6695, "tout": 2935, "ts": 1791531112.9494798, "chk": "ok", "code_len": 2320}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8413, "tout": 1209, "ts": 1791531130.716252, "chk": null, "code_len": 2320}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6695, "started": 1791531086.4824686}
{"ep": "h1-01011", "task": "L1_065", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.1796, "speedup": 2.1796, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.8, "calls": 1, "tokens_in": 6886, "tokens_out": 1056, "ctx_chars": 11175, "t_end": 1791531227.5976026, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.1796, "lo95": 2.178, "mean": 2.1777, "ev_only": 2.1787, "ref_ms": 43.63654, "cand_ms": 20.02051, "n_trials": 33, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 132.16, "compile_s": 12.65, "r_error": "", "src_len": 2167, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6886, "tout": 1056, "ts": 1791531094.358461, "chk": null, "code_len": 2167}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6886, "started": 1791531084.7886207}
{"ep": "h1-00953", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4008, "speedup": 1.4008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 333.5, "calls": 2, "tokens_in": 5210, "tokens_out": 4872, "ctx_chars": 0, "t_end": 1791531228.4988046, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4008, "lo95": 1.3992, "mean": 1.399, "ev_only": 1.399, "ref_ms": 7.53113, "cand_ms": 5.37633, "n_trials": 213, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 142.96, "compile_s": 9.31, "r_error": "", "src_len": 2716, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 3373, "ts": 1791530924.3752325, "chk": "ok", "code_len": 2763}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3643, "tout": 1499, "ts": 1791531085.3735762, "chk": null, "code_len": 2716}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791530894.9677877}
{"ep": "h1-00932", "task": "L2_068", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0006, "speedup": 1.0006, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 417.8, "calls": 2, "tokens_in": 3941, "tokens_out": 2147, "ctx_chars": 0, "t_end": 1791531229.1530192, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0006, "lo95": 0.9976, "mean": 0.9989, "ev_only": 1.001, "ref_ms": 4.45656, "cand_ms": 4.4537, "n_trials": 222, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0023, "r_wall_s": 157.65, "compile_s": 2.47, "r_error": "", "src_len": 948, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1532, "tout": 1554, "ts": 1791530827.220337, "chk": "ok", "code_len": 948}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2409, "tout": 593, "ts": 1791531071.3825736, "chk": null, "code_len": 948}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1532, "started": 1791530811.3373585}
{"ep": "h1-00930", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.5567, "speedup": 4.5567, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 431.3, "calls": 3, "tokens_in": 18183, "tokens_out": 19158, "ctx_chars": 0, "t_end": 1791531230.1239352, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.5567, "lo95": 4.5155, "mean": 4.5585, "ev_only": 4.5633, "ref_ms": 32.15635, "cand_ms": 7.05701, "n_trials": 38, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 138.01, "compile_s": 26.59, "r_error": "", "src_len": 7071, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1966, "tout": 11474, "ts": 1791530900.075278, "chk": "no_custom_kernel", "code_len": 7095}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6180, "tout": 4017, "ts": 1791530946.6969223, "chk": "ok", "code_len": 7071}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10037, "tout": 3667, "ts": 1791531092.0006928, "chk": null, "code_len": 7071}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1966, "started": 1791530798.7954884}
{"ep": "h1-00927", "task": "L3_038", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7804, "speedup": 0.7804, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 439.2, "calls": 3, "tokens_in": 18774, "tokens_out": 1759, "ctx_chars": 8224, "t_end": 1791531232.2289326, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7804, "lo95": 0.7759, "mean": 0.7801, "ev_only": 0.7802, "ref_ms": 79.18667, "cand_ms": 101.47218, "n_trials": 10, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0, "r_wall_s": 175.37, "compile_s": 2.44, "r_error": "", "src_len": 1462, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5514, "tout": 964, "ts": 1791530803.0238948, "chk": "ok", "code_len": 1462}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6590, "tout": 56, "ts": 1791531050.2286417, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6670, "tout": 739, "ts": 1791531056.7523105, "chk": null, "code_len": 1462}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5514, "started": 1791530793.0326517}
{"ep": "h1-00984", "task": "L1_080", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.307, "speedup": 0.307, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 250.7, "calls": 4, "tokens_in": 21658, "tokens_out": 6610, "ctx_chars": 0, "t_end": 1791531250.7890303, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.307, "lo95": 0.2878, "mean": 0.2874, "ev_only": 0.3069, "ref_ms": 20.21527, "cand_ms": 65.85304, "n_trials": 17, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 114.89, "compile_s": 1.91, "r_error": "", "src_len": 3145, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2006, "tout": 3096, "ts": 1791531027.5313706, "chk": "ok", "code_len": 2753}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5211, "tout": 1873, "ts": 1791531072.3712027, "chk": "ok", "code_len": 3145}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7193, "tout": 31, "ts": 1791531121.941664, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7248, "tout": 1610, "ts": 1791531135.0589612, "chk": null, "code_len": 3145}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", "no_code", null], "first_tin": 2006, "started": 1791531000.1381972}
{"ep": "h1-00952", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1652, "speedup": 1.1652, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 364.2, "calls": 3, "tokens_in": 25645, "tokens_out": 5663, "ctx_chars": 11535, "t_end": 1791531256.8829327, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1652, "lo95": 1.1641, "mean": 1.1651, "ev_only": 1.1675, "ref_ms": 20.0627, "cand_ms": 17.21807, "n_trials": 30, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0268, "r_wall_s": 185.32, "compile_s": 2.44, "r_error": "", "src_len": 2145, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6867, "tout": 2668, "ts": 1791530916.1818342, "chk": "runtime_error", "code_len": 2212}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8708, "tout": 1657, "ts": 1791530973.0064063, "chk": "ok", "code_len": 2145}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10070, "tout": 1338, "ts": 1791531071.4536183, "chk": null, "code_len": 2145}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 6867, "started": 1791530892.7143967}
{"ep": "h1-00964", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.2232, "speedup": 3.2232, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 335.4, "calls": 2, "tokens_in": 8084, "tokens_out": 15518, "ctx_chars": 0, "t_end": 1791531257.5531456, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.2232, "lo95": 3.2213, "mean": 3.2183, "ev_only": 3.2151, "ref_ms": 4.728, "cand_ms": 1.46688, "n_trials": 193, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9985, "r_wall_s": 162.61, "compile_s": 29.64, "r_error": "", "src_len": 8123, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1917, "tout": 11819, "ts": 1791531029.0359194, "chk": "ok", "code_len": 8140}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6167, "tout": 3699, "ts": 1791531094.7888288, "chk": null, "code_len": 8123}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1917, "started": 1791530922.1494184}
{"ep": "h1-00983", "task": "L3_039", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.116, "speedup": 0.116, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 263.9, "calls": 3, "tokens_in": 26379, "tokens_out": 6247, "ctx_chars": 8224, "t_end": 1791531261.0640483, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.116, "lo95": 0.115, "mean": 0.1153, "ev_only": 0.116, "ref_ms": 31.84608, "cand_ms": 274.58396, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2764, "r_wall_s": 175.72, "compile_s": 6.2, "r_error": "", "src_len": 2776, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 4800, "ts": 1791531040.2281454, "chk": "ok", "code_len": 2776}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10400, "tout": 67, "ts": 1791531073.5713415, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10491, "tout": 1380, "ts": 1791531085.2255528, "chk": null, "code_len": 2776}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5488, "started": 1791530997.1395197}
{"ep": "h1-00997", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.216, "speedup": 1.216, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.7, "calls": 2, "tokens_in": 16925, "tokens_out": 6705, "ctx_chars": 13278, "t_end": 1791531265.1946669, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.216, "lo95": 1.2153, "mean": 1.2142, "ev_only": 1.2131, "ref_ms": 5.31567, "cand_ms": 4.37138, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9987, "r_wall_s": 71.64, "compile_s": 2.77, "r_error": "", "src_len": 3551, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 4756, "ts": 1791531086.3821304, "chk": "ok", "code_len": 3551}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9763, "tout": 1949, "ts": 1791531192.8534322, "chk": null, "code_len": 3551}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791531045.5418139}
{"ep": "h1-01029", "task": "L2_062", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0079, "speedup": 1.0079, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 102.7, "calls": 2, "tokens_in": 12514, "tokens_out": 2405, "ctx_chars": 8462, "t_end": 1791531266.0464537, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0079, "lo95": 1.0066, "mean": 1.0112, "ev_only": 1.0127, "ref_ms": 8.58212, "cand_ms": 8.51444, "n_trials": 152, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0532, "r_wall_s": 68.5, "compile_s": 3.17, "r_error": "", "src_len": 1606, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5400, "tout": 1602, "ts": 1791531178.4290357, "chk": "ok", "code_len": 1606}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7114, "tout": 803, "ts": 1791531197.4402826, "chk": null, "code_len": 1606}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5400, "started": 1791531163.3426306}
{"ep": "h1-01004", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.9198, "speedup": 1.9198, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 192.2, "calls": 2, "tokens_in": 6004, "tokens_out": 10247, "ctx_chars": 0, "t_end": 1791531267.6240041, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.9198, "lo95": 1.9147, "mean": 1.9281, "ev_only": 1.9324, "ref_ms": 19.30475, "cand_ms": 10.05582, "n_trials": 74, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 85.29, "compile_s": 11.73, "r_error": "", "src_len": 4490, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1586, "tout": 7967, "ts": 1791531148.504094, "chk": "ok", "code_len": 4490}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4418, "tout": 2280, "ts": 1791531182.2611883, "chk": null, "code_len": 4490}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1586, "started": 1791531075.4583337}
{"ep": "h1-01008", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1518, "speedup": 1.1518, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 191.8, "calls": 2, "tokens_in": 18577, "tokens_out": 17362, "ctx_chars": 6513, "t_end": 1791531273.2817848, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1518, "lo95": 1.1471, "mean": 1.1766, "ev_only": 1.1532, "ref_ms": 6.23583, "cand_ms": 5.41422, "n_trials": 196, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.3693, "r_wall_s": 32.25, "compile_s": 11.81, "r_error": "", "src_len": 12432, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6068, "tout": 11517, "ts": 1791531177.0184572, "chk": "ok", "code_len": 12432}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12509, "tout": 5845, "ts": 1791531240.9685547, "chk": null, "code_len": 12432}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6068, "started": 1791531081.5312448}
{"ep": "h1-01030", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.6638, "speedup": 2.6638, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 109.5, "calls": 2, "tokens_in": 17253, "tokens_out": 8242, "ctx_chars": 10384, "t_end": 1791531278.3333185, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.6638, "lo95": 2.6613, "mean": 2.6573, "ev_only": 2.6876, "ref_ms": 3.6442, "cand_ms": 1.36806, "n_trials": 198, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5502, "r_wall_s": 27.29, "compile_s": 2.09, "r_error": "", "src_len": 4249, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 6219, "ts": 1791531225.9262593, "chk": "ok", "code_len": 4249}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9956, "tout": 2023, "ts": 1791531250.8125863, "chk": null, "code_len": 4249}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791531168.7883182}
{"ep": "h1-01049", "task": "L2_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0399, "speedup": 1.0399, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 55.3, "calls": 1, "tokens_in": 6248, "tokens_out": 1010, "ctx_chars": 10191, "t_end": 1791531285.4649003, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0399, "lo95": 1.0344, "mean": 1.0088, "ev_only": 1.0371, "ref_ms": 8.60157, "cand_ms": 8.2715, "n_trials": 140, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0367, "r_wall_s": 46.12, "compile_s": 1.86, "r_error": "", "src_len": 1961, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6248, "tout": 1010, "ts": 1791531239.2358527, "chk": null, "code_len": 1961}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6248, "started": 1791531230.1241663}
{"ep": "h1-01022", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4164, "speedup": 1.4164, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 165.3, "calls": 2, "tokens_in": 13984, "tokens_out": 1944, "ctx_chars": 10756, "t_end": 1791531293.2494297, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4164, "lo95": 1.4145, "mean": 1.4155, "ev_only": 1.4146, "ref_ms": 14.02213, "cand_ms": 9.89972, "n_trials": 100, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0818, "r_wall_s": 100.69, "compile_s": 2.45, "r_error": "", "src_len": 1207, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6463, "tout": 1311, "ts": 1791531139.863093, "chk": "ok", "code_len": 1207}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7521, "tout": 633, "ts": 1791531191.75026, "chk": null, "code_len": 1207}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6463, "started": 1791531127.9124594}
{"ep": "h1-01020", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5995, "speedup": 0.5995, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.4, "calls": 2, "tokens_in": 16156, "tokens_out": 11997, "ctx_chars": 6513, "t_end": 1791531295.4941635, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.5995, "lo95": 0.5979, "mean": 0.6043, "ev_only": 0.5992, "ref_ms": 5.91179, "cand_ms": 9.86125, "n_trials": 156, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3233, "r_wall_s": 79.06, "compile_s": 5.88, "r_error": "", "src_len": 7416, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6068, "tout": 8329, "ts": 1791531177.7152476, "chk": "ok", "code_len": 7416}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10088, "tout": 3668, "ts": 1791531216.4086661, "chk": null, "code_len": 7416}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6068, "started": 1791531106.1198144}
{"ep": "h1-00993", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5421, "speedup": 1.5421, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.5, "calls": 2, "tokens_in": 5479, "tokens_out": 5102, "ctx_chars": 0, "t_end": 1791531296.1167324, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5421, "lo95": 1.5414, "mean": 1.5506, "ev_only": 1.5442, "ref_ms": 7.99561, "cand_ms": 5.1848, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 29.89, "compile_s": 2.07, "r_error": "", "src_len": 3279, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1588, "tout": 3301, "ts": 1791531086.9984574, "chk": "ok", "code_len": 3279}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3891, "tout": 1801, "ts": 1791531266.1263518, "chk": null, "code_len": 3279}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1588, "started": 1791531057.9232497}
{"ep": "h1-00999", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.0621, "speedup": 4.0621, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.5, "calls": 2, "tokens_in": 7331, "tokens_out": 13305, "ctx_chars": 0, "t_end": 1791531297.5118306, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.0621, "lo95": 4.059, "mean": 4.0559, "ev_only": 4.0672, "ref_ms": 20.08775, "cand_ms": 4.94519, "n_trials": 70, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 94.84, "compile_s": 19.73, "r_error": "", "src_len": 6702, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1729, "tout": 10068, "ts": 1791531146.825469, "chk": "ok", "code_len": 6721}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5602, "tout": 3237, "ts": 1791531202.6478589, "chk": null, "code_len": 6702}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1729, "started": 1791531054.0164156}
{"ep": "h1-01058", "task": "L2_070", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.014, "speedup": 1.014, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 27.5, "calls": 1, "tokens_in": 5600, "tokens_out": 441, "ctx_chars": 9220, "t_end": 1791531300.7865136, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.014, "lo95": 1.0104, "mean": 1.0146, "ev_only": 1.015, "ref_ms": 8.09282, "cand_ms": 7.98142, "n_trials": 166, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 22.87, "compile_s": 2.54, "r_error": "", "src_len": 876, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5600, "tout": 441, "ts": 1791531277.8457448, "chk": null, "code_len": 876}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5600, "started": 1791531273.2820399}
{"ep": "h1-00969", "task": "L2_025", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0172, "speedup": 1.0172, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 359.3, "calls": 2, "tokens_in": 4103, "tokens_out": 1530, "ctx_chars": 0, "t_end": 1791531305.2121646, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0172, "lo95": 1.0166, "mean": 1.0304, "ev_only": 1.0174, "ref_ms": 19.19246, "cand_ms": 18.8674, "n_trials": 76, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0745, "r_wall_s": 236.78, "compile_s": 2.49, "r_error": "", "src_len": 1264, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1584, "tout": 826, "ts": 1791530955.3698835, "chk": "ok", "code_len": 1322}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2519, "tout": 704, "ts": 1791531068.270209, "chk": null, "code_len": 1264}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1584, "started": 1791530945.8866196}
{"ep": "h1-01037", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.5034, "speedup": 2.5034, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 119.8, "calls": 2, "tokens_in": 16670, "tokens_out": 7449, "ctx_chars": 10384, "t_end": 1791531305.7212434, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.5034, "lo95": 2.4978, "mean": 2.4927, "ev_only": 2.5192, "ref_ms": 4.03515, "cand_ms": 1.61184, "n_trials": 179, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3929, "r_wall_s": 45.37, "compile_s": 2.0, "r_error": "", "src_len": 3062, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 5892, "ts": 1791531238.9679315, "chk": "ok", "code_len": 3062}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9373, "tout": 1557, "ts": 1791531260.0840054, "chk": null, "code_len": 3062}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791531185.9248185}
{"ep": "h1-01047", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.7882, "speedup": 4.7882, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 87.3, "calls": 2, "tokens_in": 5606, "tokens_out": 5575, "ctx_chars": 0, "t_end": 1791531315.7585127, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.7882, "lo95": 4.7862, "mean": 4.7932, "ev_only": 4.8284, "ref_ms": 7.36674, "cand_ms": 1.53852, "n_trials": 213, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 31.49, "compile_s": 1.96, "r_error": "", "src_len": 2998, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1678, "tout": 3605, "ts": 1791531260.5585701, "chk": "ok", "code_len": 3536}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3928, "tout": 1970, "ts": 1791531284.1258202, "chk": null, "code_len": 2998}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1678, "started": 1791531228.4990785}
{"ep": "h1-01048", "task": "L1_077", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9126, "speedup": 0.9126, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 90.3, "calls": 1, "tokens_in": 2021, "tokens_out": 1148, "ctx_chars": 0, "t_end": 1791531319.458674, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9126, "lo95": 0.9122, "mean": 0.9128, "ev_only": 0.913, "ref_ms": 8.60431, "cand_ms": 9.42872, "n_trials": 138, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0723, "r_wall_s": 77.05, "compile_s": 1.99, "r_error": "", "src_len": 1812, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2021, "tout": 1148, "ts": 1791531241.334575, "chk": null, "code_len": 1812}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2021, "started": 1791531229.1532457}
{"ep": "h1-01003", "task": "L2_025", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.8269, "speedup": 1.8269, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 248.9, "calls": 2, "tokens_in": 6062, "tokens_out": 8351, "ctx_chars": 0, "t_end": 1791531321.7914467, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.8269, "lo95": 1.8254, "mean": 1.8538, "ev_only": 1.8283, "ref_ms": 19.17407, "cand_ms": 10.49536, "n_trials": 68, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 131.2, "compile_s": 15.57, "r_error": "", "src_len": 4619, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1586, "tout": 6049, "ts": 1791531124.798235, "chk": "ok", "code_len": 4619}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4476, "tout": 2302, "ts": 1791531190.515607, "chk": null, "code_len": 4619}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1586, "started": 1791531072.8798661}
{"ep": "h1-01052", "task": "L2_025", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 66.3, "calls": 1, "tokens_in": 1584, "tokens_out": 959, "ctx_chars": 0, "t_end": 1791531323.1456482, "error": "RuntimeError: Error building extension 'min_tanh_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=min_tanh_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 56.85, "compile_s": 56.85, "r_error": "RuntimeError: Error building extension 'min_tanh_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=min_tanh_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 1936, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1584, "tout": 959, "ts": 1791531266.27053, "chk": null, "code_len": 1936}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1584, "started": 1791531256.8831701}
{"ep": "h1-00986", "task": "L1_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2071, "speedup": 1.2071, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 320.1, "calls": 2, "tokens_in": 5021, "tokens_out": 4354, "ctx_chars": 0, "t_end": 1791531336.6814528, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2071, "lo95": 1.2065, "mean": 1.27, "ev_only": 1.2087, "ref_ms": 7.283, "cand_ms": 6.03351, "n_trials": 107, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 268.06, "compile_s": 2.33, "r_error": "", "src_len": 2453, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1572, "tout": 2722, "ts": 1791531039.7309418, "chk": "ok", "code_len": 2453}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3449, "tout": 1632, "ts": 1791531068.397083, "chk": null, "code_len": 2453}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1572, "started": 1791531016.6114333}
{"ep": "h1-01001", "task": "L2_074", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2601, "speedup": 1.2601, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 281.8, "calls": 3, "tokens_in": 22081, "tokens_out": 2403, "ctx_chars": 10364, "t_end": 1791531341.242017, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2601, "lo95": 1.2589, "mean": 1.2573, "ev_only": 1.2651, "ref_ms": 5.90563, "cand_ms": 4.68655, "n_trials": 215, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0451, "r_wall_s": 55.39, "compile_s": 1.91, "r_error": "", "src_len": 2152, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6395, "tout": 1311, "ts": 1791531072.158332, "chk": "ok", "code_len": 2152}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7818, "tout": 26, "ts": 1791531276.4890711, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7868, "tout": 1066, "ts": 1791531285.771346, "chk": null, "code_len": 2152}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6395, "started": 1791531059.4461024}
{"ep": "h1-00920", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.3607, "speedup": 3.3607, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 583.2, "calls": 3, "tokens_in": 29481, "tokens_out": 21595, "ctx_chars": 8224, "t_end": 1791531349.4138381, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.3607, "lo95": 3.3535, "mean": 3.5429, "ev_only": 3.3628, "ref_ms": 31.90108, "cand_ms": 9.49237, "n_trials": 41, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 264.87, "compile_s": 21.25, "r_error": "", "src_len": 7997, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 13274, "ts": 1791530885.7229695, "chk": "no_custom_kernel", "code_len": 8002}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9978, "tout": 4550, "ts": 1791530940.3734965, "chk": "ok", "code_len": 7997}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14013, "tout": 3771, "ts": 1791531084.4265463, "chk": null, "code_len": 7997}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791530766.174192}
{"ep": "h1-00942", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.1805, "speedup": 4.1805, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 510.4, "calls": 3, "tokens_in": 33704, "tokens_out": 18395, "ctx_chars": 11175, "t_end": 1791531353.559073, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.1805, "lo95": 4.1729, "mean": 4.1747, "ev_only": 4.2302, "ref_ms": 4.38685, "cand_ms": 1.04936, "n_trials": 200, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 271.81, "compile_s": 18.62, "r_error": "", "src_len": 7422, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 10606, "ts": 1791530958.6478753, "chk": "no_custom_kernel", "code_len": 7444}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11364, "tout": 4109, "ts": 1791531029.2786007, "chk": "ok", "code_len": 7422}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15273, "tout": 3680, "ts": 1791531081.4534495, "chk": null, "code_len": 7422}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 7067, "started": 1791530863.5444264}
{"ep": "h1-01023", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.287, "speedup": 1.287, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.5, "calls": 2, "tokens_in": 15967, "tokens_out": 6222, "ctx_chars": 11535, "t_end": 1791531354.1491709, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.287, "lo95": 1.2865, "mean": 1.2872, "ev_only": 1.2876, "ref_ms": 20.11043, "cand_ms": 15.62627, "n_trials": 73, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9971, "r_wall_s": 145.91, "compile_s": 3.23, "r_error": "", "src_len": 3305, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6867, "tout": 4446, "ts": 1791531174.1492229, "chk": "ok", "code_len": 3305}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9100, "tout": 1776, "ts": 1791531208.2140894, "chk": null, "code_len": 3305}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6867, "started": 1791531134.69467}
{"ep": "h1-01032", "task": "L2_053", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0121, "speedup": 1.0121, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.6, "calls": 2, "tokens_in": 13642, "tokens_out": 1406, "ctx_chars": 10749, "t_end": 1791531362.51642, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0121, "lo95": 1.0116, "mean": 1.012, "ev_only": 1.0123, "ref_ms": 15.9374, "cand_ms": 15.74723, "n_trials": 83, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 151.45, "compile_s": 3.39, "r_error": "", "src_len": 1140, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6387, "tout": 759, "ts": 1791531179.5375302, "chk": "ok", "code_len": 1140}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7255, "tout": 647, "ts": 1791531210.889219, "chk": null, "code_len": 1140}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6387, "started": 1791531172.8849015}
{"ep": "h1-00907", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0562, "speedup": 1.0562, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 675.2, "calls": 5, "tokens_in": 39092, "tokens_out": 23323, "ctx_chars": 2425, "t_end": 1791531366.8979075, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0562, "lo95": 1.0559, "mean": 1.0576, "ev_only": 1.0559, "ref_ms": 15.87929, "cand_ms": 15.03446, "n_trials": 90, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0695, "r_wall_s": 75.66, "compile_s": 1.92, "r_error": "", "src_len": 3611, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3753, "tout": 4180, "ts": 1791530729.6371458, "chk": "incorrect", "code_len": 2985}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5718, "tout": 6484, "ts": 1791530818.9448519, "chk": "incorrect", "code_len": 3147}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7831, "tout": 7493, "ts": 1791531014.0890067, "chk": "incorrect", "code_len": 3147}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9793, "tout": 3250, "ts": 1791531063.22661, "chk": "ok", "code_len": 3611}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11997, "tout": 1916, "ts": 1791531290.4173486, "chk": null, "code_len": 3611}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 3753, "started": 1791530691.652648}
{"ep": "h1-01068", "task": "L2_068", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 64.5, "calls": 1, "tokens_in": 1530, "tokens_out": 887, "ctx_chars": 0, "t_end": 1791531380.2159836, "error": "RuntimeError: Error building extension 'fuse_minsub': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_minsub -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 55.84, "compile_s": 55.83, "r_error": "RuntimeError: Error building extension 'fuse_minsub': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_minsub -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "src_len": 1699, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1530, "tout": 887, "ts": 1791531324.3557692, "chk": null, "code_len": 1699}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1530, "started": 1791531315.7587492}
{"ep": "h1-01024", "task": "L1_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.8944, "speedup": 0.8944, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 247.9, "calls": 3, "tokens_in": 8732, "tokens_out": 3696, "ctx_chars": 0, "t_end": 1791531393.1712236, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8944, "lo95": 0.894, "mean": 0.8942, "ev_only": 0.895, "ref_ms": 7.31951, "cand_ms": 8.18412, "n_trials": 185, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 180.72, "compile_s": 3.24, "r_error": "", "src_len": 3077, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1570, "tout": 1855, "ts": 1791531161.152635, "chk": "ok", "code_len": 3077}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3534, "tout": 70, "ts": 1791531198.202189, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3628, "tout": 1771, "ts": 1791531212.2424471, "chk": null, "code_len": 3077}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1570, "started": 1791531145.2691667}
{"ep": "h1-01031", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2577, "speedup": 1.2577, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 222.4, "calls": 2, "tokens_in": 21496, "tokens_out": 15800, "ctx_chars": 0, "t_end": 1791531394.763562, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2577, "lo95": 1.129, "mean": 1.3216, "ev_only": 1.2692, "ref_ms": 9.77776, "cand_ms": 7.7745, "n_trials": 119, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.09, "r_wall_s": 89.92, "compile_s": 2.64, "r_error": "", "src_len": 12199, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7618, "tout": 10126, "ts": 1791531255.2914164, "chk": "ok", "code_len": 12332}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 13878, "tout": 5674, "ts": 1791531304.5730321, "chk": null, "code_len": 12199}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7618, "started": 1791531172.3444269}
{"ep": "h1-01051", "task": "L1_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4173, "speedup": 1.4173, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.0, "calls": 2, "tokens_in": 4933, "tokens_out": 4288, "ctx_chars": 0, "t_end": 1791531394.8130918, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4173, "lo95": 1.4147, "mean": 1.4063, "ev_only": 1.4134, "ref_ms": 7.58744, "cand_ms": 5.35343, "n_trials": 170, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 93.68, "compile_s": 3.04, "r_error": "", "src_len": 2483, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 2726, "ts": 1791531275.121054, "chk": "ok", "code_len": 2483}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3366, "tout": 1562, "ts": 1791531301.0628028, "chk": null, "code_len": 2483}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791531250.789277}
{"ep": "h1-01041", "task": "L1_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.68, "speedup": 4.68, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 192.6, "calls": 1, "tokens_in": 5859, "tokens_out": 1187, "ctx_chars": 9438, "t_end": 1791531397.625552, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.68, "lo95": 4.6678, "mean": 4.6449, "ev_only": 4.7284, "ref_ms": 7.41638, "cand_ms": 1.58471, "n_trials": 216, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9702, "r_wall_s": 181.93, "compile_s": 3.32, "r_error": "", "src_len": 1908, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5859, "tout": 1187, "ts": 1791531215.552322, "chk": null, "code_len": 1908}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5859, "started": 1791531205.0646482}
{"ep": "h1-01043", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 25.9613, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 191.0, "calls": 2, "tokens_in": 6241, "tokens_out": 6505, "ctx_chars": 0, "t_end": 1791531404.9392173, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 25.9613, "lo95": 25.6385, "mean": 25.1414, "ev_only": 25.9421, "ref_ms": 25.12302, "cand_ms": 0.96771, "n_trials": 32, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 111.47, "compile_s": 16.29, "r_error": "", "src_len": 4348, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1755, "tout": 4327, "ts": 1791531251.133915, "chk": "ok", "code_len": 4348}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4486, "tout": 2178, "ts": 1791531293.3301222, "chk": null, "code_len": 4348}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1755, "started": 1791531213.932905}
{"ep": "h1-00987", "task": "L3_042", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.5434, "speedup": 3.5434, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 393.9, "calls": 3, "tokens_in": 27622, "tokens_out": 16417, "ctx_chars": 8224, "t_end": 1791531411.728612, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 3.5434, "lo95": 3.531, "mean": 3.5486, "ev_only": 3.545, "ref_ms": 60.73242, "cand_ms": 17.13966, "n_trials": 21, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8289, "r_wall_s": 205.93, "compile_s": 18.7, "r_error": "", "src_len": 6604, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5503, "tout": 9339, "ts": 1791531102.3734233, "chk": "no_custom_kernel", "code_len": 6626}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9358, "tout": 3623, "ts": 1791531148.8088384, "chk": "ok", "code_len": 6604}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12761, "tout": 3455, "ts": 1791531205.7688236, "chk": null, "code_len": 6604}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5503, "started": 1791531017.846046}
{"ep": "h1-00981", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0431, "speedup": 1.0431, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 421.5, "calls": 2, "tokens_in": 19256, "tokens_out": 25753, "ctx_chars": 6513, "t_end": 1791531414.6528888, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0431, "lo95": 1.0415, "mean": 1.0422, "ev_only": 1.0433, "ref_ms": 20.04846, "cand_ms": 19.22036, "n_trials": 62, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3001, "r_wall_s": 197.33, "compile_s": 8.35, "r_error": "", "src_len": 11735, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6296, "tout": 19765, "ts": 1791531166.955746, "chk": "ok", "code_len": 11735}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12960, "tout": 5988, "ts": 1791531217.2950866, "chk": null, "code_len": 11735}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6296, "started": 1791530993.118714}
{"ep": "h1-01026", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5376, "speedup": 1.5376, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.5, "calls": 2, "tokens_in": 5448, "tokens_out": 6032, "ctx_chars": 0, "t_end": 1791531418.0132835, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5376, "lo95": 1.5353, "mean": 1.5359, "ev_only": 1.5378, "ref_ms": 33.77633, "cand_ms": 21.96761, "n_trials": 38, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 56.46, "compile_s": 2.01, "r_error": "", "src_len": 2571, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 4623, "ts": 1791531199.1407256, "chk": "ok", "code_len": 2571}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3733, "tout": 1409, "ts": 1791531361.492579, "chk": null, "code_len": 2571}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791531157.503557}
{"ep": "h1-01028", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0331, "speedup": 1.0331, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.6, "calls": 2, "tokens_in": 14069, "tokens_out": 1500, "ctx_chars": 10901, "t_end": 1791531419.7728698, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0331, "lo95": 1.0329, "mean": 1.0331, "ev_only": 1.0355, "ref_ms": 8.23902, "cand_ms": 7.97487, "n_trials": 148, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 209.87, "compile_s": 3.26, "r_error": "", "src_len": 966, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6549, "tout": 859, "ts": 1791531191.8605998, "chk": "ok", "code_len": 966}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7520, "tout": 641, "ts": 1791531209.8317912, "chk": null, "code_len": 966}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6549, "started": 1791531181.5423796}
{"ep": "h1-01014", "task": "L2_055", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0024, "speedup": 1.0024, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 330.5, "calls": 3, "tokens_in": 19718, "tokens_out": 1291, "ctx_chars": 9898, "t_end": 1791531420.6276603, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0024, "lo95": 1.001, "mean": 1.0028, "ev_only": 1.0024, "ref_ms": 16.12794, "cand_ms": 16.08958, "n_trials": 73, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0012, "r_wall_s": 66.74, "compile_s": 1.9, "r_error": "", "src_len": 1227, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6025, "tout": 693, "ts": 1791531097.9398527, "chk": "ok", "code_len": 1406}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6828, "tout": 13, "ts": 1791531348.3682034, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6865, "tout": 585, "ts": 1791531353.846249, "chk": null, "code_len": 1227}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6025, "started": 1791531090.087068}
{"ep": "h1-01034", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.244, "speedup": 1.244, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 242.5, "calls": 2, "tokens_in": 16178, "tokens_out": 3888, "ctx_chars": 12471, "t_end": 1791531423.3281648, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.244, "lo95": 1.2435, "mean": 1.2436, "ev_only": 1.246, "ref_ms": 3.63845, "cand_ms": 2.92472, "n_trials": 225, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 121.5, "compile_s": 2.89, "r_error": "", "src_len": 2155, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7230, "tout": 2739, "ts": 1791531206.2180521, "chk": "ok", "code_len": 2155}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8948, "tout": 1149, "ts": 1791531301.01061, "chk": null, "code_len": 2155}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7230, "started": 1791531180.843154}
{"ep": "h1-00955", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7863, "speedup": 0.7863, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 522.7, "calls": 2, "tokens_in": 12108, "tokens_out": 29438, "ctx_chars": 0, "t_end": 1791531427.0999048, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7863, "lo95": 0.7856, "mean": 0.7883, "ev_only": 0.7865, "ref_ms": 5.22686, "cand_ms": 6.64759, "n_trials": 166, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0593, "r_wall_s": 138.26, "compile_s": 19.26, "r_error": "", "src_len": 13465, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1974, "tout": 21822, "ts": 1791531090.5907023, "chk": "ok", "code_len": 13465}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10134, "tout": 7616, "ts": 1791531288.6157844, "chk": null, "code_len": 13465}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1974, "started": 1791530904.3901374}
{"ep": "h1-01039", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.1407, "speedup": 5.1407, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.3, "calls": 2, "tokens_in": 4941, "tokens_out": 3814, "ctx_chars": 0, "t_end": 1791531428.7965605, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.1407, "lo95": 5.1334, "mean": 5.0806, "ev_only": 5.1893, "ref_ms": 7.37533, "cand_ms": 1.43469, "n_trials": 155, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 48.71, "compile_s": 1.98, "r_error": "", "src_len": 2174, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1678, "tout": 2657, "ts": 1791531215.1691804, "chk": "ok", "code_len": 2174}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3263, "tout": 1157, "ts": 1791531379.9330587, "chk": null, "code_len": 2174}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1678, "started": 1791531191.4984798}
{"ep": "h1-00976", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0082, "speedup": 1.0082, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 477.9, "calls": 5, "tokens_in": 52324, "tokens_out": 23973, "ctx_chars": 0, "t_end": 1791531435.6315615, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0082, "lo95": 1.0065, "mean": 0.986, "ev_only": 1.0074, "ref_ms": 23.47036, "cand_ms": 23.27985, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0079, "r_wall_s": 72.04, "compile_s": 3.31, "r_error": "", "src_len": 4454, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2736, "tout": 7453, "ts": 1791531022.903546, "chk": "incorrect", "code_len": 7420}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7070, "tout": 6340, "ts": 1791531119.4341578, "chk": "incorrect", "code_len": 7368}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11319, "tout": 4249, "ts": 1791531165.0083928, "chk": "incorrect", "code_len": 5016}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 14234, "tout": 3408, "ts": 1791531202.3866751, "chk": "ok", "code_len": 4454}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 16965, "tout": 2523, "ts": 1791531363.480921, "chk": null, "code_len": 4454}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 2736, "started": 1791530957.7321012}
{"ep": "h1-01066", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 7.2882, "speedup": 7.2882, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 136.2, "calls": 2, "tokens_in": 4170, "tokens_out": 1485, "ctx_chars": 0, "t_end": 1791531441.4444854, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.2882, "lo95": 7.2673, "mean": 7.1038, "ev_only": 7.2677, "ref_ms": 3.58394, "cand_ms": 0.49174, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 87.77, "compile_s": 2.04, "r_error": "", "src_len": 924, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 930, "ts": 1791531313.5522091, "chk": "ok", "code_len": 924}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2606, "tout": 555, "ts": 1791531352.9838026, "chk": null, "code_len": 924}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791531305.2124112}
{"ep": "h1-01006", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 5.9007, "speedup": 5.9007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 361.6, "calls": 4, "tokens_in": 24521, "tokens_out": 26970, "ctx_chars": 0, "t_end": 1791531442.109143, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.9007, "lo95": 5.8557, "mean": 6.2381, "ev_only": 5.9058, "ref_ms": 32.90246, "cand_ms": 5.57598, "n_trials": 34, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 69.07, "compile_s": 12.29, "r_error": "", "src_len": 8233, "atts": [{"turn": 0, "action": "CHECK", "stop": null, "tin": 1966, "tout": 8688, "ts": 1791531164.278669, "chk": "no_code", "code_len": 0}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3117, "tout": 9954, "ts": 1791531243.6997538, "chk": "no_custom_kernel", "code_len": 8257}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7650, "tout": 4350, "ts": 1791531292.4532728, "chk": "ok", "code_len": 8233}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11788, "tout": 3978, "ts": 1791531372.9931185, "chk": null, "code_len": 8233}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn", null], "chk_statuses": ["no_code", "no_custom_kernel", "ok", null], "first_tin": 1966, "started": 1791531080.550991}
{"ep": "h1-01040", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.067, "speedup": 1.067, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 243.6, "calls": 2, "tokens_in": 13753, "tokens_out": 1945, "ctx_chars": 10191, "t_end": 1791531442.133325, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.067, "lo95": 1.0661, "mean": 1.0679, "ev_only": 1.0648, "ref_ms": 8.49402, "cand_ms": 7.96062, "n_trials": 168, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0057, "r_wall_s": 33.77, "compile_s": 1.97, "r_error": "", "src_len": 1575, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6250, "tout": 1141, "ts": 1791531208.102636, "chk": "ok", "code_len": 1575}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7503, "tout": 804, "ts": 1791531408.1997702, "chk": null, "code_len": 1575}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6250, "started": 1791531198.5748494}
{"ep": "h1-01073", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1075, "speedup": 1.1075, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 103.1, "calls": 2, "tokens_in": 4868, "tokens_out": 4178, "ctx_chars": 0, "t_end": 1791531444.3531826, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1075, "lo95": 1.1066, "mean": 1.1063, "ev_only": 1.1086, "ref_ms": 3.71477, "cand_ms": 3.35433, "n_trials": 192, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9996, "r_wall_s": 58.31, "compile_s": 2.14, "r_error": "", "src_len": 2122, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 3009, "ts": 1791531369.3765008, "chk": "ok", "code_len": 2122}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3301, "tout": 1169, "ts": 1791531386.0027316, "chk": null, "code_len": 2122}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791531341.2422721}
{"ep": "h1-00995", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.6669, "speedup": 2.6669, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 406.2, "calls": 2, "tokens_in": 6270, "tokens_out": 6489, "ctx_chars": 0, "t_end": 1791531448.3697188, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.6669, "lo95": 2.6652, "mean": 2.7515, "ev_only": 2.666, "ref_ms": 35.39282, "cand_ms": 13.27119, "n_trials": 38, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 135.66, "compile_s": 3.42, "r_error": "", "src_len": 3478, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 4666, "ts": 1791531083.0086775, "chk": "ok", "code_len": 3478}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4308, "tout": 1823, "ts": 1791531311.3855968, "chk": null, "code_len": 3478}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791531042.1991906}
{"ep": "h1-01071", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0591, "speedup": 1.0591, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 131.6, "calls": 2, "tokens_in": 15851, "tokens_out": 5071, "ctx_chars": 11755, "t_end": 1791531454.7485433, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0591, "lo95": 1.0581, "mean": 1.077, "ev_only": 1.058, "ref_ms": 72.85788, "cand_ms": 68.79321, "n_trials": 19, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0169, "r_wall_s": 78.24, "compile_s": 2.74, "r_error": "", "src_len": 2503, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6940, "tout": 3776, "ts": 1791531359.6523526, "chk": "ok", "code_len": 2585}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8911, "tout": 1295, "ts": 1791531376.4036372, "chk": null, "code_len": 2503}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6940, "started": 1791531323.145939}
{"ep": "h1-01033", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1724, "speedup": 1.1724, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 281.4, "calls": 2, "tokens_in": 8766, "tokens_out": 10585, "ctx_chars": 0, "t_end": 1791531456.2683957, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1724, "lo95": 1.1716, "mean": 1.1928, "ev_only": 1.1734, "ref_ms": 8.39502, "cand_ms": 7.16059, "n_trials": 159, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0832, "r_wall_s": 180.82, "compile_s": 12.99, "r_error": "", "src_len": 8413, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2192, "tout": 6570, "ts": 1791531230.3256586, "chk": "ok", "code_len": 8413}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6574, "tout": 4015, "ts": 1791531275.402741, "chk": null, "code_len": 8413}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2192, "started": 1791531174.8751462}
{"ep": "h1-01025", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.7452, "speedup": 1.7452, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 301.2, "calls": 2, "tokens_in": 6985, "tokens_out": 8868, "ctx_chars": 0, "t_end": 1791531457.3487852, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.7452, "lo95": 1.7443, "mean": 1.7463, "ev_only": 1.7437, "ref_ms": 8.61987, "cand_ms": 4.93909, "n_trials": 190, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.3325, "r_wall_s": 102.26, "compile_s": 14.32, "r_error": "", "src_len": 4768, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2023, "tout": 6592, "ts": 1791531216.0785952, "chk": "ok", "code_len": 4768}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4962, "tout": 2276, "ts": 1791531354.114521, "chk": null, "code_len": 4768}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2023, "started": 1791531156.1587093}
{"ep": "h1-01019", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.2054, "speedup": 2.2054, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 362.8, "calls": 2, "tokens_in": 8190, "tokens_out": 16633, "ctx_chars": 0, "t_end": 1791531461.4330988, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.2054, "lo95": 2.1937, "mean": 2.2648, "ev_only": 2.2231, "ref_ms": 5.59915, "cand_ms": 2.53881, "n_trials": 168, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9973, "r_wall_s": 176.31, "compile_s": 14.62, "r_error": "", "src_len": 9239, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 12265, "ts": 1791531228.0442362, "chk": "ok", "code_len": 9289}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6580, "tout": 4368, "ts": 1791531284.3220913, "chk": null, "code_len": 9239}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1610, "started": 1791531119.00275}
{"ep": "h1-01044", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2939, "speedup": 1.2939, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 253.4, "calls": 2, "tokens_in": 9782, "tokens_out": 8705, "ctx_chars": 2932, "t_end": 1791531468.7312891, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2939, "lo95": 1.2924, "mean": 1.3046, "ev_only": 1.2951, "ref_ms": 8.36811, "cand_ms": 6.46757, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0753, "r_wall_s": 38.0, "compile_s": 1.91, "r_error": "", "src_len": 5546, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3305, "tout": 6013, "ts": 1791531267.3804243, "chk": "ok", "code_len": 5546}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6477, "tout": 2692, "ts": 1791531294.582621, "chk": null, "code_len": 5546}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3305, "started": 1791531215.3084362}
{"ep": "h1-01055", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8771, "speedup": 1.8771, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 206.2, "calls": 2, "tokens_in": 15857, "tokens_out": 6493, "ctx_chars": 11175, "t_end": 1791531471.3955657, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.8771, "lo95": 1.8646, "mean": 1.8672, "ev_only": 1.8774, "ref_ms": 8.68101, "cand_ms": 4.62459, "n_trials": 166, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2633, "r_wall_s": 111.95, "compile_s": 2.12, "r_error": "", "src_len": 2990, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6872, "tout": 4919, "ts": 1791531311.316157, "chk": "ok", "code_len": 2990}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8985, "tout": 1574, "ts": 1791531358.5534446, "chk": null, "code_len": 2990}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6872, "started": 1791531265.19493}
{"ep": "h1-00944", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.4975, "speedup": 7.4975, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 596.4, "calls": 3, "tokens_in": 30769, "tokens_out": 22071, "ctx_chars": 8224, "t_end": 1791531471.4190512, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 7.4975, "lo95": 4.9517, "mean": 6.8586, "ev_only": 7.509, "ref_ms": 45.98515, "cand_ms": 6.13337, "n_trials": 33, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 44.73, "compile_s": 11.27, "r_error": "", "src_len": 8256, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 13064, "ts": 1791530990.0470452, "chk": "no_custom_kernel", "code_len": 8219}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10409, "tout": 4824, "ts": 1791531077.6449373, "chk": "ok", "code_len": 8256}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14870, "tout": 4183, "ts": 1791531293.3474, "chk": null, "code_len": 8256}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791530875.0619433}
{"ep": "h1-00996", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0116, "speedup": 1.0116, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 442.6, "calls": 2, "tokens_in": 13946, "tokens_out": 5609, "ctx_chars": 9192, "t_end": 1791531484.8623219, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0116, "lo95": 1.0084, "mean": 1.0034, "ev_only": 1.0145, "ref_ms": 8.13535, "cand_ms": 8.04209, "n_trials": 148, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.009, "r_wall_s": 159.86, "compile_s": 3.61, "r_error": "", "src_len": 3873, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5721, "tout": 3607, "ts": 1791531072.8394847, "chk": "ok", "code_len": 3873}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8225, "tout": 2002, "ts": 1791531324.9050922, "chk": null, "code_len": 3873}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5721, "started": 1791531042.308033}
{"ep": "h1-01027", "task": "L3_043", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.1105, "speedup": 0.1105, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 335.6, "calls": 4, "tokens_in": 26327, "tokens_out": 6974, "ctx_chars": 2425, "t_end": 1791531494.0874581, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.1105, "lo95": 0.1103, "mean": 0.1106, "ev_only": 0.1104, "ref_ms": 30.85359, "cand_ms": 279.31655, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9369, "r_wall_s": 157.14, "compile_s": 6.92, "r_error": "", "src_len": 4286, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3322, "tout": 2391, "ts": 1791531179.8391871, "chk": "runtime_error", "code_len": 4377}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6044, "tout": 2299, "ts": 1791531206.6993752, "chk": "ok", "code_len": 4286}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8455, "tout": 27, "ts": 1791531318.0436287, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8506, "tout": 2257, "ts": 1791531336.4605632, "chk": null, "code_len": 4286}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 3322, "started": 1791531158.5259593}
{"ep": "h1-01092", "task": "L2_069", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 68.4, "calls": 1, "tokens_in": 1629, "tokens_out": 767, "ctx_chars": 0, "t_end": 1791531497.23097, "error": "RuntimeError: Error building extension 'fuse_hs_relu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_hs_relu -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 60.16, "compile_s": 60.14, "r_error": "RuntimeError: Error building extension 'fuse_hs_relu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_hs_relu -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 1380, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1629, "tout": 767, "ts": 1791531437.0473855, "chk": null, "code_len": 1380}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1629, "started": 1791531428.7968235}
{"ep": "h1-01062", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2357, "speedup": 1.2357, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 206.7, "calls": 2, "tokens_in": 12707, "tokens_out": 9313, "ctx_chars": 6513, "t_end": 1791531502.1935666, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2357, "lo95": 1.2171, "mean": 1.0726, "ev_only": 1.2266, "ref_ms": 5.426, "cand_ms": 4.39104, "n_trials": 198, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0903, "r_wall_s": 115.37, "compile_s": 2.93, "r_error": "", "src_len": 5636, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4677, "tout": 6512, "ts": 1791531353.167427, "chk": "ok", "code_len": 5636}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8030, "tout": 2801, "ts": 1791531386.5833642, "chk": null, "code_len": 5636}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4677, "started": 1791531295.4944065}
{"ep": "h1-01035", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.9007, "speedup": 1.9007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 328.5, "calls": 2, "tokens_in": 6432, "tokens_out": 5749, "ctx_chars": 0, "t_end": 1791531509.7488735, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.9007, "lo95": 1.8992, "mean": 1.9024, "ev_only": 1.8974, "ref_ms": 8.62819, "cand_ms": 4.53952, "n_trials": 160, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.2755, "r_wall_s": 178.5, "compile_s": 19.26, "r_error": "", "src_len": 3809, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2023, "tout": 3869, "ts": 1791531216.0149865, "chk": "ok", "code_len": 3809}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4409, "tout": 1880, "ts": 1791531330.309244, "chk": null, "code_len": 3809}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2023, "started": 1791531181.1996949}
{"ep": "h1-01053", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9336, "speedup": 0.9336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 253.6, "calls": 2, "tokens_in": 13416, "tokens_out": 21955, "ctx_chars": 0, "t_end": 1791531511.1929607, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9336, "lo95": 0.9316, "mean": 0.9352, "ev_only": 0.9337, "ref_ms": 20.12781, "cand_ms": 21.55867, "n_trials": 70, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2666, "r_wall_s": 17.83, "compile_s": 2.12, "r_error": "", "src_len": 10814, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 16363, "ts": 1791531401.1331584, "chk": "ok", "code_len": 10814}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9823, "tout": 5592, "ts": 1791531493.3195992, "chk": null, "code_len": 10814}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3593, "started": 1791531257.5533779}
{"ep": "h1-01063", "task": "L3_029", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7011, "speedup": 0.7011, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.3, "calls": 1, "tokens_in": 7616, "tokens_out": 5032, "ctx_chars": 0, "t_end": 1791531515.4631987, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7011, "lo95": 0.6987, "mean": 0.708, "ev_only": 0.7009, "ref_ms": 8.42575, "cand_ms": 12.01865, "n_trials": 78, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0455, "r_wall_s": 179.03, "compile_s": 6.12, "r_error": "", "src_len": 11759, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7616, "tout": 5032, "ts": 1791531336.4057362, "chk": null, "code_len": 11759}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7616, "started": 1791531296.1170642}
{"ep": "h1-01010", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.8637, "speedup": 4.8637, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 433.2, "calls": 3, "tokens_in": 12518, "tokens_out": 11443, "ctx_chars": 0, "t_end": 1791531516.972754, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.8637, "lo95": 4.7983, "mean": 4.7965, "ev_only": 4.9029, "ref_ms": 6.55964, "cand_ms": 1.3487, "n_trials": 167, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 127.97, "compile_s": 12.76, "r_error": "", "src_len": 4405, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1559, "tout": 6952, "ts": 1791531147.7137442, "chk": "no_custom_kernel", "code_len": 4430}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4318, "tout": 2372, "ts": 1791531189.809634, "chk": "ok", "code_len": 4405}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6641, "tout": 2119, "ts": 1791531388.1938362, "chk": null, "code_len": 4405}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1559, "started": 1791531083.7493286}
{"ep": "h1-01100", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0157, "speedup": 1.0157, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 61.0, "calls": 2, "tokens_in": 11944, "tokens_out": 1123, "ctx_chars": 9220, "t_end": 1791531517.253783, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0157, "lo95": 1.0152, "mean": 1.016, "ev_only": 1.0153, "ref_ms": 8.08402, "cand_ms": 7.9591, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0038, "r_wall_s": 23.63, "compile_s": 2.12, "r_error": "", "src_len": 891, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5602, "tout": 628, "ts": 1791531462.146026, "chk": "ok", "code_len": 891}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6342, "tout": 495, "ts": 1791531493.5292356, "chk": null, "code_len": 891}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5602, "started": 1791531456.268655}
{"ep": "h1-01079", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1948, "speedup": 1.1948, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.4, "calls": 2, "tokens_in": 9829, "tokens_out": 7907, "ctx_chars": 2932, "t_end": 1791531535.6174748, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1948, "lo95": 1.1926, "mean": 1.1924, "ev_only": 1.195, "ref_ms": 8.39061, "cand_ms": 7.02241, "n_trials": 164, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0839, "r_wall_s": 28.93, "compile_s": 1.97, "r_error": "", "src_len": 5234, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3305, "tout": 5242, "ts": 1791531423.903896, "chk": "ok", "code_len": 5234}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6524, "tout": 2665, "ts": 1791531506.5815709, "chk": null, "code_len": 5234}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3305, "started": 1791531380.2162137}
{"ep": "h1-01064", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0863, "speedup": 1.0863, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.4, "calls": 2, "tokens_in": 5184, "tokens_out": 7107, "ctx_chars": 0, "t_end": 1791531538.8645532, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0863, "lo95": 1.0857, "mean": 1.086, "ev_only": 1.0861, "ref_ms": 72.86002, "cand_ms": 67.07132, "n_trials": 22, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0112, "r_wall_s": 27.89, "compile_s": 2.23, "r_error": "", "src_len": 2372, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1699, "tout": 5891, "ts": 1791531356.3982928, "chk": "ok", "code_len": 2451}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3485, "tout": 1216, "ts": 1791531510.8691921, "chk": null, "code_len": 2372}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1699, "started": 1791531297.5120687}
{"ep": "h1-01105", "task": "L1_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.6494, "speedup": 4.6494, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 69.6, "calls": 2, "tokens_in": 13425, "tokens_out": 3558, "ctx_chars": 9438, "t_end": 1791531541.0214016, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.6494, "lo95": 4.6415, "mean": 4.6484, "ev_only": 4.6876, "ref_ms": 7.39398, "cand_ms": 1.59031, "n_trials": 164, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 23.9, "compile_s": 2.0, "r_error": "", "src_len": 2227, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5861, "tout": 2225, "ts": 1791531493.54779, "chk": "ok", "code_len": 2319}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7564, "tout": 1333, "ts": 1791531516.9647057, "chk": null, "code_len": 2227}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5861, "started": 1791531471.4194713}
{"ep": "h1-01036", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4013, "speedup": 1.4013, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 356.2, "calls": 2, "tokens_in": 5378, "tokens_out": 5215, "ctx_chars": 0, "t_end": 1791531541.3841045, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4013, "lo95": 1.4007, "mean": 1.4012, "ev_only": 1.4036, "ref_ms": 7.49435, "cand_ms": 5.3481, "n_trials": 215, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1238, "r_wall_s": 123.45, "compile_s": 3.5, "r_error": "", "src_len": 2960, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1685, "tout": 3609, "ts": 1791531218.0860615, "chk": "ok", "code_len": 2960}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3693, "tout": 1606, "ts": 1791531417.533052, "chk": null, "code_len": 2960}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1685, "started": 1791531185.1819801}
{"ep": "h1-01080", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0321, "speedup": 1.0321, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 148.5, "calls": 2, "tokens_in": 12283, "tokens_out": 1800, "ctx_chars": 9028, "t_end": 1791531541.6978421, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0321, "lo95": 1.03, "mean": 1.0355, "ev_only": 1.0316, "ref_ms": 8.35405, "cand_ms": 8.0943, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 84.4, "compile_s": 1.98, "r_error": "", "src_len": 1167, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 1095, "ts": 1791531402.7883325, "chk": "ok", "code_len": 1167}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6745, "tout": 705, "ts": 1791531457.2212029, "chk": null, "code_len": 1167}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5538, "started": 1791531393.1714737}
{"ep": "h1-01099", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3132, "speedup": 1.3132, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 95.5, "calls": 2, "tokens_in": 15494, "tokens_out": 4436, "ctx_chars": 11357, "t_end": 1791531550.2750924, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3132, "lo95": 1.3128, "mean": 1.3132, "ev_only": 1.3153, "ref_ms": 7.49836, "cand_ms": 5.70985, "n_trials": 163, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1153, "r_wall_s": 43.6, "compile_s": 2.26, "r_error": "", "src_len": 2588, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6781, "tout": 3075, "ts": 1791531485.3394072, "chk": "ok", "code_len": 2588}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8713, "tout": 1361, "ts": 1791531506.0544791, "chk": null, "code_len": 2588}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6781, "started": 1791531454.7488241}
{"ep": "h1-00989", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1102, "speedup": 1.1102, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 522.6, "calls": 2, "tokens_in": 6642, "tokens_out": 9166, "ctx_chars": 0, "t_end": 1791531550.922969, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1102, "lo95": 1.1097, "mean": 1.1184, "ev_only": 1.1109, "ref_ms": 20.43513, "cand_ms": 18.40722, "n_trials": 57, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 214.52, "compile_s": 3.42, "r_error": "", "src_len": 4090, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 7123, "ts": 1791531094.1331937, "chk": "ok", "code_len": 4090}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4639, "tout": 2043, "ts": 1791531336.3661022, "chk": null, "code_len": 4090}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791531028.2754753}
{"ep": "h1-01069", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0022, "speedup": 1.0022, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 232.2, "calls": 2, "tokens_in": 13697, "tokens_out": 1536, "ctx_chars": 10909, "t_end": 1791531551.6140215, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0022, "lo95": 1.0016, "mean": 1.0019, "ev_only": 1.0025, "ref_ms": 16.15772, "cand_ms": 16.12193, "n_trials": 61, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0007, "r_wall_s": 33.46, "compile_s": 1.86, "r_error": "", "src_len": 938, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6428, "tout": 984, "ts": 1791531328.315478, "chk": "ok", "code_len": 938}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7269, "tout": 552, "ts": 1791531518.105449, "chk": null, "code_len": 938}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6428, "started": 1791531319.458951}
{"ep": "h1-00979", "task": "L2_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.2236, "speedup": 3.2236, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 572.0, "calls": 3, "tokens_in": 14477, "tokens_out": 12473, "ctx_chars": 0, "t_end": 1791531552.3523343, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.2236, "lo95": 3.2186, "mean": 3.2266, "ev_only": 3.236, "ref_ms": 12.67255, "cand_ms": 3.93112, "n_trials": 73, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.996, "r_wall_s": 220.43, "compile_s": 19.23, "r_error": "", "src_len": 5057, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1863, "tout": 7141, "ts": 1791531044.8034, "chk": "no_custom_kernel", "code_len": 5102}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4966, "tout": 2814, "ts": 1791531088.5931618, "chk": "ok", "code_len": 5057}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7648, "tout": 2518, "ts": 1791531331.8995926, "chk": null, "code_len": 5057}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1863, "started": 1791530980.3368216}
{"ep": "h1-01102", "task": "L2_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0332, "speedup": 1.0332, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 94.4, "calls": 1, "tokens_in": 5550, "tokens_out": 477, "ctx_chars": 8989, "t_end": 1791531555.8039062, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0332, "lo95": 1.0328, "mean": 1.0332, "ev_only": 1.0337, "ref_ms": 30.41738, "cand_ms": 29.441, "n_trials": 55, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.013, "r_wall_s": 89.3, "compile_s": 3.04, "r_error": "", "src_len": 911, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5550, "tout": 477, "ts": 1791531466.0092566, "chk": null, "code_len": 911}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5550, "started": 1791531461.4333496}
{"ep": "h1-01076", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.008, "speedup": 1.008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 202.2, "calls": 2, "tokens_in": 4219, "tokens_out": 2068, "ctx_chars": 0, "t_end": 1791531556.3401804, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.008, "lo95": 1.0077, "mean": 1.0101, "ev_only": 1.0102, "ref_ms": 8.00433, "cand_ms": 7.94069, "n_trials": 155, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 35.96, "compile_s": 1.98, "r_error": "", "src_len": 1105, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1588, "tout": 1449, "ts": 1791531368.4414942, "chk": "ok", "code_len": 1105}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2631, "tout": 619, "ts": 1791531520.3119552, "chk": null, "code_len": 1105}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1588, "started": 1791531354.1494145}
{"ep": "h1-01042", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.9121, "speedup": 3.9121, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 351.0, "calls": 2, "tokens_in": 17599, "tokens_out": 15121, "ctx_chars": 11535, "t_end": 1791531557.3556848, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 3.9121, "lo95": 3.9056, "mean": 3.9064, "ev_only": 3.9236, "ref_ms": 20.09389, "cand_ms": 5.13635, "n_trials": 74, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0039, "r_wall_s": 33.93, "compile_s": 11.47, "r_error": "", "src_len": 6925, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6867, "tout": 11796, "ts": 1791531314.144099, "chk": "ok", "code_len": 6925}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10732, "tout": 3325, "ts": 1791531523.3785374, "chk": null, "code_len": 6925}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6867, "started": 1791531206.3126144}
{"ep": "h1-01108", "task": "L2_012", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0056, "speedup": 1.0056, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 61.5, "calls": 2, "tokens_in": 12671, "tokens_out": 1330, "ctx_chars": 9890, "t_end": 1791531558.762723, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0056, "lo95": 1.0049, "mean": 1.0054, "ev_only": 1.0058, "ref_ms": 8.04883, "cand_ms": 8.00379, "n_trials": 86, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0041, "r_wall_s": 31.98, "compile_s": 1.95, "r_error": "", "src_len": 1036, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5890, "tout": 782, "ts": 1791531504.676437, "chk": "ok", "code_len": 1036}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6781, "tout": 548, "ts": 1791531526.7054617, "chk": null, "code_len": 1036}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5890, "started": 1791531497.2312233}
{"ep": "h1-01083", "task": "L2_052", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3155, "speedup": 1.3155, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.3, "calls": 3, "tokens_in": 23073, "tokens_out": 3357, "ctx_chars": 11132, "t_end": 1791531559.9345355, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3155, "lo95": 1.3133, "mean": 1.3157, "ev_only": 1.3141, "ref_ms": 11.03341, "cand_ms": 8.3875, "n_trials": 129, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1979, "r_wall_s": 93.24, "compile_s": 2.5, "r_error": "", "src_len": 3276, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6454, "tout": 1725, "ts": 1791531412.236515, "chk": "ok", "code_len": 3276}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8291, "tout": 13, "ts": 1791531452.6334927, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8328, "tout": 1619, "ts": 1791531465.9110198, "chk": null, "code_len": 3276}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6454, "started": 1791531397.6258206}
{"ep": "h1-01038", "task": "L2_082", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9496, "speedup": 1.9496, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 381.2, "calls": 2, "tokens_in": 14685, "tokens_out": 4090, "ctx_chars": 10743, "t_end": 1791531567.4974136, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.9496, "lo95": 1.9491, "mean": 1.949, "ev_only": 1.9503, "ref_ms": 19.41324, "cand_ms": 9.95749, "n_trials": 64, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1013, "r_wall_s": 252.7, "compile_s": 3.14, "r_error": "", "src_len": 2330, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6466, "tout": 2895, "ts": 1791531212.8626485, "chk": "ok", "code_len": 2330}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8219, "tout": 1195, "ts": 1791531314.460804, "chk": null, "code_len": 2330}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6466, "started": 1791531186.3445804}
{"ep": "h1-01054", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0061, "speedup": 1.0061, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 314.8, "calls": 4, "tokens_in": 29472, "tokens_out": 15668, "ctx_chars": 0, "t_end": 1791531575.8199666, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0061, "lo95": 1.0048, "mean": 1.0057, "ev_only": 1.0055, "ref_ms": 23.41698, "cand_ms": 23.27611, "n_trials": 54, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0083, "r_wall_s": 94.63, "compile_s": 7.06, "r_error": "", "src_len": 4537, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2736, "tout": 5445, "ts": 1791531309.6290665, "chk": "incorrect", "code_len": 5045}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5894, "tout": 4039, "ts": 1791531357.8573997, "chk": "incorrect", "code_len": 5200}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9035, "tout": 3716, "ts": 1791531402.794949, "chk": "ok", "code_len": 4537}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11807, "tout": 2468, "ts": 1791531481.1600602, "chk": null, "code_len": 4537}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2736, "started": 1791531261.0642989}
{"ep": "h1-01060", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4383, "speedup": 1.4383, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 290.9, "calls": 2, "tokens_in": 5115, "tokens_out": 4432, "ctx_chars": 0, "t_end": 1791531576.3256288, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4383, "lo95": 1.4372, "mean": 1.4496, "ev_only": 1.4379, "ref_ms": 8.02508, "cand_ms": 5.57961, "n_trials": 180, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 28.69, "compile_s": 2.01, "r_error": "", "src_len": 2724, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1520, "tout": 2903, "ts": 1791531330.8870914, "chk": "ok", "code_len": 2724}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3595, "tout": 1529, "ts": 1791531547.536183, "chk": null, "code_len": 2724}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1520, "started": 1791531305.8634434}
{"ep": "h1-00851", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9292, "speedup": 0.9292, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 1071.3, "calls": 5, "tokens_in": 91547, "tokens_out": 53539, "ctx_chars": 6513, "t_end": 1791531579.1384506, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9292, "lo95": 0.8506, "mean": 0.8852, "ev_only": 0.921, "ref_ms": 4.17345, "cand_ms": 4.49162, "n_trials": 184, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0223, "r_wall_s": 112.25, "compile_s": 58.31, "r_error": "", "src_len": 4122, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5548, "tout": 18641, "ts": 1791530673.3494463, "chk": "runtime_error", "code_len": 13589}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 12949, "tout": 8717, "ts": 1791530850.130016, "chk": "incorrect", "code_len": 14708}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 20685, "tout": 19259, "ts": 1791531096.0907063, "chk": "incorrect", "code_len": 7711}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 24906, "tout": 4690, "ts": 1791531381.9761329, "chk": "ok", "code_len": 4122}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 27459, "tout": 2232, "ts": 1791531466.8569767, "chk": null, "code_len": 4122}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "incorrect", "incorrect", "ok", null], "first_tin": 5548, "started": 1791530507.8214684}
{"ep": "h1-01077", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1931, "speedup": 1.1931, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 221.0, "calls": 2, "tokens_in": 8496, "tokens_out": 10075, "ctx_chars": 0, "t_end": 1791531583.5477424, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1931, "lo95": 1.1851, "mean": 1.1916, "ev_only": 1.1947, "ref_ms": 8.34798, "cand_ms": 6.9968, "n_trials": 95, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0758, "r_wall_s": 74.23, "compile_s": 12.82, "r_error": "", "src_len": 7513, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2192, "tout": 6381, "ts": 1791531415.9812663, "chk": "ok", "code_len": 7513}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6304, "tout": 3694, "ts": 1791531509.2073252, "chk": null, "code_len": 7513}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2192, "started": 1791531362.5166547}
{"ep": "h1-01078", "task": "L3_043", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1907, "speedup": 1.1907, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.0, "calls": 2, "tokens_in": 9200, "tokens_out": 6346, "ctx_chars": 2425, "t_end": 1791531585.860056, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1907, "lo95": 1.1904, "mean": 1.1908, "ev_only": 1.1904, "ref_ms": 30.79005, "cand_ms": 25.85919, "n_trials": 47, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3652, "r_wall_s": 111.64, "compile_s": 12.38, "r_error": "", "src_len": 3823, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3324, "tout": 4336, "ts": 1791531403.7117243, "chk": "ok", "code_len": 3823}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5876, "tout": 2010, "ts": 1791531473.8384955, "chk": null, "code_len": 3823}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3324, "started": 1791531366.8981464}
{"ep": "h1-01098", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.7631, "speedup": 9.7631, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 140.9, "calls": 2, "tokens_in": 7104, "tokens_out": 8229, "ctx_chars": 0, "t_end": 1791531589.2501988, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 9.7631, "lo95": 9.7528, "mean": 9.7732, "ev_only": 9.8856, "ref_ms": 10.12292, "cand_ms": 1.03685, "n_trials": 131, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 59.68, "compile_s": 12.82, "r_error": "", "src_len": 6447, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1642, "tout": 4991, "ts": 1791531488.387398, "chk": "ok", "code_len": 6447}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5462, "tout": 3238, "ts": 1791531529.1596065, "chk": null, "code_len": 6447}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1642, "started": 1791531448.3699908}
{"ep": "h1-01085", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.9313, "speedup": 2.9313, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.7, "calls": 2, "tokens_in": 8648, "tokens_out": 10976, "ctx_chars": 0, "t_end": 1791531599.4092457, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.9313, "lo95": 2.9286, "mean": 2.9275, "ev_only": 2.9553, "ref_ms": 3.64787, "cand_ms": 1.24443, "n_trials": 215, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5, "r_wall_s": 62.72, "compile_s": 2.17, "r_error": "", "src_len": 5269, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 8141, "ts": 1791531505.2892723, "chk": "ok", "code_len": 5269}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5955, "tout": 2835, "ts": 1791531536.3948205, "chk": null, "code_len": 5269}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791531432.0775988}
{"ep": "h1-01089", "task": "L2_032", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1082, "speedup": 1.1082, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.9, "calls": 1, "tokens_in": 6637, "tokens_out": 654, "ctx_chars": 11296, "t_end": 1791531600.524607, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1082, "lo95": 1.1064, "mean": 1.1081, "ev_only": 1.109, "ref_ms": 31.45952, "cand_ms": 28.38835, "n_trials": 36, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0499, "r_wall_s": 173.61, "compile_s": 3.58, "r_error": "", "src_len": 1231, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6637, "tout": 654, "ts": 1791531426.8579862, "chk": null, "code_len": 1231}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6637, "started": 1791531420.6279347}
{"ep": "h1-01056", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 14.0672, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 343.4, "calls": 2, "tokens_in": 6525, "tokens_out": 7110, "ctx_chars": 0, "t_end": 1791531609.4794185, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 14.0672, "lo95": 14.0202, "mean": 13.9285, "ev_only": 14.1766, "ref_ms": 25.18155, "cand_ms": 1.79009, "n_trials": 57, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 186.79, "compile_s": 21.96, "r_error": "", "src_len": 5290, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1755, "tout": 4691, "ts": 1791531305.4164252, "chk": "ok", "code_len": 5290}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4770, "tout": 2419, "ts": 1791531422.5125194, "chk": null, "code_len": 5290}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1755, "started": 1791531266.0466835}
{"ep": "h1-01090", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0013, "speedup": 1.0013, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.3, "calls": 2, "tokens_in": 12754, "tokens_out": 1904, "ctx_chars": 9898, "t_end": 1791531612.61369, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0013, "lo95": 1.0008, "mean": 1.0237, "ev_only": 1.0004, "ref_ms": 16.02671, "cand_ms": 16.00669, "n_trials": 71, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0013, "r_wall_s": 141.98, "compile_s": 13.85, "r_error": "", "src_len": 1079, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5911, "tout": 1232, "ts": 1791531434.4556074, "chk": "ok", "code_len": 1079}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6843, "tout": 672, "ts": 1791531470.605677, "chk": null, "code_len": 1079}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5911, "started": 1791531423.3284152}
{"ep": "h1-00998", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.9361, "speedup": 1.9361, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 565.3, "calls": 2, "tokens_in": 8995, "tokens_out": 4643, "ctx_chars": 2425, "t_end": 1791531613.0127044, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.9361, "lo95": 1.9221, "mean": 1.9094, "ev_only": 1.9318, "ref_ms": 12.76746, "cand_ms": 6.5943, "n_trials": 111, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5228, "r_wall_s": 282.95, "compile_s": 3.3, "r_error": "", "src_len": 2919, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3400, "tout": 3064, "ts": 1791531074.8119402, "chk": "ok", "code_len": 2919}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5595, "tout": 1579, "ts": 1791531329.955246, "chk": null, "code_len": 2919}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3400, "started": 1791531047.686672}
{"ep": "h1-01084", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.0843, "speedup": 3.0843, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 208.9, "calls": 2, "tokens_in": 6527, "tokens_out": 6708, "ctx_chars": 0, "t_end": 1791531613.8816702, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.0843, "lo95": 3.0804, "mean": 3.0801, "ev_only": 3.0828, "ref_ms": 44.31785, "cand_ms": 14.36893, "n_trials": 31, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 88.12, "compile_s": 1.86, "r_error": "", "src_len": 3560, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2039, "tout": 4927, "ts": 1791531448.2333293, "chk": "ok", "code_len": 3560}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4488, "tout": 1781, "ts": 1791531524.8586175, "chk": null, "code_len": 3560}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2039, "started": 1791531404.9394681}
{"ep": "h1-01094", "task": "L3_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8509, "speedup": 1.8509, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 174.2, "calls": 2, "tokens_in": 10247, "tokens_out": 4869, "ctx_chars": 2425, "t_end": 1791531615.6056633, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.8509, "lo95": 1.8496, "mean": 1.8536, "ev_only": 1.8572, "ref_ms": 12.66832, "cand_ms": 6.84427, "n_trials": 45, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4921, "r_wall_s": 53.1, "compile_s": 3.03, "r_error": "", "src_len": 2864, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3398, "tout": 3342, "ts": 1791531469.5628133, "chk": "ok", "code_len": 2864}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6849, "tout": 1527, "ts": 1791531562.3873289, "chk": null, "code_len": 2864}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3398, "started": 1791531441.4447172}
{"ep": "h1-01122", "task": "L2_053", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 64.3, "calls": 1, "tokens_in": 1669, "tokens_out": 957, "ctx_chars": 0, "t_end": 1791531615.9503787, "error": "RuntimeError: Error building extension 'fused_act_053': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_053 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 54.89, "compile_s": 54.88, "r_error": "RuntimeError: Error building extension 'fused_act_053': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_053 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "src_len": 2003, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1669, "tout": 957, "ts": 1791531561.0150502, "chk": null, "code_len": 2003}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1669, "started": 1791531551.614637}
{"ep": "h1-01061", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4075, "speedup": 0.4075, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 323.9, "calls": 2, "tokens_in": 8212, "tokens_out": 12602, "ctx_chars": 0, "t_end": 1791531617.1320877, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.4075, "lo95": 0.4073, "mean": 0.4092, "ev_only": 0.4062, "ref_ms": 4.73572, "cand_ms": 11.62096, "n_trials": 133, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0093, "r_wall_s": 69.79, "compile_s": 13.08, "r_error": "", "src_len": 7882, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1917, "tout": 8790, "ts": 1791531369.5944915, "chk": "ok", "code_len": 7931}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6295, "tout": 3812, "ts": 1791531547.1880274, "chk": null, "code_len": 7882}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1917, "started": 1791531293.2496762}
{"ep": "h1-01103", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0011, "speedup": 1.0011, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 149.6, "calls": 2, "tokens_in": 3911, "tokens_out": 1848, "ctx_chars": 0, "t_end": 1791531618.36211, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0011, "lo95": 1.0003, "mean": 1.0028, "ev_only": 1.0033, "ref_ms": 8.03226, "cand_ms": 8.02371, "n_trials": 137, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 62.79, "compile_s": 1.91, "r_error": "", "src_len": 863, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1520, "tout": 1340, "ts": 1791531481.732865, "chk": "ok", "code_len": 863}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2391, "tout": 508, "ts": 1791531555.4801824, "chk": null, "code_len": 863}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1520, "started": 1791531468.731567}
{"ep": "h1-01009", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 8.4668, "speedup": 8.4668, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 539.2, "calls": 3, "tokens_in": 27613, "tokens_out": 21924, "ctx_chars": 8224, "t_end": 1791531621.9587011, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 8.4668, "lo95": 8.4134, "mean": 8.8748, "ev_only": 8.4765, "ref_ms": 32.58892, "cand_ms": 3.84901, "n_trials": 44, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 153.12, "compile_s": 22.59, "r_error": "", "src_len": 6546, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 14220, "ts": 1791531213.3006375, "chk": "no_custom_kernel", "code_len": 6549}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9301, "tout": 3989, "ts": 1791531403.06118, "chk": "ok", "code_len": 6546}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12822, "tout": 3715, "ts": 1791531468.798329, "chk": null, "code_len": 6546}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791531082.7863297}
{"ep": "h1-01059", "task": "L2_052", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3912, "speedup": 1.3912, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 352.8, "calls": 2, "tokens_in": 5318, "tokens_out": 4783, "ctx_chars": 0, "t_end": 1791531631.1695228, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3912, "lo95": 1.3892, "mean": 1.3907, "ev_only": 1.39, "ref_ms": 11.02773, "cand_ms": 7.92674, "n_trials": 151, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1396, "r_wall_s": 282.02, "compile_s": 2.17, "r_error": "", "src_len": 3206, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1619, "tout": 3188, "ts": 1791531306.6660776, "chk": "ok", "code_len": 3206}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3699, "tout": 1595, "ts": 1791531348.3666317, "chk": null, "code_len": 3206}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1619, "started": 1791531278.333534}
{"ep": "h1-01070", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0361, "speedup": 1.0361, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 311.9, "calls": 2, "tokens_in": 14268, "tokens_out": 2057, "ctx_chars": 10901, "t_end": 1791531633.6962242, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0361, "lo95": 1.0356, "mean": 1.0681, "ev_only": 1.0355, "ref_ms": 8.21191, "cand_ms": 7.92543, "n_trials": 138, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 209.43, "compile_s": 3.59, "r_error": "", "src_len": 985, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6549, "tout": 1465, "ts": 1791531335.2788944, "chk": "ok", "code_len": 985}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7719, "tout": 592, "ts": 1791531424.1901684, "chk": null, "code_len": 985}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6549, "started": 1791531321.7916996}
{"ep": "h1-01096", "task": "L2_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.034, "speedup": 1.034, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 193.1, "calls": 1, "tokens_in": 5550, "tokens_out": 483, "ctx_chars": 8989, "t_end": 1791531635.1906312, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.034, "lo95": 1.0333, "mean": 1.034, "ev_only": 1.0336, "ref_ms": 30.34183, "cand_ms": 29.34422, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0129, "r_wall_s": 187.17, "compile_s": 2.04, "r_error": "", "src_len": 911, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5550, "tout": 483, "ts": 1791531447.5874622, "chk": null, "code_len": 911}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5550, "started": 1791531442.133531}
{"ep": "h1-01072", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0158, "speedup": 1.0158, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 312.4, "calls": 2, "tokens_in": 11906, "tokens_out": 1103, "ctx_chars": 9220, "t_end": 1791531649.0619838, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0158, "lo95": 1.0154, "mean": 1.0618, "ev_only": 1.0165, "ref_ms": 8.06215, "cand_ms": 7.9365, "n_trials": 152, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 29.47, "compile_s": 1.92, "r_error": "", "src_len": 913, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5602, "tout": 590, "ts": 1791531342.4040313, "chk": "ok", "code_len": 913}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6304, "tout": 513, "ts": 1791531619.4967074, "chk": null, "code_len": 913}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5602, "started": 1791531336.6816745}
{"ep": "h1-01095", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 29.0014, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.5, "calls": 3, "tokens_in": 20858, "tokens_out": 10799, "ctx_chars": 6034, "t_end": 1791531679.6452487, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 29.0014, "lo95": 26.677, "mean": 31.1871, "ev_only": 29.6449, "ref_ms": 32.87509, "cand_ms": 1.13357, "n_trials": 48, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.865, "r_wall_s": 105.06, "compile_s": 13.84, "r_error": "", "src_len": 4068, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4548, "tout": 6594, "ts": 1791531500.8016217, "chk": "no_custom_kernel", "code_len": 4090}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7088, "tout": 2274, "ts": 1791531533.6316392, "chk": "ok", "code_len": 4068}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9222, "tout": 1931, "ts": 1791531574.535749, "chk": null, "code_len": 4068}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 4548, "started": 1791531442.1094}
{"ep": "h1-01107", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4759, "speedup": 1.4759, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 193.3, "calls": 2, "tokens_in": 15099, "tokens_out": 4188, "ctx_chars": 10850, "t_end": 1791531687.3826206, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4759, "lo95": 1.4692, "mean": 1.4731, "ev_only": 1.4793, "ref_ms": 7.41615, "cand_ms": 5.02489, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 116.03, "compile_s": 2.43, "r_error": "", "src_len": 2520, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6676, "tout": 2735, "ts": 1791531518.9560235, "chk": "ok", "code_len": 2520}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8423, "tout": 1453, "ts": 1791531571.0773654, "chk": null, "code_len": 2520}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6676, "started": 1791531494.0876951}
{"ep": "h1-01111", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.6901, "speedup": 0.6901, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 186.5, "calls": 2, "tokens_in": 8696, "tokens_out": 6663, "ctx_chars": 3355, "t_end": 1791531697.7113976, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6901, "lo95": 0.6895, "mean": 0.7302, "ev_only": 0.69, "ref_ms": 20.5654, "cand_ms": 29.80125, "n_trials": 48, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 75.44, "compile_s": 1.98, "r_error": "", "src_len": 2929, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3296, "tout": 5102, "ts": 1791531556.8758547, "chk": "ok", "code_len": 2929}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5400, "tout": 1561, "ts": 1791531622.2309577, "chk": null, "code_len": 2929}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3296, "started": 1791531511.1932344}
{"ep": "h1-01116", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 9.1624, "speedup": 9.1624, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 160.3, "calls": 2, "tokens_in": 8844, "tokens_out": 4105, "ctx_chars": 4348, "t_end": 1791531699.2107882, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 9.1624, "lo95": 9.1078, "mean": 8.9531, "ev_only": 9.3067, "ref_ms": 10.19223, "cand_ms": 1.1124, "n_trials": 149, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 106.28, "compile_s": 3.82, "r_error": "", "src_len": 2385, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3531, "tout": 2782, "ts": 1791531563.270483, "chk": "ok", "code_len": 2385}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5313, "tout": 1323, "ts": 1791531592.4424946, "chk": null, "code_len": 2385}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3531, "started": 1791531538.8648283}
{"ep": "h1-01075", "task": "L2_056", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.411, "speedup": 4.411, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 347.5, "calls": 3, "tokens_in": 10260, "tokens_out": 6716, "ctx_chars": 0, "t_end": 1791531701.0991058, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.411, "lo95": 4.4057, "mean": 4.5248, "ev_only": 4.4307, "ref_ms": 16.03894, "cand_ms": 3.63609, "n_trials": 95, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9993, "r_wall_s": 45.39, "compile_s": 2.0, "r_error": "", "src_len": 2264, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1574, "tout": 3570, "ts": 1791531386.7067354, "chk": "incorrect", "code_len": 2207}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3569, "tout": 1758, "ts": 1791531490.7458389, "chk": "ok", "code_len": 2264}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5117, "tout": 1388, "ts": 1791531655.6653254, "chk": null, "code_len": 2264}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1574, "started": 1791531353.5593436}
{"ep": "h1-01124", "task": "L2_063", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3256, "speedup": 1.3256, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 147.3, "calls": 2, "tokens_in": 4722, "tokens_out": 3971, "ctx_chars": 0, "t_end": 1791531703.1144915, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3256, "lo95": 1.3252, "mean": 1.3283, "ev_only": 1.3272, "ref_ms": 8.01549, "cand_ms": 6.04654, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 62.1, "compile_s": 1.91, "r_error": "", "src_len": 2434, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1520, "tout": 2572, "ts": 1791531578.6914327, "chk": "ok", "code_len": 2434}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3202, "tout": 1399, "ts": 1791531640.9401388, "chk": null, "code_len": 2434}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1520, "started": 1791531555.804311}
{"ep": "h1-01109", "task": "L3_033", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5083, "speedup": 1.5083, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 201.9, "calls": 2, "tokens_in": 6419, "tokens_out": 6600, "ctx_chars": 0, "t_end": 1791531704.1148138, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.5083, "lo95": 1.5064, "mean": 1.5076, "ev_only": 1.511, "ref_ms": 20.61277, "cand_ms": 13.66625, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 78.88, "compile_s": 2.0, "r_error": "", "src_len": 3256, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 4775, "ts": 1791531545.1317327, "chk": "ok", "code_len": 3256}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4416, "tout": 1825, "ts": 1791531625.2020133, "chk": null, "code_len": 3256}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791531502.1938522}
{"ep": "h1-01106", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.8249, "speedup": 2.8249, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 222.0, "calls": 2, "tokens_in": 16364, "tokens_out": 6718, "ctx_chars": 11582, "t_end": 1791531706.864435, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.8249, "lo95": 2.8224, "mean": 2.8224, "ev_only": 2.8275, "ref_ms": 35.53644, "cand_ms": 12.57972, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 124.85, "compile_s": 3.88, "r_error": "", "src_len": 3257, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7119, "tout": 4975, "ts": 1791531550.3649137, "chk": "ok", "code_len": 3257}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9245, "tout": 1743, "ts": 1791531581.085843, "chk": null, "code_len": 3257}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7119, "started": 1791531505.2127216}
{"ep": "h1-01067", "task": "L2_079", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.6801, "speedup": 2.6801, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 405.1, "calls": 3, "tokens_in": 15960, "tokens_out": 12169, "ctx_chars": 0, "t_end": 1791531710.7873044, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.6801, "lo95": 2.6703, "mean": 2.6278, "ev_only": 2.6838, "ref_ms": 2.15747, "cand_ms": 0.80499, "n_trials": 189, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9973, "r_wall_s": 147.66, "compile_s": 17.1, "r_error": "", "src_len": 6468, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1813, "tout": 5740, "ts": 1791531353.1671283, "chk": "no_custom_kernel", "code_len": 6513}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5407, "tout": 3321, "ts": 1791531464.573596, "chk": "ok", "code_len": 6468}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8740, "tout": 3108, "ts": 1791531563.0757298, "chk": null, "code_len": 6468}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1813, "started": 1791531305.7214718}
{"ep": "h1-01114", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0129, "speedup": 1.0129, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 199.4, "calls": 2, "tokens_in": 14008, "tokens_out": 5402, "ctx_chars": 9192, "t_end": 1791531716.6052635, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0129, "lo95": 1.0125, "mean": 1.014, "ev_only": 1.0122, "ref_ms": 8.10015, "cand_ms": 7.99681, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.013, "r_wall_s": 137.9, "compile_s": 3.52, "r_error": "", "src_len": 3973, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5721, "tout": 3364, "ts": 1791531544.2898335, "chk": "ok", "code_len": 3973}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8287, "tout": 2038, "ts": 1791531578.6079352, "chk": null, "code_len": 3973}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5721, "started": 1791531517.2540185}
{"ep": "h1-01112", "task": "L3_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.0373, "speedup": 2.0373, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 205.5, "calls": 2, "tokens_in": 7009, "tokens_out": 4059, "ctx_chars": 0, "t_end": 1791531720.9678667, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.0373, "lo95": 2.0346, "mean": 2.0347, "ev_only": 2.0403, "ref_ms": 12.6906, "cand_ms": 6.22922, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4959, "r_wall_s": 155.92, "compile_s": 3.68, "r_error": "", "src_len": 2744, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2484, "tout": 2602, "ts": 1791531537.0954132, "chk": "ok", "code_len": 2744}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4525, "tout": 1457, "ts": 1791531564.9265852, "chk": null, "code_len": 2744}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2484, "started": 1791531515.4634478}
{"ep": "h1-01057", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.3517, "speedup": 7.3517, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 458.3, "calls": 3, "tokens_in": 30541, "tokens_out": 23222, "ctx_chars": 8224, "t_end": 1791531725.9739072, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.3517, "lo95": 7.3323, "mean": 7.3421, "ev_only": 7.3439, "ref_ms": 31.6813, "cand_ms": 4.30941, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 58.91, "compile_s": 11.23, "r_error": "", "src_len": 8424, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 14224, "ts": 1791531395.4209657, "chk": "no_custom_kernel", "code_len": 8428}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10319, "tout": 4823, "ts": 1791531481.7182975, "chk": "ok", "code_len": 8424}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14732, "tout": 4175, "ts": 1791531667.0329611, "chk": null, "code_len": 8424}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791531267.6242304}
{"ep": "h1-00959", "task": "L3_045", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 830.8, "calls": 5, "tokens_in": 40846, "tokens_out": 12848, "ctx_chars": 0, "t_end": 1791531745.1755188, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": 0.093, "r_wall_s": 157.11, "compile_s": 46.38, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 4358, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2734, "tout": 2873, "ts": 1791530947.3283744, "chk": "incorrect", "code_len": 5585}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5739, "tout": 2397, "ts": 1791531077.7996414, "chk": "incorrect", "code_len": 4277}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8269, "tout": 2240, "ts": 1791531327.9255893, "chk": "incorrect", "code_len": 4274}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 10642, "tout": 2664, "ts": 1791531511.464545, "chk": "incorrect", "code_len": 4346}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13462, "tout": 2674, "ts": 1791531588.0194588, "chk": null, "code_len": 4358}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 2734, "started": 1791530914.3725655}
{"ep": "h1-01133", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6136, "speedup": 1.6136, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 174.4, "calls": 2, "tokens_in": 16851, "tokens_out": 4871, "ctx_chars": 11886, "t_end": 1791531757.9088032, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.6136, "lo95": 1.6047, "mean": 1.6139, "ev_only": 1.6192, "ref_ms": 4.77086, "cand_ms": 2.95663, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2823, "r_wall_s": 53.13, "compile_s": 2.0, "r_error": "", "src_len": 3525, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7269, "tout": 3089, "ts": 1791531609.7238498, "chk": "ok", "code_len": 3525}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9582, "tout": 1782, "ts": 1791531704.6767826, "chk": null, "code_len": 3525}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7269, "started": 1791531583.548025}
{"ep": "h1-01148", "task": "L1_017", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7008, "speedup": 0.7008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 127.8, "calls": 3, "tokens_in": 20530, "tokens_out": 3551, "ctx_chars": 9033, "t_end": 1791531761.4752777, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7008, "lo95": 0.6999, "mean": 0.7013, "ev_only": 0.7018, "ref_ms": 7.80925, "cand_ms": 11.14264, "n_trials": 95, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 67.93, "compile_s": 1.92, "r_error": "", "src_len": 2904, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 1840, "ts": 1791531651.5181072, "chk": "ok", "code_len": 2997}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7435, "tout": 150, "ts": 1791531680.5875208, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7609, "tout": 1561, "ts": 1791531693.4685762, "chk": null, "code_len": 2904}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5486, "started": 1791531633.6964624}
{"ep": "h1-01151", "task": "L2_069", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 82.1, "calls": 1, "tokens_in": 1629, "tokens_out": 746, "ctx_chars": 0, "t_end": 1791531761.7576697, "error": "RuntimeError: Error building extension 'fused_act_hs_relu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_hs_relu -DTORCH_API_INCLUDE_EXTENSION_H", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 54.18, "compile_s": 54.17, "r_error": "RuntimeError: Error building extension 'fused_act_hs_relu': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_act_hs_relu -DTORCH_API_INCLUDE_EXTENSION_H", "src_len": 1489, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1629, "tout": 746, "ts": 1791531707.556728, "chk": null, "code_len": 1489}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1629, "started": 1791531700.0299742}
{"ep": "h1-01143", "task": "L2_055", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0025, "speedup": 1.0025, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 147.7, "calls": 3, "tokens_in": 20411, "tokens_out": 1651, "ctx_chars": 9898, "t_end": 1791531763.6969507, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0025, "lo95": 1.0022, "mean": 1.0223, "ev_only": 1.0029, "ref_ms": 16.14565, "cand_ms": 16.10512, "n_trials": 73, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0011, "r_wall_s": 112.65, "compile_s": 2.12, "r_error": "", "src_len": 1193, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6025, "tout": 1009, "ts": 1791531627.4070284, "chk": "ok", "code_len": 1501}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7144, "tout": 74, "ts": 1791531645.6154044, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7242, "tout": 568, "ts": 1791531651.0260649, "chk": null, "code_len": 1193}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6025, "started": 1791531615.9507778}
{"ep": "h1-01147", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9393, "speedup": 0.9393, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 138.1, "calls": 2, "tokens_in": 12232, "tokens_out": 3094, "ctx_chars": 9033, "t_end": 1791531769.2380688, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9393, "lo95": 0.9388, "mean": 0.9395, "ev_only": 0.9436, "ref_ms": 3.71376, "cand_ms": 3.95355, "n_trials": 179, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0035, "r_wall_s": 100.47, "compile_s": 2.0, "r_error": "", "src_len": 1130, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 2226, "ts": 1791531653.3537786, "chk": "ok", "code_len": 1130}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6742, "tout": 868, "ts": 1791531668.7393813, "chk": null, "code_len": 1130}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791531631.169777}
{"ep": "h1-01113", "task": "L2_084", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.5222, "speedup": 4.5222, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 252.3, "calls": 2, "tokens_in": 6643, "tokens_out": 9784, "ctx_chars": 0, "t_end": 1791531769.2626078, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.5222, "lo95": 4.5133, "mean": 4.5134, "ev_only": 4.5605, "ref_ms": 8.13478, "cand_ms": 1.79885, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9685, "r_wall_s": 118.91, "compile_s": 2.58, "r_error": "", "src_len": 4469, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1771, "tout": 7042, "ts": 1791531579.2610016, "chk": "ok", "code_len": 4469}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4872, "tout": 2742, "ts": 1791531649.8203635, "chk": null, "code_len": 4469}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1771, "started": 1791531516.9730082}
{"ep": "h1-01104", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9602, "speedup": 0.9602, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 302.1, "calls": 2, "tokens_in": 6178, "tokens_out": 9301, "ctx_chars": 0, "t_end": 1791531773.5279002, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9602, "lo95": 0.9596, "mean": 0.9887, "ev_only": 0.9613, "ref_ms": 3.721, "cand_ms": 3.87542, "n_trials": 196, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 193.46, "compile_s": 13.55, "r_error": "", "src_len": 4774, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1567, "tout": 6646, "ts": 1791531529.4910202, "chk": "ok", "code_len": 4774}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4611, "tout": 2655, "ts": 1791531580.0144875, "chk": null, "code_len": 4774}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1567, "started": 1791531471.3958483}
{"ep": "h1-01149", "task": "L3_043", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.1092, "speedup": 0.1092, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 148.7, "calls": 2, "tokens_in": 10471, "tokens_out": 7456, "ctx_chars": 0, "t_end": 1791531783.8900099, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.1092, "lo95": 0.1089, "mean": 0.1092, "ev_only": 0.109, "ref_ms": 30.88619, "cand_ms": 282.89437, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9376, "r_wall_s": 68.59, "compile_s": 2.03, "r_error": "", "src_len": 3657, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2406, "tout": 5547, "ts": 1791531681.967316, "chk": "ok", "code_len": 3657}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8065, "tout": 1909, "ts": 1791531714.7862148, "chk": null, "code_len": 3657}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2406, "started": 1791531635.1909003}
{"ep": "h1-01144", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.7272, "speedup": 1.7272, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 175.1, "calls": 2, "tokens_in": 16068, "tokens_out": 7264, "ctx_chars": 11175, "t_end": 1791531792.2207112, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.7272, "lo95": 1.7259, "mean": 1.7235, "ev_only": 1.7308, "ref_ms": 8.61643, "cand_ms": 4.98854, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.3253, "r_wall_s": 85.54, "compile_s": 2.09, "r_error": "", "src_len": 3061, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6872, "tout": 5669, "ts": 1791531673.2330096, "chk": "ok", "code_len": 3061}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9196, "tout": 1595, "ts": 1791531705.861447, "chk": null, "code_len": 3061}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6872, "started": 1791531617.132334}
{"ep": "h1-01121", "task": "L2_071", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2595, "speedup": 1.2595, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 249.1, "calls": 2, "tokens_in": 13752, "tokens_out": 2126, "ctx_chars": 11132, "t_end": 1791531800.051036, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2595, "lo95": 1.259, "mean": 1.2587, "ev_only": 1.2553, "ref_ms": 3.63547, "cand_ms": 2.88654, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2375, "r_wall_s": 84.31, "compile_s": 2.09, "r_error": "", "src_len": 999, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6426, "tout": 1575, "ts": 1791531567.1484797, "chk": "ok", "code_len": 999}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7326, "tout": 551, "ts": 1791531714.4575067, "chk": null, "code_len": 999}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6426, "started": 1791531550.9231987}
{"ep": "h1-01125", "task": "L2_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0605, "speedup": 1.0605, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 244.6, "calls": 2, "tokens_in": 4980, "tokens_out": 2633, "ctx_chars": 0, "t_end": 1791531800.9064806, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0605, "lo95": 1.0569, "mean": 1.0662, "ev_only": 1.0611, "ref_ms": 8.63275, "cand_ms": 8.14001, "n_trials": 128, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 53.35, "compile_s": 2.12, "r_error": "", "src_len": 1786, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1791, "tout": 1667, "ts": 1791531571.3072686, "chk": "ok", "code_len": 1786}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3189, "tout": 966, "ts": 1791531747.4226222, "chk": null, "code_len": 1786}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1791, "started": 1791531556.3404646}
{"ep": "h1-01146", "task": "L1_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 12.8069, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.6, "calls": 2, "tokens_in": 6604, "tokens_out": 7390, "ctx_chars": 0, "t_end": 1791531801.5878434, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 12.8069, "lo95": 12.7624, "mean": 12.7847, "ev_only": 13.4563, "ref_ms": 10.21834, "cand_ms": 0.79788, "n_trials": 152, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 100.7, "compile_s": 10.68, "r_error": "", "src_len": 5560, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1642, "tout": 4628, "ts": 1791531660.8536682, "chk": "ok", "code_len": 5560}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4962, "tout": 2762, "ts": 1791531700.3550382, "chk": null, "code_len": 5560}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1642, "started": 1791531621.9589634}
{"ep": "h1-01101", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8547, "speedup": 0.8547, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 346.2, "calls": 2, "tokens_in": 18013, "tokens_out": 19608, "ctx_chars": 6513, "t_end": 1791531803.557912, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8547, "lo95": 0.8507, "mean": 0.8776, "ev_only": 0.8546, "ref_ms": 15.98109, "cand_ms": 18.69873, "n_trials": 80, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1165, "r_wall_s": 138.55, "compile_s": 2.02, "r_error": "", "src_len": 12079, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 13729, "ts": 1791531572.2665708, "chk": "ok", "code_len": 12079}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12286, "tout": 5879, "ts": 1791531664.9798374, "chk": null, "code_len": 12079}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791531457.3491707}
{"ep": "h1-01132", "task": "L3_036", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.0768, "speedup": 0.0768, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 225.0, "calls": 5, "tokens_in": 29224, "tokens_out": 6447, "ctx_chars": 0, "t_end": 1791531804.106366, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.0768, "lo95": 0.0713, "mean": 0.0833, "ev_only": 0.0768, "ref_ms": 32.99165, "cand_ms": 429.50583, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1429, "r_wall_s": 63.75, "compile_s": 1.94, "r_error": "", "src_len": 2364, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1964, "tout": 2867, "ts": 1791531606.2280931, "chk": "runtime_error", "code_len": 2189}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5195, "tout": 1177, "ts": 1791531697.4465306, "chk": "tampered", "code_len": 2237}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6455, "tout": 1150, "ts": 1791531714.2091637, "chk": "ok", "code_len": 2227}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7717, "tout": 129, "ts": 1791531730.9292126, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7893, "tout": 1124, "ts": 1791531740.332455, "chk": null, "code_len": 2364}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "tampered", "ok", "no_code", null], "first_tin": 1964, "started": 1791531579.1400561}
{"ep": "h1-01140", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2423, "speedup": 1.2423, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 196.0, "calls": 2, "tokens_in": 9690, "tokens_out": 10021, "ctx_chars": 0, "t_end": 1791531809.035503, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2423, "lo95": 1.2413, "mean": 1.2397, "ev_only": 1.2424, "ref_ms": 75.27129, "cand_ms": 60.59221, "n_trials": 22, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1821, "r_wall_s": 92.38, "compile_s": 2.96, "r_error": "", "src_len": 5823, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 6837, "ts": 1791531670.4982777, "chk": "ok", "code_len": 5823}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6669, "tout": 3184, "ts": 1791531716.3165088, "chk": null, "code_len": 5823}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791531613.0131216}
{"ep": "h1-01065", "task": "L2_067", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5812, "speedup": 0.5812, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 519.9, "calls": 2, "tokens_in": 16281, "tokens_out": 10341, "ctx_chars": 11023, "t_end": 1791531820.6465695, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.5812, "lo95": 0.5789, "mean": 0.5796, "ev_only": 0.5809, "ref_ms": 13.00901, "cand_ms": 22.38282, "n_trials": 72, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9999, "r_wall_s": 360.43, "compile_s": 13.63, "r_error": "", "src_len": 5405, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6480, "tout": 7688, "ts": 1791531367.882458, "chk": "ok", "code_len": 5405}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9801, "tout": 2653, "ts": 1791531460.190237, "chk": null, "code_len": 5405}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6480, "started": 1791531300.7867532}
{"ep": "h1-01088", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.7464, "speedup": 3.7464, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 404.4, "calls": 2, "tokens_in": 13505, "tokens_out": 3337, "ctx_chars": 9311, "t_end": 1791531824.1685944, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.7464, "lo95": 3.7369, "mean": 3.7456, "ev_only": 3.7767, "ref_ms": 7.37844, "cand_ms": 1.96946, "n_trials": 236, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 353.57, "compile_s": 10.34, "r_error": "", "src_len": 2202, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5877, "tout": 2032, "ts": 1791531436.4393516, "chk": "ok", "code_len": 2202}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7628, "tout": 1305, "ts": 1791531470.4189522, "chk": null, "code_len": 2202}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5877, "started": 1791531419.7731302}
{"ep": "h1-01118", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0007, "speedup": 1.0007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 284.1, "calls": 2, "tokens_in": 15711, "tokens_out": 4595, "ctx_chars": 11755, "t_end": 1791531825.5333748, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0007, "lo95": 1.0005, "mean": 1.0008, "ev_only": 1.0008, "ref_ms": 72.7639, "cand_ms": 72.71569, "n_trials": 23, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0231, "r_wall_s": 90.68, "compile_s": 3.34, "r_error": "", "src_len": 2406, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6940, "tout": 3327, "ts": 1791531572.6422853, "chk": "ok", "code_len": 2450}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8771, "tout": 1268, "ts": 1791531734.7368171, "chk": null, "code_len": 2406}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6940, "started": 1791531541.384503}
{"ep": "h1-01110", "task": "L3_044", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3789, "speedup": 1.3789, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 317.6, "calls": 4, "tokens_in": 24580, "tokens_out": 4916, "ctx_chars": 0, "t_end": 1791531827.3138378, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.3789, "lo95": 1.3781, "mean": 1.3791, "ev_only": 1.3801, "ref_ms": 75.38402, "cand_ms": 54.67152, "n_trials": 15, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0224, "r_wall_s": 80.44, "compile_s": 13.67, "r_error": "", "src_len": 3148, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3019, "tout": 1773, "ts": 1791531526.2896059, "chk": "compile_error", "code_len": 3131}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6051, "tout": 1553, "ts": 1791531589.693968, "chk": "ok", "code_len": 3148}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7716, "tout": 54, "ts": 1791531733.117631, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7794, "tout": 1536, "ts": 1791531746.326607, "chk": null, "code_len": 3148}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 3019, "started": 1791531509.7492554}
{"ep": "h1-01097", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.166, "speedup": 2.166, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 384.5, "calls": 3, "tokens_in": 12705, "tokens_out": 10037, "ctx_chars": 0, "t_end": 1791531828.9006925, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.166, "lo95": 2.1653, "mean": 2.1642, "ev_only": 2.1593, "ref_ms": 3.64313, "cand_ms": 1.68195, "n_trials": 215, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 175.3, "compile_s": 12.32, "r_error": "", "src_len": 4371, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1631, "tout": 5256, "ts": 1791531490.0136833, "chk": "no_custom_kernel", "code_len": 4396}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4329, "tout": 2570, "ts": 1791531613.3030071, "chk": "ok", "code_len": 4371}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6745, "tout": 2211, "ts": 1791531652.6886036, "chk": null, "code_len": 4371}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1631, "started": 1791531444.3534262}
{"ep": "h1-01160", "task": "L2_035", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2674, "speedup": 1.2674, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 114.7, "calls": 1, "tokens_in": 5908, "tokens_out": 951, "ctx_chars": 9835, "t_end": 1791531831.2904031, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2674, "lo95": 1.2646, "mean": 1.2676, "ev_only": 1.269, "ref_ms": 17.54729, "cand_ms": 13.84491, "n_trials": 87, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0715, "r_wall_s": 105.87, "compile_s": 2.28, "r_error": "", "src_len": 1838, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5908, "tout": 951, "ts": 1791531725.0065475, "chk": null, "code_len": 1838}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5908, "started": 1791531716.6056087}
{"ep": "h1-01120", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.173, "speedup": 2.173, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 287.9, "calls": 2, "tokens_in": 12572, "tokens_out": 1575, "ctx_chars": 9855, "t_end": 1791531838.154871, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.173, "lo95": 2.1702, "mean": 2.1702, "ev_only": 2.1817, "ref_ms": 6.34691, "cand_ms": 2.92079, "n_trials": 214, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.238, "r_wall_s": 90.0, "compile_s": 2.12, "r_error": "", "src_len": 955, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5846, "tout": 989, "ts": 1791531580.066306, "chk": "ok", "code_len": 955}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6726, "tout": 586, "ts": 1791531747.1786306, "chk": null, "code_len": 955}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5846, "started": 1791531570.6196735}
{"ep": "h1-01050", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.3589, "speedup": 0.3589, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 613.8, "calls": 2, "tokens_in": 15885, "tokens_out": 6279, "ctx_chars": 10864, "t_end": 1791531846.0593088, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.3589, "lo95": 0.3555, "mean": 0.341, "ev_only": 0.3586, "ref_ms": 9.94258, "cand_ms": 27.70086, "n_trials": 38, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 377.43, "compile_s": 3.4, "r_error": "", "src_len": 4048, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6627, "tout": 4176, "ts": 1791531267.8210404, "chk": "ok", "code_len": 4048}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9258, "tout": 2103, "ts": 1791531467.8513012, "chk": null, "code_len": 4048}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6627, "started": 1791531232.2291682}
{"ep": "h1-01169", "task": "L2_032", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 77.0, "calls": 1, "tokens_in": 1681, "tokens_out": 972, "ctx_chars": 0, "t_end": 1791531846.312448, "error": "RuntimeError: Error building extension 'scale_min_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=scale_min_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 67.06, "compile_s": 67.05, "r_error": "RuntimeError: Error building extension 'scale_min_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=scale_min_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "src_len": 2084, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1681, "tout": 972, "ts": 1791531779.2099614, "chk": null, "code_len": 2084}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1681, "started": 1791531769.2628267}
{"ep": "h1-01170", "task": "L2_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 73.8, "calls": 1, "tokens_in": 1694, "tokens_out": 759, "ctx_chars": 0, "t_end": 1791531847.2940965, "error": "RuntimeError: Error building extension 'scale_fused_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=scale_fused_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 66.49, "compile_s": 66.48, "r_error": "RuntimeError: Error building extension 'scale_fused_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=scale_fused_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/", "src_len": 1509, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1694, "tout": 759, "ts": 1791531780.762177, "chk": null, "code_len": 1509}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1694, "started": 1791531773.5281358}
{"ep": "h1-01074", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4031, "speedup": 1.4031, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 500.8, "calls": 2, "tokens_in": 4665, "tokens_out": 3892, "ctx_chars": 0, "t_end": 1791531850.198921, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4031, "lo95": 1.4027, "mean": 1.4356, "ev_only": 1.4013, "ref_ms": 8.01899, "cand_ms": 5.71507, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 404.97, "compile_s": 2.13, "r_error": "", "src_len": 1934, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 2522, "ts": 1791531392.0304885, "chk": "ok", "code_len": 1934}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3100, "tout": 1370, "ts": 1791531445.1475732, "chk": null, "code_len": 1934}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791531369.7537036}
{"ep": "h1-01176", "task": "L2_098", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0009, "speedup": 1.0009, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 55.9, "calls": 1, "tokens_in": 1737, "tokens_out": 2189, "ctx_chars": 0, "t_end": 1791531859.501559, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0009, "lo95": 0.9994, "mean": 1.0012, "ev_only": 1.0011, "ref_ms": 8.12878, "cand_ms": 8.12183, "n_trials": 179, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.004, "r_wall_s": 33.3, "compile_s": 2.32, "r_error": "", "src_len": 1469, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1737, "tout": 2189, "ts": 1791531826.150237, "chk": null, "code_len": 1469}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1737, "started": 1791531803.5581598}
{"ep": "h1-01150", "task": "L1_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4612, "speedup": 0.4612, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 210.4, "calls": 2, "tokens_in": 6769, "tokens_out": 7614, "ctx_chars": 0, "t_end": 1791531859.5071802, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.4612, "lo95": 0.4607, "mean": 0.4617, "ev_only": 0.4608, "ref_ms": 10.04277, "cand_ms": 21.77583, "n_trials": 49, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9998, "r_wall_s": 118.14, "compile_s": 2.83, "r_error": "", "src_len": 4463, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2003, "tout": 5209, "ts": 1791531693.2557797, "chk": "ok", "code_len": 4463}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4766, "tout": 2405, "ts": 1791531740.47553, "chk": null, "code_len": 4463}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2003, "started": 1791531649.0622299}
{"ep": "h1-01164", "task": "L2_027", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1578, "speedup": 1.1578, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 104.7, "calls": 3, "tokens_in": 9841, "tokens_out": 3273, "ctx_chars": 0, "t_end": 1791531862.5811143, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1578, "lo95": 1.1557, "mean": 1.1587, "ev_only": 1.161, "ref_ms": 20.21785, "cand_ms": 17.46284, "n_trials": 64, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0244, "r_wall_s": 37.87, "compile_s": 2.7, "r_error": "", "src_len": 2044, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1727, "tout": 2168, "ts": 1791531779.33512, "chk": "ok", "code_len": 2092}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4007, "tout": 76, "ts": 1791531815.7841501, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4107, "tout": 1029, "ts": 1791531824.553733, "chk": null, "code_len": 2044}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1727, "started": 1791531757.909055}
{"ep": "h1-01130", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2431, "speedup": 1.2431, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 287.7, "calls": 2, "tokens_in": 4563, "tokens_out": 3047, "ctx_chars": 0, "t_end": 1791531863.5653787, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2431, "lo95": 1.2396, "mean": 1.2443, "ev_only": 1.2445, "ref_ms": 31.23387, "cand_ms": 25.12638, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0286, "r_wall_s": 105.81, "compile_s": 3.93, "r_error": "", "src_len": 1569, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 2227, "ts": 1791531596.703999, "chk": "ok", "code_len": 1569}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2880, "tout": 820, "ts": 1791531757.6671276, "chk": null, "code_len": 1569}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1683, "started": 1791531575.8202326}
{"ep": "h1-01174", "task": "L2_072", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 67.6, "calls": 1, "tokens_in": 1763, "tokens_out": 2124, "ctx_chars": 0, "t_end": 1791531868.4790695, "error": "RuntimeError: Error building extension 'fused_pbn': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pbn -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 46.17, "compile_s": 46.16, "r_error": "RuntimeError: Error building extension 'fused_pbn': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pbn -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "src_len": 3770, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1763, "tout": 2124, "ts": 1791531822.266419, "chk": null, "code_len": 3770}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1763, "started": 1791531800.9067175}
{"ep": "h1-01161", "task": "L2_040", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0409, "speedup": 1.0409, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.9, "calls": 2, "tokens_in": 12087, "tokens_out": 2144, "ctx_chars": 8989, "t_end": 1791531876.8665776, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0409, "lo95": 1.0406, "mean": 1.0405, "ev_only": 1.0412, "ref_ms": 30.53747, "cand_ms": 29.33847, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 46.14, "compile_s": 1.9, "r_error": "", "src_len": 955, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5552, "tout": 1573, "ts": 1791531736.1672266, "chk": "ok", "code_len": 955}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6535, "tout": 571, "ts": 1791531829.9566665, "chk": null, "code_len": 955}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5552, "started": 1791531720.9683557}
{"ep": "h1-01127", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.3567, "speedup": 0.3567, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 325.3, "calls": 2, "tokens_in": 9882, "tokens_out": 18053, "ctx_chars": 0, "t_end": 1791531884.071597, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.3567, "lo95": 0.3561, "mean": 0.3605, "ev_only": 0.3545, "ref_ms": 3.86416, "cand_ms": 10.83434, "n_trials": 118, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9983, "r_wall_s": 154.77, "compile_s": 2.44, "r_error": "", "src_len": 8941, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2380, "tout": 13377, "ts": 1791531673.976347, "chk": "ok", "code_len": 8941}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7502, "tout": 4676, "ts": 1791531729.1866992, "chk": null, "code_len": 8941}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2380, "started": 1791531558.7630038}
{"ep": "h1-01021", "task": "L3_015", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4694, "speedup": 0.4694, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 772.7, "calls": 4, "tokens_in": 32791, "tokens_out": 11041, "ctx_chars": 0, "t_end": 1791531892.0121, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.4694, "lo95": 0.4672, "mean": 0.469, "ev_only": 0.4693, "ref_ms": 15.66454, "cand_ms": 33.37072, "n_trials": 34, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0469, "r_wall_s": 42.1, "compile_s": 12.19, "r_error": "", "src_len": 6125, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3022, "tout": 2820, "ts": 1791531144.5682797, "chk": "compile_error", "code_len": 6107}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7095, "tout": 2546, "ts": 1791531218.6643305, "chk": "no_custom_kernel", "code_len": 6087}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9765, "tout": 3032, "ts": 1791531303.6385887, "chk": "ok", "code_len": 6218}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 12909, "tout": 2643, "ts": 1791531849.8924952, "chk": null, "code_len": 6125}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "no_custom_kernel", "ok", null], "first_tin": 3022, "started": 1791531119.301872}
{"ep": "h1-01159", "task": "L2_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2499, "speedup": 1.2499, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.5, "calls": 2, "tokens_in": 15629, "tokens_out": 2375, "ctx_chars": 12155, "t_end": 1791531893.3306463, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2499, "lo95": 1.2491, "mean": 1.2498, "ev_only": 1.2504, "ref_ms": 12.20865, "cand_ms": 9.76766, "n_trials": 113, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0699, "r_wall_s": 87.13, "compile_s": 3.28, "r_error": "", "src_len": 1501, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7203, "tout": 1546, "ts": 1791531724.364901, "chk": "ok", "code_len": 1501}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8426, "tout": 829, "ts": 1791531805.3754163, "chk": null, "code_len": 1501}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7203, "started": 1791531710.7875764}
{"ep": "h1-01128", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8593, "speedup": 0.8593, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 342.8, "calls": 2, "tokens_in": 10670, "tokens_out": 5307, "ctx_chars": 6513, "t_end": 1791531902.691068, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.8593, "lo95": 0.8589, "mean": 0.8809, "ev_only": 0.8595, "ref_ms": 10.71223, "cand_ms": 12.46626, "n_trials": 133, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 124.69, "compile_s": 2.52, "r_error": "", "src_len": 2655, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4389, "tout": 3403, "ts": 1791531589.9473252, "chk": "ok", "code_len": 2655}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6281, "tout": 1904, "ts": 1791531777.9273503, "chk": null, "code_len": 2655}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4389, "started": 1791531559.9349709}
{"ep": "h1-01134", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.6893, "speedup": 2.6893, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 318.9, "calls": 2, "tokens_in": 16442, "tokens_out": 6395, "ctx_chars": 11582, "t_end": 1791531904.727135, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 2.6893, "lo95": 2.6872, "mean": 2.6875, "ev_only": 2.6895, "ref_ms": 35.60879, "cand_ms": 13.24109, "n_trials": 42, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9997, "r_wall_s": 197.74, "compile_s": 2.06, "r_error": "", "src_len": 3247, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7119, "tout": 4713, "ts": 1791531627.5228727, "chk": "ok", "code_len": 3247}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9323, "tout": 1682, "ts": 1791531706.173795, "chk": null, "code_len": 3247}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7119, "started": 1791531585.8603046}
{"ep": "h1-01086", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 54.9091, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 490.3, "calls": 3, "tokens_in": 32965, "tokens_out": 22240, "ctx_chars": 10613, "t_end": 1791531904.9291253, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 54.9091, "lo95": 54.3862, "mean": 53.4024, "ev_only": 56.0252, "ref_ms": 36.37364, "cand_ms": 0.66243, "n_trials": 38, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.8529, "r_wall_s": 152.2, "compile_s": 16.88, "r_error": "", "src_len": 8291, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6522, "tout": 14221, "ts": 1791531546.1072657, "chk": "no_custom_kernel", "code_len": 8313}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11192, "tout": 4125, "ts": 1791531590.6388028, "chk": "ok", "code_len": 8291}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15251, "tout": 3894, "ts": 1791531752.6608305, "chk": null, "code_len": 8291}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6522, "started": 1791531414.6531737}
{"ep": "h1-01091", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0298, "speedup": 1.0298, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 477.9, "calls": 2, "tokens_in": 12874, "tokens_out": 5501, "ctx_chars": 8449, "t_end": 1791531904.9646928, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0298, "lo95": 1.0284, "mean": 1.0307, "ev_only": 1.0285, "ref_ms": 8.25454, "cand_ms": 8.01579, "n_trials": 88, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0091, "r_wall_s": 62.57, "compile_s": 2.72, "r_error": "", "src_len": 3311, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5359, "tout": 3759, "ts": 1791531459.8779728, "chk": "ok", "code_len": 3311}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7515, "tout": 1742, "ts": 1791531842.267308, "chk": null, "code_len": 3311}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5359, "started": 1791531427.1001477}
{"ep": "h1-01137", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.039, "speedup": 3.039, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 317.2, "calls": 2, "tokens_in": 7277, "tokens_out": 10603, "ctx_chars": 0, "t_end": 1791531917.7589307, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.039, "lo95": 3.0374, "mean": 3.2354, "ev_only": 3.0447, "ref_ms": 35.46156, "cand_ms": 11.66867, "n_trials": 40, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 187.95, "compile_s": 16.02, "r_error": "", "src_len": 5297, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 8066, "ts": 1791531673.1711895, "chk": "ok", "code_len": 5297}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5315, "tout": 2537, "ts": 1791531728.8936143, "chk": null, "code_len": 5297}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791531600.5248864}
{"ep": "h1-01165", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3953, "speedup": 1.3953, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.8, "calls": 3, "tokens_in": 11976, "tokens_out": 8297, "ctx_chars": 0, "t_end": 1791531920.2826288, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3953, "lo95": 1.3947, "mean": 1.3954, "ev_only": 1.393, "ref_ms": 7.50174, "cand_ms": 5.37631, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1068, "r_wall_s": 77.43, "compile_s": 2.31, "r_error": "", "src_len": 3781, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1685, "tout": 4263, "ts": 1791531799.1386623, "chk": "forbidden", "code_len": 3776}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4143, "tout": 2091, "ts": 1791531814.69467, "chk": "ok", "code_len": 3781}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6148, "tout": 1943, "ts": 1791531842.4412117, "chk": null, "code_len": 3781}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", null], "first_tin": 1685, "started": 1791531761.4755075}
{"ep": "h1-01136", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3698, "speedup": 1.3698, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 332.4, "calls": 3, "tokens_in": 11299, "tokens_out": 7719, "ctx_chars": 0, "t_end": 1791531931.7852008, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3698, "lo95": 1.3681, "mean": 1.3916, "ev_only": 1.373, "ref_ms": 7.2895, "cand_ms": 5.32158, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 203.76, "compile_s": 2.45, "r_error": "", "src_len": 2339, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1701, "tout": 4027, "ts": 1791531634.914077, "chk": "ok", "code_len": 2960}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3970, "tout": 2078, "ts": 1791531664.4549153, "chk": "ok", "code_len": 2339}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5628, "tout": 1614, "ts": 1791531727.8075502, "chk": null, "code_len": 2339}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 1701, "started": 1791531599.4097788}
{"ep": "h1-01156", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1948, "speedup": 1.1948, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 238.7, "calls": 2, "tokens_in": 5428, "tokens_out": 5196, "ctx_chars": 0, "t_end": 1791531941.7932568, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1948, "lo95": 1.1933, "mean": 1.2021, "ev_only": 1.1961, "ref_ms": 10.7266, "cand_ms": 8.97782, "n_trials": 118, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 70.38, "compile_s": 4.25, "r_error": "", "src_len": 3102, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1686, "tout": 3566, "ts": 1791531735.9395318, "chk": "ok", "code_len": 3102}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3742, "tout": 1630, "ts": 1791531871.378216, "chk": null, "code_len": 3102}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1686, "started": 1791531703.1147397}
{"ep": "h1-01126", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0038, "speedup": 1.0038, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 387.2, "calls": 2, "tokens_in": 13702, "tokens_out": 1533, "ctx_chars": 10909, "t_end": 1791531944.548637, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0038, "lo95": 1.001, "mean": 1.0163, "ev_only": 1.0043, "ref_ms": 16.1913, "cand_ms": 16.12987, "n_trials": 72, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.001, "r_wall_s": 168.99, "compile_s": 2.78, "r_error": "", "src_len": 948, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6428, "tout": 972, "ts": 1791531566.1312478, "chk": "ok", "code_len": 948}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7274, "tout": 561, "ts": 1791531775.50014, "chk": null, "code_len": 948}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6428, "started": 1791531557.3559818}
{"ep": "h1-01158", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 9.2598, "speedup": 9.2598, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 240.5, "calls": 3, "tokens_in": 14914, "tokens_out": 12937, "ctx_chars": 0, "t_end": 1791531947.343254, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 9.2598, "lo95": 9.2485, "mean": 9.1807, "ev_only": 9.2592, "ref_ms": 5.90582, "cand_ms": 0.63779, "n_trials": 177, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 80.12, "compile_s": 19.8, "r_error": "", "src_len": 5150, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1845, "tout": 7524, "ts": 1791531773.2466304, "chk": "no_custom_kernel", "code_len": 5172}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5149, "tout": 2805, "ts": 1791531832.6237497, "chk": "ok", "code_len": 5150}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7920, "tout": 2608, "ts": 1791531867.1518073, "chk": null, "code_len": 5150}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1845, "started": 1791531706.8646781}
{"ep": "h1-01119", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3629, "speedup": 1.3629, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 407.7, "calls": 2, "tokens_in": 5083, "tokens_out": 4834, "ctx_chars": 0, "t_end": 1791531949.3688788, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.3629, "lo95": 1.3615, "mean": 1.3617, "ev_only": 1.3655, "ref_ms": 7.37105, "cand_ms": 5.4082, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 59.82, "compile_s": 2.59, "r_error": "", "src_len": 2613, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 3332, "ts": 1791531571.4052675, "chk": "ok", "code_len": 2613}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3519, "tout": 1502, "ts": 1791531754.5283453, "chk": null, "code_len": 2613}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791531541.698154}
{"ep": "h1-01145", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.6058, "speedup": 2.6058, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 331.3, "calls": 2, "tokens_in": 6725, "tokens_out": 6022, "ctx_chars": 0, "t_end": 1791531949.6617427, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.6058, "lo95": 2.6004, "mean": 2.8317, "ev_only": 2.633, "ref_ms": 2.36347, "cand_ms": 0.907, "n_trials": 201, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 214.31, "compile_s": 15.01, "r_error": "", "src_len": 4915, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1921, "tout": 3587, "ts": 1791531647.6319704, "chk": "ok", "code_len": 4915}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4804, "tout": 2435, "ts": 1791531734.39605, "chk": null, "code_len": 4915}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1921, "started": 1791531618.3623533}
{"ep": "h1-01141", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.9859, "speedup": 4.9859, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 341.4, "calls": 3, "tokens_in": 32118, "tokens_out": 25675, "ctx_chars": 8224, "t_end": 1791531955.282615, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.9859, "lo95": 4.9637, "mean": 4.9735, "ev_only": 4.995, "ref_ms": 32.60805, "cand_ms": 6.54, "n_trials": 31, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9868, "r_wall_s": 52.54, "compile_s": 11.78, "r_error": "", "src_len": 8900, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5510, "tout": 15396, "ts": 1791531748.436312, "chk": "no_custom_kernel", "code_len": 8924}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10758, "tout": 5417, "ts": 1791531849.3114176, "chk": "ok", "code_len": 8900}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15850, "tout": 4862, "ts": 1791531902.717349, "chk": null, "code_len": 8900}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5510, "started": 1791531613.8819594}
{"ep": "h1-01155", "task": "L1_013", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8824, "speedup": 0.8824, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.0, "calls": 3, "tokens_in": 23788, "tokens_out": 3284, "ctx_chars": 10850, "t_end": 1791531956.0606074, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.8824, "lo95": 0.8813, "mean": 0.8825, "ev_only": 0.8824, "ref_ms": 7.33154, "cand_ms": 8.30863, "n_trials": 165, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 158.48, "compile_s": 3.04, "r_error": "", "src_len": 2533, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6674, "tout": 1731, "ts": 1791531717.1407318, "chk": "ok", "code_len": 2533}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8514, "tout": 62, "ts": 1791531785.3579886, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8600, "tout": 1491, "ts": 1791531797.423681, "chk": null, "code_len": 2533}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6674, "started": 1791531701.099335}
{"ep": "h1-01171", "task": "L1_001", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9478, "speedup": 0.9478, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 173.7, "calls": 2, "tokens_in": 14381, "tokens_out": 3581, "ctx_chars": 10384, "t_end": 1791531957.5569155, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9478, "lo95": 0.9475, "mean": 0.9474, "ev_only": 0.9465, "ref_ms": 7.29217, "cand_ms": 7.69393, "n_trials": 128, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 45.01, "compile_s": 2.27, "r_error": "", "src_len": 2884, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6174, "tout": 1924, "ts": 1791531802.2319713, "chk": "ok", "code_len": 2884}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8207, "tout": 1657, "ts": 1791531912.4272506, "chk": null, "code_len": 2884}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6174, "started": 1791531783.8903666}
{"ep": "h1-01045", "task": "L3_045", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9977, "speedup": 0.9977, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 736.1, "calls": 5, "tokens_in": 41253, "tokens_out": 19237, "ctx_chars": 0, "t_end": 1791531958.491418, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9977, "lo95": 0.9968, "mean": 0.9978, "ev_only": 0.9966, "ref_ms": 23.4231, "cand_ms": 23.47737, "n_trials": 55, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0004, "r_wall_s": 45.26, "compile_s": 2.68, "r_error": "", "src_len": 3218, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2736, "tout": 6739, "ts": 1791531302.3924615, "chk": "incorrect", "code_len": 5838}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6368, "tout": 4459, "ts": 1791531445.134949, "chk": "incorrect", "code_len": 6189}, {"turn": 2, "action": "CHECK", "stop": null, "tin": 9951, "tout": 2112, "ts": 1791531659.1626754, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9983, "tout": 3757, "ts": 1791531693.2523763, "chk": "incorrect", "code_len": 3726}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 12215, "tout": 2170, "ts": 1791531913.2071145, "chk": null, "code_len": 3218}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn", null], "chk_statuses": ["incorrect", "incorrect", "no_code", "incorrect", null], "first_tin": 2736, "started": 1791531242.7226548}
{"ep": "h1-01087", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2914, "speedup": 1.2914, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 547.1, "calls": 2, "tokens_in": 7544, "tokens_out": 8050, "ctx_chars": 0, "t_end": 1791531965.065195, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2914, "lo95": 1.2873, "mean": 1.2798, "ev_only": 1.2907, "ref_ms": 8.37828, "cand_ms": 6.48753, "n_trials": 165, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0882, "r_wall_s": 117.23, "compile_s": 2.03, "r_error": "", "src_len": 5148, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2192, "tout": 5375, "ts": 1791531465.2521563, "chk": "ok", "code_len": 5148}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5352, "tout": 2675, "ts": 1791531847.8126166, "chk": null, "code_len": 5148}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2192, "started": 1791531418.0135887}
{"ep": "h1-01082", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4521, "speedup": 1.4521, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 572.4, "calls": 3, "tokens_in": 25983, "tokens_out": 8614, "ctx_chars": 10850, "t_end": 1791531967.1668465, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4521, "lo95": 1.4517, "mean": 1.4522, "ev_only": 1.4571, "ref_ms": 7.28298, "cand_ms": 5.01536, "n_trials": 181, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 66.8, "compile_s": 1.96, "r_error": "", "src_len": 2332, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6676, "tout": 5139, "ts": 1791531442.1367912, "chk": "ok", "code_len": 2811}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8821, "tout": 2071, "ts": 1791531861.1008692, "chk": "ok", "code_len": 2332}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10486, "tout": 1404, "ts": 1791531900.2310266, "chk": null, "code_len": 2332}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 6676, "started": 1791531394.8133159}
{"ep": "h1-01123", "task": "L3_039", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.7226, "speedup": 7.7226, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 415.2, "calls": 3, "tokens_in": 28857, "tokens_out": 23422, "ctx_chars": 8224, "t_end": 1791531967.5589883, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.7226, "lo95": 7.2067, "mean": 7.6972, "ev_only": 7.7475, "ref_ms": 42.05256, "cand_ms": 5.44541, "n_trials": 45, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 100.74, "compile_s": 19.24, "r_error": "", "src_len": 7548, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 15436, "ts": 1791531689.2714958, "chk": "no_custom_kernel", "code_len": 7531}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9730, "tout": 4282, "ts": 1791531734.2775443, "chk": "ok", "code_len": 7548}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13637, "tout": 3704, "ts": 1791531866.7901819, "chk": null, "code_len": 7548}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5490, "started": 1791531552.3525774}
{"ep": "h1-01046", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.2508, "speedup": 2.2508, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 742.2, "calls": 3, "tokens_in": 20579, "tokens_out": 15622, "ctx_chars": 0, "t_end": 1791531969.828346, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.2508, "lo95": 2.25, "mean": 2.2452, "ev_only": 2.2656, "ref_ms": 4.02238, "cand_ms": 1.78709, "n_trials": 185, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4412, "r_wall_s": 108.47, "compile_s": 20.85, "r_error": "", "src_len": 7300, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 7783, "ts": 1791531291.8381002, "chk": "no_custom_kernel", "code_len": 7325}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6971, "tout": 4091, "ts": 1791531439.5789435, "chk": "ok", "code_len": 7300}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10915, "tout": 3748, "ts": 1791531861.127202, "chk": null, "code_len": 7300}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2693, "started": 1791531227.598175}
{"ep": "h1-01131", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2022, "speedup": 1.2022, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 413.0, "calls": 2, "tokens_in": 4939, "tokens_out": 4659, "ctx_chars": 0, "t_end": 1791531989.3363523, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2022, "lo95": 1.2014, "mean": 1.2181, "ev_only": 1.2031, "ref_ms": 16.10774, "cand_ms": 13.39886, "n_trials": 60, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 223.15, "compile_s": 2.83, "r_error": "", "src_len": 2341, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1550, "tout": 3367, "ts": 1791531606.9142914, "chk": "ok", "code_len": 2341}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3389, "tout": 1292, "ts": 1791531765.9900856, "chk": null, "code_len": 2341}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1550, "started": 1791531576.3259966}
{"ep": "h1-01157", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5428, "speedup": 1.5428, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 290.6, "calls": 2, "tokens_in": 6520, "tokens_out": 7779, "ctx_chars": 0, "t_end": 1791531994.728608, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.5428, "lo95": 1.5415, "mean": 1.5397, "ev_only": 1.5437, "ref_ms": 8.2509, "cand_ms": 5.348, "n_trials": 186, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9995, "r_wall_s": 209.49, "compile_s": 2.13, "r_error": "", "src_len": 4614, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1730, "tout": 5202, "ts": 1791531749.8344915, "chk": "ok", "code_len": 4681}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4790, "tout": 2577, "ts": 1791531785.1358528, "chk": null, "code_len": 4614}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1730, "started": 1791531704.115055}
{"ep": "h1-01182", "task": "L2_056", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9965, "speedup": 0.9965, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 168.1, "calls": 1, "tokens_in": 1572, "tokens_out": 824, "ctx_chars": 0, "t_end": 1791531995.451445, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9965, "lo95": 0.996, "mean": 1.0067, "ev_only": 0.9969, "ref_ms": 16.12411, "cand_ms": 16.18045, "n_trials": 73, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.005, "r_wall_s": 159.9, "compile_s": 52.92, "r_error": "", "src_len": 1408, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1572, "tout": 824, "ts": 1791531835.522751, "chk": null, "code_len": 1408}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1572, "started": 1791531827.3140833}
{"ep": "h1-01216", "task": "L2_095", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0351, "speedup": 1.0351, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 48.1, "calls": 1, "tokens_in": 1668, "tokens_out": 638, "ctx_chars": 0, "t_end": 1791532015.2709832, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0351, "lo95": 1.0345, "mean": 1.0354, "ev_only": 1.0335, "ref_ms": 8.23701, "cand_ms": 7.95782, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 41.05, "compile_s": 1.99, "r_error": "", "src_len": 1131, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1668, "tout": 638, "ts": 1791531974.0683136, "chk": null, "code_len": 1131}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1668, "started": 1791531967.1670847}
{"ep": "h1-01194", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "no_custom_kernel", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 151.6, "calls": 1, "tokens_in": 1751, "tokens_out": 4965, "ctx_chars": 0, "t_end": 1791532020.103107, "error": "none of the candidate's kernels ['__launch_bounds__'] ran on the GPU during forward (torch-only paths are not a kernel)", "f_status": "no_custom_kernel", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": 0.0, "r_wall_s": 108.03, "compile_s": 14.17, "r_error": "none of the candidate's kernels ['__launch_bounds__'] ran on the GPU during forward (torch-only paths are not a kernel)", "src_len": 4298, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1751, "tout": 4965, "ts": 1791531912.0385623, "chk": null, "code_len": 4298}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1751, "started": 1791531868.479307}
{"ep": "h1-01168", "task": "L1_014", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.5599, "speedup": 4.5599, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 251.7, "calls": 2, "tokens_in": 5231, "tokens_out": 5117, "ctx_chars": 0, "t_end": 1791532020.923038, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.5599, "lo95": 4.5429, "mean": 4.5691, "ev_only": 4.6892, "ref_ms": 7.44583, "cand_ms": 1.6329, "n_trials": 76, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 97.44, "compile_s": 2.08, "r_error": "", "src_len": 2844, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1678, "tout": 3694, "ts": 1791531802.8195932, "chk": "ok", "code_len": 2844}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3553, "tout": 1423, "ts": 1791531923.329444, "chk": null, "code_len": 2844}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1678, "started": 1791531769.2383153}
{"ep": "h1-01135", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4501, "speedup": 0.4501, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 433.7, "calls": 3, "tokens_in": 11112, "tokens_out": 10387, "ctx_chars": 0, "t_end": 1791532022.9656546, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.4501, "lo95": 0.4497, "mean": 0.4833, "ev_only": 0.4492, "ref_ms": 16.10566, "cand_ms": 35.7816, "n_trials": 35, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9974, "r_wall_s": 214.77, "compile_s": 3.38, "r_error": "", "src_len": 2498, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1690, "tout": 6635, "ts": 1791531652.7793086, "chk": "incorrect", "code_len": 2763}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3866, "tout": 2318, "ts": 1791531743.0979424, "chk": "ok", "code_len": 2498}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5556, "tout": 1434, "ts": 1791531808.1448028, "chk": null, "code_len": 2498}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1690, "started": 1791531589.2504437}
{"ep": "h1-01180", "task": "L3_047", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.9577, "speedup": 2.9577, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 199.7, "calls": 2, "tokens_in": 8208, "tokens_out": 7974, "ctx_chars": 0, "t_end": 1791532023.8421094, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.9577, "lo95": 2.9509, "mean": 2.9388, "ev_only": 2.9873, "ref_ms": 3.65027, "cand_ms": 1.23417, "n_trials": 158, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9082, "r_wall_s": 91.7, "compile_s": 1.97, "r_error": "", "src_len": 4611, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2693, "tout": 5682, "ts": 1791531873.4489808, "chk": "ok", "code_len": 4611}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5515, "tout": 2292, "ts": 1791531931.8896868, "chk": null, "code_len": 4611}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2693, "started": 1791531824.169164}
{"ep": "h1-01213", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0659, "speedup": 1.0659, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 86.8, "calls": 2, "tokens_in": 4899, "tokens_out": 2880, "ctx_chars": 0, "t_end": 1791532044.3375978, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0659, "lo95": 1.0643, "mean": 1.0664, "ev_only": 1.0644, "ref_ms": 8.4834, "cand_ms": 7.959, "n_trials": 116, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 50.09, "compile_s": 3.09, "r_error": "", "src_len": 1779, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 1826, "ts": 1791531973.416605, "chk": "ok", "code_len": 1779}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3184, "tout": 1054, "ts": 1791531994.1780562, "chk": null, "code_len": 1779}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791531957.5571518}
{"ep": "h1-01217", "task": "L3_029", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5402, "speedup": 0.5402, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 77.9, "calls": 1, "tokens_in": 10319, "tokens_out": 5093, "ctx_chars": 6513, "t_end": 1791532045.4466567, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.5402, "lo95": 0.5061, "mean": 0.6657, "ev_only": 0.5406, "ref_ms": 8.83286, "cand_ms": 16.35187, "n_trials": 113, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0453, "r_wall_s": 37.71, "compile_s": 3.39, "r_error": "", "src_len": 12037, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 10319, "tout": 5093, "ts": 1791532007.7060885, "chk": null, "code_len": 12037}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 10319, "started": 1791531967.5594566}
{"ep": "h1-01175", "task": "L1_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.9625, "speedup": 2.9625, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 245.3, "calls": 2, "tokens_in": 7219, "tokens_out": 10632, "ctx_chars": 0, "t_end": 1791532046.913096, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 2.9625, "lo95": 2.9617, "mean": 2.9598, "ev_only": 2.9667, "ref_ms": 35.77439, "cand_ms": 12.07556, "n_trials": 45, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9993, "r_wall_s": 108.71, "compile_s": 11.77, "r_error": "", "src_len": 5559, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 7941, "ts": 1791531870.9650989, "chk": "ok", "code_len": 5559}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5257, "tout": 2691, "ts": 1791531937.408451, "chk": null, "code_len": 5559}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791531801.5880806}
{"ep": "h1-01203", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.6219, "speedup": 4.6219, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 129.3, "calls": 2, "tokens_in": 7147, "tokens_out": 6823, "ctx_chars": 0, "t_end": 1791532047.0540755, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.6219, "lo95": 4.615, "mean": 4.5056, "ev_only": 4.5981, "ref_ms": 2.295, "cand_ms": 0.49654, "n_trials": 194, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.7952, "r_wall_s": 62.63, "compile_s": 14.94, "r_error": "", "src_len": 5449, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 4201, "ts": 1791531951.51704, "chk": "ok", "code_len": 5524}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5132, "tout": 2622, "ts": 1791531984.3063896, "chk": null, "code_len": 5449}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2015, "started": 1791531917.7591732}
{"ep": "h1-01208", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3192, "speedup": 1.3192, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 107.7, "calls": 2, "tokens_in": 15448, "tokens_out": 4952, "ctx_chars": 11357, "t_end": 1791532055.0364718, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.3192, "lo95": 1.3185, "mean": 1.3189, "ev_only": 1.3213, "ref_ms": 7.49293, "cand_ms": 5.68, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0551, "r_wall_s": 48.02, "compile_s": 3.29, "r_error": "", "src_len": 2840, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6781, "tout": 3437, "ts": 1791531978.8289943, "chk": "ok", "code_len": 2840}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8667, "tout": 1515, "ts": 1791532006.6149194, "chk": null, "code_len": 2840}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6781, "started": 1791531947.3434913}
{"ep": "h1-01115", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.5904, "speedup": 2.5904, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 522.1, "calls": 2, "tokens_in": 14628, "tokens_out": 3898, "ctx_chars": 10362, "t_end": 1791532057.7224202, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.5904, "lo95": 2.5844, "mean": 2.8037, "ev_only": 2.6207, "ref_ms": 2.37213, "cand_ms": 0.91575, "n_trials": 210, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 291.03, "compile_s": 2.9, "r_error": "", "src_len": 2742, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6379, "tout": 2509, "ts": 1791531557.4651637, "chk": "ok", "code_len": 2742}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8249, "tout": 1389, "ts": 1791531765.8953176, "chk": null, "code_len": 2742}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6379, "started": 1791531535.6177368}
{"ep": "h1-01185", "task": "L2_074", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2711, "speedup": 1.2711, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 222.4, "calls": 3, "tokens_in": 21726, "tokens_out": 2205, "ctx_chars": 10364, "t_end": 1791532060.5768447, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2711, "lo95": 1.2705, "mean": 1.2857, "ev_only": 1.2735, "ref_ms": 5.89568, "cand_ms": 4.6384, "n_trials": 197, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.045, "r_wall_s": 139.9, "compile_s": 2.32, "r_error": "", "src_len": 2140, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6395, "tout": 1140, "ts": 1791531848.4047918, "chk": "ok", "code_len": 2169}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7647, "tout": 13, "ts": 1791531911.6311715, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7684, "tout": 1052, "ts": 1791531920.6083844, "chk": null, "code_len": 2140}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6395, "started": 1791531838.1551235}
{"ep": "h1-01209", "task": "L3_001", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.8945, "speedup": 0.8945, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 111.9, "calls": 2, "tokens_in": 10700, "tokens_out": 5200, "ctx_chars": 6513, "t_end": 1791532061.3178365, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8945, "lo95": 0.8935, "mean": 0.8991, "ev_only": 0.8947, "ref_ms": 10.75306, "cand_ms": 12.02154, "n_trials": 96, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 41.74, "compile_s": 2.09, "r_error": "", "src_len": 2788, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4389, "tout": 3693, "ts": 1791531982.1671557, "chk": "ok", "code_len": 2788}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6311, "tout": 1507, "ts": 1791532019.5443652, "chk": null, "code_len": 2788}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4389, "started": 1791531949.3691018}
{"ep": "h1-01195", "task": "L3_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0833, "speedup": 1.0833, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.0, "calls": 2, "tokens_in": 11075, "tokens_out": 13789, "ctx_chars": 0, "t_end": 1791532063.8314698, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0833, "lo95": 1.0807, "mean": 1.1098, "ev_only": 1.0841, "ref_ms": 39.16216, "cand_ms": 36.15021, "n_trials": 33, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0513, "r_wall_s": 45.72, "compile_s": 1.97, "r_error": "", "src_len": 9302, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3024, "tout": 9390, "ts": 1791531975.0983865, "chk": "ok", "code_len": 9302}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8051, "tout": 4399, "ts": 1791532018.0862513, "chk": null, "code_len": 9302}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3024, "started": 1791531897.2226}
{"ep": "h1-01202", "task": "L2_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.7267, "speedup": 2.7267, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.6, "calls": 3, "tokens_in": 26561, "tokens_out": 9671, "ctx_chars": 10177, "t_end": 1791532067.5245678, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.7267, "lo95": 2.7207, "mean": 2.6333, "ev_only": 2.7272, "ref_ms": 2.38189, "cand_ms": 0.87355, "n_trials": 205, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 50.58, "compile_s": 11.67, "r_error": "", "src_len": 4563, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6105, "tout": 4913, "ts": 1791531948.620672, "chk": "no_custom_kernel", "code_len": 4635}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9021, "tout": 2486, "ts": 1791531981.2434583, "chk": "ok", "code_len": 4563}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11435, "tout": 2272, "ts": 1791532016.895787, "chk": null, "code_len": 4563}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6105, "started": 1791531904.9649217}
{"ep": "h1-01163", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5418, "speedup": 1.5418, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 330.6, "calls": 2, "tokens_in": 15970, "tokens_out": 4352, "ctx_chars": 11288, "t_end": 1791532075.7764714, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5418, "lo95": 1.5412, "mean": 1.5906, "ev_only": 1.5423, "ref_ms": 28.75926, "cand_ms": 18.6535, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.056, "r_wall_s": 237.18, "compile_s": 1.97, "r_error": "", "src_len": 2757, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6972, "tout": 2912, "ts": 1791531790.829521, "chk": "ok", "code_len": 2757}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8998, "tout": 1440, "ts": 1791531838.1750066, "chk": null, "code_len": 2757}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6972, "started": 1791531765.5178246}
{"ep": "h1-01117", "task": "L2_069", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.3036, "speedup": 2.3036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 539.4, "calls": 3, "tokens_in": 13933, "tokens_out": 11000, "ctx_chars": 0, "t_end": 1791532080.4073756, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 2.3036, "lo95": 2.3012, "mean": 2.3556, "ev_only": 2.3162, "ref_ms": 3.63862, "cand_ms": 1.57953, "n_trials": 197, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 94.6, "compile_s": 15.62, "r_error": "", "src_len": 5003, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1631, "tout": 5517, "ts": 1791531590.2882893, "chk": "no_custom_kernel", "code_len": 5025}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4787, "tout": 2879, "ts": 1791531757.4690537, "chk": "ok", "code_len": 5003}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7515, "tout": 2604, "ts": 1791531984.9584239, "chk": null, "code_len": 5003}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1631, "started": 1791531541.0216334}
{"ep": "h1-01142", "task": "L3_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7887, "speedup": 0.7887, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 470.0, "calls": 2, "tokens_in": 17782, "tokens_out": 19177, "ctx_chars": 6513, "t_end": 1791532085.5655599, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7887, "lo95": 0.7834, "mean": 0.9099, "ev_only": 0.7882, "ref_ms": 15.82446, "cand_ms": 20.06431, "n_trials": 82, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.1259, "r_wall_s": 60.91, "compile_s": 2.32, "r_error": "", "src_len": 11465, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5727, "tout": 13580, "ts": 1791531730.8123498, "chk": "ok", "code_len": 11465}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12055, "tout": 5597, "ts": 1791531891.9120474, "chk": null, "code_len": 11465}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5727, "started": 1791531615.6059344}
{"ep": "h1-01166", "task": "L3_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2141, "speedup": 1.2141, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 327.2, "calls": 2, "tokens_in": 7085, "tokens_out": 6108, "ctx_chars": 0, "t_end": 1791532089.0054739, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2141, "lo95": 1.2111, "mean": 1.2155, "ev_only": 1.2174, "ref_ms": 8.36189, "cand_ms": 6.88716, "n_trials": 167, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0444, "r_wall_s": 64.36, "compile_s": 2.15, "r_error": "", "src_len": 4223, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2192, "tout": 3940, "ts": 1791531795.6714547, "chk": "ok", "code_len": 4223}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4893, "tout": 2168, "ts": 1791531889.6390238, "chk": null, "code_len": 4223}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2192, "started": 1791531761.7579427}
{"ep": "h1-01218", "task": "L1_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7302, "speedup": 0.7302, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.9, "calls": 1, "tokens_in": 6878, "tokens_out": 1003, "ctx_chars": 11175, "t_end": 1791532092.7386513, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7302, "lo95": 0.7296, "mean": 0.7351, "ev_only": 0.7275, "ref_ms": 3.2732, "cand_ms": 4.48291, "n_trials": 219, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0006, "r_wall_s": 112.98, "compile_s": 2.38, "r_error": "", "src_len": 2209, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6878, "tout": 1003, "ts": 1791531978.9489214, "chk": null, "code_len": 2209}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6878, "started": 1791531969.8287938}
{"ep": "h1-01207", "task": "L1_017", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5634, "speedup": 1.5634, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 150.5, "calls": 2, "tokens_in": 5126, "tokens_out": 4778, "ctx_chars": 0, "t_end": 1791532095.0385659, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.5634, "lo95": 1.5611, "mean": 1.5613, "ev_only": 1.5645, "ref_ms": 7.74681, "cand_ms": 4.95496, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 98.8, "compile_s": 3.09, "r_error": "", "src_len": 2787, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 2981, "ts": 1791531970.4181113, "chk": "ok", "code_len": 2787}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3561, "tout": 1797, "ts": 1791531996.081599, "chk": null, "code_len": 2787}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1565, "started": 1791531944.548936}
{"ep": "h1-01162", "task": "L2_011", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0579, "speedup": 1.0579, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 374.6, "calls": 2, "tokens_in": 7901, "tokens_out": 9935, "ctx_chars": 0, "t_end": 1791532100.5845292, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0579, "lo95": 1.0563, "mean": 1.058, "ev_only": 1.0601, "ref_ms": 27.93036, "cand_ms": 26.40128, "n_trials": 25, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0205, "r_wall_s": 100.5, "compile_s": 11.56, "r_error": "", "src_len": 7880, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1810, "tout": 6147, "ts": 1791531776.1845953, "chk": "ok", "code_len": 7880}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6091, "tout": 3788, "ts": 1791531999.8685155, "chk": null, "code_len": 7880}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1810, "started": 1791531725.9741497}
{"ep": "h1-01183", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 7.1836, "speedup": 7.1836, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 274.7, "calls": 2, "tokens_in": 5722, "tokens_out": 1168, "ctx_chars": 2425, "t_end": 1791532103.608951, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 7.1836, "lo95": 7.1627, "mean": 7.111, "ev_only": 7.3783, "ref_ms": 3.58281, "cand_ms": 0.49875, "n_trials": 180, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 142.32, "compile_s": 2.18, "r_error": "", "src_len": 844, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2480, "tout": 650, "ts": 1791531834.6431005, "chk": "ok", "code_len": 844}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3242, "tout": 518, "ts": 1791531960.8228462, "chk": null, "code_len": 844}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2480, "started": 1791531828.9009376}
{"ep": "h1-01222", "task": "L2_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 88.5, "calls": 1, "tokens_in": 1587, "tokens_out": 715, "ctx_chars": 0, "t_end": 1791532103.7521355, "error": "RuntimeError: Error building extension 'div_lrelu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=div_lrelu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 60.41, "compile_s": 60.41, "r_error": "RuntimeError: Error building extension 'div_lrelu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=div_lrelu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "src_len": 1424, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1587, "tout": 715, "ts": 1791532043.3154178, "chk": null, "code_len": 1424}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1587, "started": 1791532035.706443}
{"ep": "h1-01173", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3732, "speedup": 1.3732, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 306.8, "calls": 2, "tokens_in": 8853, "tokens_out": 6964, "ctx_chars": 0, "t_end": 1791532106.881822, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3732, "lo95": 1.3724, "mean": 1.3748, "ev_only": 1.3745, "ref_ms": 75.39319, "cand_ms": 54.90241, "n_trials": 22, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0365, "r_wall_s": 77.85, "compile_s": 2.87, "r_error": "", "src_len": 4044, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 4757, "ts": 1791531841.8173494, "chk": "ok", "code_len": 4117}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5832, "tout": 2207, "ts": 1791531894.0596635, "chk": null, "code_len": 4044}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791531800.0514061}
{"ep": "h1-01221", "task": "L2_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2608, "speedup": 1.2608, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 120.1, "calls": 1, "tokens_in": 6424, "tokens_out": 506, "ctx_chars": 11132, "t_end": 1791532115.561611, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2608, "lo95": 1.2602, "mean": 1.2603, "ev_only": 1.2593, "ref_ms": 3.64085, "cand_ms": 2.88766, "n_trials": 203, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2685, "r_wall_s": 114.25, "compile_s": 2.01, "r_error": "", "src_len": 987, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6424, "tout": 506, "ts": 1791532000.4769466, "chk": null, "code_len": 987}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6424, "started": 1791531995.4516997}
{"ep": "h1-01167", "task": "L3_004", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.9695, "speedup": 0.9695, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 354.8, "calls": 4, "tokens_in": 16992, "tokens_out": 4898, "ctx_chars": 0, "t_end": 1791532118.4916759, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9695, "lo95": 0.9663, "mean": 0.9666, "ev_only": 0.9687, "ref_ms": 2.39866, "cand_ms": 2.47406, "n_trials": 220, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0666, "r_wall_s": 37.84, "compile_s": 2.08, "r_error": "", "src_len": 2882, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2013, "tout": 1667, "ts": 1791531779.1674728, "chk": "incorrect", "code_len": 2864}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3814, "tout": 1632, "ts": 1791531936.3850703, "chk": "ok", "code_len": 2882}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5558, "tout": 25, "ts": 1791532067.9981499, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5607, "tout": 1574, "ts": 1791532080.6068957, "chk": null, "code_len": 2882}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 2013, "started": 1791531763.6972075}
{"ep": "h1-01211", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.526, "speedup": 0.526, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 165.3, "calls": 2, "tokens_in": 13440, "tokens_out": 8083, "ctx_chars": 6513, "t_end": 1791532120.5787306, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.526, "lo95": 0.3627, "mean": 0.5451, "ev_only": 0.5235, "ref_ms": 6.63847, "cand_ms": 12.62147, "n_trials": 93, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3303, "r_wall_s": 36.89, "compile_s": 3.4, "r_error": "", "src_len": 5553, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 5285, "ts": 1791531999.521895, "chk": "ok", "code_len": 5553}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8357, "tout": 2798, "ts": 1791532083.6461031, "chk": null, "code_len": 5553}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791531955.2828925}
{"ep": "h1-01199", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5696, "speedup": 1.5696, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.9, "calls": 2, "tokens_in": 5182, "tokens_out": 4428, "ctx_chars": 0, "t_end": 1791532120.6186533, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.5696, "lo95": 1.5667, "mean": 1.6046, "ev_only": 1.5717, "ref_ms": 8.45359, "cand_ms": 5.38592, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 38.77, "compile_s": 2.11, "r_error": "", "src_len": 2670, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1670, "tout": 2918, "ts": 1791531927.386212, "chk": "ok", "code_len": 2670}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3512, "tout": 1510, "ts": 1791532081.312559, "chk": null, "code_len": 2670}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1670, "started": 1791531902.6913202}
{"ep": "h1-01093", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.8299, "speedup": 4.8299, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 691.3, "calls": 4, "tokens_in": 24688, "tokens_out": 21560, "ctx_chars": 0, "t_end": 1791532126.9321108, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.8299, "lo95": 4.813, "mean": 4.7497, "ev_only": 4.8213, "ref_ms": 8.04997, "cand_ms": 1.66669, "n_trials": 197, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9875, "r_wall_s": 277.24, "compile_s": 12.25, "r_error": "", "src_len": 7671, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1783, "tout": 3870, "ts": 1791531468.4757242, "chk": "incorrect", "code_len": 4197}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4436, "tout": 3515, "ts": 1791531656.9170647, "chk": "incorrect", "code_len": 4372}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7055, "tout": 10016, "ts": 1791531764.8044207, "chk": "ok", "code_len": 7798}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11414, "tout": 4159, "ts": 1791531849.6469705, "chk": null, "code_len": 7671}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1783, "started": 1791531435.6318514}
{"ep": "h1-01196", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 6.3896, "speedup": 6.3896, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 249.0, "calls": 2, "tokens_in": 4093, "tokens_out": 1405, "ctx_chars": 0, "t_end": 1791532133.0268087, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.3896, "lo95": 6.3375, "mean": 6.5884, "ev_only": 6.602, "ref_ms": 3.67191, "cand_ms": 0.57467, "n_trials": 208, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 49.06, "compile_s": 3.18, "r_error": "", "src_len": 925, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 853, "ts": 1791531892.1383157, "chk": "ok", "code_len": 925}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2529, "tout": 552, "ts": 1791532083.2354307, "chk": null, "code_len": 925}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791531884.0718484}
{"ep": "h1-01154", "task": "L2_003", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.5016, "speedup": 1.5016, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 443.7, "calls": 2, "tokens_in": 15893, "tokens_out": 4851, "ctx_chars": 11288, "t_end": 1791532142.901359, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5016, "lo95": 1.5004, "mean": 1.5017, "ev_only": 1.4998, "ref_ms": 29.05551, "cand_ms": 19.34998, "n_trials": 55, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0801, "r_wall_s": 283.68, "compile_s": 1.94, "r_error": "", "src_len": 2701, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6972, "tout": 3421, "ts": 1791531730.832088, "chk": "ok", "code_len": 2701}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8921, "tout": 1430, "ts": 1791531858.9858918, "chk": null, "code_len": 2701}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6972, "started": 1791531699.211032}
{"ep": "h1-01129", "task": "L3_026", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2893, "speedup": 1.2893, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 578.7, "calls": 2, "tokens_in": 14495, "tokens_out": 28769, "ctx_chars": 0, "t_end": 1791532146.190619, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.2893, "lo95": 1.1985, "mean": 1.2184, "ev_only": 1.2874, "ref_ms": 21.79394, "cand_ms": 16.90401, "n_trials": 73, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.223, "r_wall_s": 51.9, "compile_s": 2.63, "r_error": "", "src_len": 13137, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3593, "tout": 22039, "ts": 1791531756.8978305, "chk": "ok", "code_len": 13137}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10902, "tout": 6730, "ts": 1791531959.642479, "chk": null, "code_len": 13137}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3593, "started": 1791531567.49768}
{"ep": "h1-01220", "task": "L2_015", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4269, "speedup": 1.4269, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 160.1, "calls": 2, "tokens_in": 15485, "tokens_out": 4748, "ctx_chars": 11357, "t_end": 1791532154.79352, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4269, "lo95": 1.4257, "mean": 1.4289, "ev_only": 1.4275, "ref_ms": 7.51533, "cand_ms": 5.26683, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1038, "r_wall_s": 103.77, "compile_s": 4.66, "r_error": "", "src_len": 2870, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6781, "tout": 3296, "ts": 1791532025.0258083, "chk": "ok", "code_len": 2898}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8704, "tout": 1452, "ts": 1791532050.3345382, "chk": null, "code_len": 2870}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6781, "started": 1791531994.7288818}
{"ep": "h1-01152", "task": "L1_071", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.096, "speedup": 0.096, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 468.5, "calls": 2, "tokens_in": 6498, "tokens_out": 4610, "ctx_chars": 0, "t_end": 1791532155.8856304, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.096, "lo95": 0.0958, "mean": 0.0915, "ev_only": 0.0958, "ref_ms": 3.32137, "cand_ms": 34.59348, "n_trials": 43, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 306.48, "compile_s": 12.06, "r_error": "", "src_len": 4445, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2029, "tout": 2328, "ts": 1791531708.3683083, "chk": "ok", "code_len": 4529}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4469, "tout": 2282, "ts": 1791531848.5712392, "chk": null, "code_len": 4445}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2029, "started": 1791531687.3829}
{"ep": "h1-01223", "task": "L2_011", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.6434, "speedup": 3.6434, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 138.8, "calls": 3, "tokens_in": 29589, "tokens_out": 6608, "ctx_chars": 12352, "t_end": 1791532158.886196, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.6434, "lo95": 3.6398, "mean": 3.5316, "ev_only": 3.6505, "ref_ms": 27.90949, "cand_ms": 7.66038, "n_trials": 60, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.205, "r_wall_s": 55.45, "compile_s": 2.13, "r_error": "", "src_len": 6050, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7392, "tout": 3570, "ts": 1791532052.076724, "chk": "ok", "code_len": 6296}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11074, "tout": 25, "ts": 1791532079.1451142, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11123, "tout": 3013, "ts": 1791532103.1885555, "chk": null, "code_len": 6050}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7392, "started": 1791532020.1033618}
{"ep": "h1-01204", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0552, "speedup": 1.0552, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 242.6, "calls": 2, "tokens_in": 15832, "tokens_out": 3849, "ctx_chars": 10864, "t_end": 1791532162.8429322, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0552, "lo95": 1.0546, "mean": 1.0547, "ev_only": 1.0532, "ref_ms": 3.74308, "cand_ms": 3.5472, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 116.1, "compile_s": 8.52, "r_error": "", "src_len": 3193, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6949, "tout": 2277, "ts": 1791531938.2953107, "chk": "ok", "code_len": 3193}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8883, "tout": 1572, "ts": 1791532045.8965745, "chk": null, "code_len": 3193}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6949, "started": 1791531920.2829154}
{"ep": "h1-01238", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0275, "speedup": 1.0275, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 83.5, "calls": 2, "tokens_in": 13201, "tokens_out": 5223, "ctx_chars": 8449, "t_end": 1791532163.9405282, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0275, "lo95": 1.0272, "mean": 1.0396, "ev_only": 1.0287, "ref_ms": 8.20362, "cand_ms": 7.98375, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0099, "r_wall_s": 17.33, "compile_s": 1.82, "r_error": "", "src_len": 3986, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5359, "tout": 3292, "ts": 1791532108.7810278, "chk": "ok", "code_len": 3986}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7842, "tout": 1931, "ts": 1791532146.4565196, "chk": null, "code_len": 3986}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5359, "started": 1791532080.4076314}
{"ep": "h1-01227", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0298, "speedup": 1.0298, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 126.3, "calls": 2, "tokens_in": 12600, "tokens_out": 3803, "ctx_chars": 8449, "t_end": 1791532170.6524088, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0298, "lo95": 1.0295, "mean": 1.0647, "ev_only": 1.0303, "ref_ms": 8.20875, "cand_ms": 7.97125, "n_trials": 134, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0132, "r_wall_s": 24.93, "compile_s": 1.83, "r_error": "", "src_len": 2592, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5359, "tout": 2445, "ts": 1791532065.3930576, "chk": "ok", "code_len": 2592}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7241, "tout": 1358, "ts": 1791532145.6450188, "chk": null, "code_len": 2592}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5359, "started": 1791532044.3378718}
{"ep": "h1-01226", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 25.1339, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.4, "calls": 2, "tokens_in": 6486, "tokens_out": 6738, "ctx_chars": 0, "t_end": 1791532179.2665765, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 25.1339, "lo95": 25.0463, "mean": 24.5735, "ev_only": 25.1095, "ref_ms": 25.12665, "cand_ms": 0.99971, "n_trials": 62, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 29.37, "compile_s": 12.82, "r_error": "", "src_len": 4671, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1755, "tout": 4318, "ts": 1791532059.880424, "chk": "ok", "code_len": 4671}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4731, "tout": 2420, "ts": 1791532149.7225835, "chk": null, "code_len": 4671}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1755, "started": 1791532023.8423991}
{"ep": "h1-01212", "task": "L2_008", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0636, "speedup": 1.0636, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 224.3, "calls": 4, "tokens_in": 34535, "tokens_out": 3718, "ctx_chars": 11062, "t_end": 1791532180.3680465, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0636, "lo95": 1.0602, "mean": 1.0655, "ev_only": 1.0657, "ref_ms": 12.84766, "cand_ms": 12.07953, "n_trials": 81, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0241, "r_wall_s": 115.54, "compile_s": 3.67, "r_error": "", "src_len": 2144, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6693, "tout": 1617, "ts": 1791531973.7172332, "chk": "runtime_error", "code_len": 2155}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8485, "tout": 1063, "ts": 1791531991.3423002, "chk": "ok", "code_len": 2144}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9660, "tout": 13, "ts": 1791532056.179627, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9697, "tout": 1025, "ts": 1791532064.8013825, "chk": null, "code_len": 2144}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 6693, "started": 1791531956.060876}
{"ep": "h1-01186", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.8276, "speedup": 3.8276, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 335.1, "calls": 3, "tokens_in": 14986, "tokens_out": 9548, "ctx_chars": 0, "t_end": 1791532181.1691978, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.8276, "lo95": 3.685, "mean": 3.7491, "ev_only": 4.0024, "ref_ms": 2.31722, "cand_ms": 0.6054, "n_trials": 211, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8092, "r_wall_s": 35.27, "compile_s": 13.36, "r_error": "", "src_len": 5190, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 4306, "ts": 1791531880.5708952, "chk": "no_custom_kernel", "code_len": 5212}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5135, "tout": 2693, "ts": 1791532081.299111, "chk": "ok", "code_len": 5190}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7836, "tout": 2549, "ts": 1791532145.8517208, "chk": null, "code_len": 5190}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2015, "started": 1791531846.0595458}
{"ep": "h1-01233", "task": "L2_012", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0117, "speedup": 1.0117, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 121.4, "calls": 1, "tokens_in": 5888, "tokens_out": 535, "ctx_chars": 9890, "t_end": 1791532181.9574144, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0117, "lo95": 1.0106, "mean": 1.0318, "ev_only": 1.0109, "ref_ms": 8.06279, "cand_ms": 7.96928, "n_trials": 143, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 115.75, "compile_s": 4.86, "r_error": "", "src_len": 1011, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5888, "tout": 535, "ts": 1791532066.0971835, "chk": null, "code_len": 1011}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5888, "started": 1791532060.5771253}
{"ep": "h1-01184", "task": "L1_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2275, "speedup": 1.2275, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 352.3, "calls": 2, "tokens_in": 4913, "tokens_out": 4159, "ctx_chars": 0, "t_end": 1791532183.6316767, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.2275, "lo95": 1.224, "mean": 1.2109, "ev_only": 1.2214, "ref_ms": 7.4836, "cand_ms": 6.09674, "n_trials": 217, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 92.91, "compile_s": 2.47, "r_error": "", "src_len": 2353, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 2653, "ts": 1791531854.5746214, "chk": "ok", "code_len": 2353}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3349, "tout": 1506, "ts": 1791532090.603607, "chk": null, "code_len": 2353}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791531831.2907429}
{"ep": "h1-01181", "task": "L3_049", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.4468, "speedup": 2.4468, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 358.6, "calls": 5, "tokens_in": 77443, "tokens_out": 23655, "ctx_chars": 0, "t_end": 1791532184.1324716, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.4468, "lo95": 2.4187, "mean": 2.4364, "ev_only": 2.4543, "ref_ms": 12.04273, "cand_ms": 4.92181, "n_trials": 111, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0204, "r_wall_s": 28.16, "compile_s": 1.98, "r_error": "", "src_len": 2574, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2675, "tout": 5879, "ts": 1791531888.8654733, "chk": "incorrect", "code_len": 2168}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8690, "tout": 7536, "ts": 1791531994.3783653, "chk": "incorrect", "code_len": 2518}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 16362, "tout": 7617, "ts": 1791532110.4896867, "chk": "forbidden", "code_len": 2689}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 24073, "tout": 1438, "ts": 1791532123.3566113, "chk": "ok", "code_len": 2719}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 25643, "tout": 1185, "ts": 1791532155.775659, "chk": null, "code_len": 2574}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "forbidden", "ok", null], "first_tin": 2675, "started": 1791531825.5336194}
{"ep": "h1-01193", "task": "L1_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.0405, "speedup": 4.0405, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 321.3, "calls": 3, "tokens_in": 17070, "tokens_out": 12840, "ctx_chars": 0, "t_end": 1791532184.8461978, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 4.0405, "lo95": 4.0382, "mean": 4.1415, "ev_only": 4.0288, "ref_ms": 3.73522, "cand_ms": 0.92445, "n_trials": 205, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 87.57, "compile_s": 15.59, "r_error": "", "src_len": 5662, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2325, "tout": 6714, "ts": 1791531924.3855746, "chk": "no_custom_kernel", "code_len": 5686}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5847, "tout": 3172, "ts": 1791532002.1454723, "chk": "ok", "code_len": 5662}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8898, "tout": 2954, "ts": 1791532096.3006358, "chk": null, "code_len": 5662}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2325, "started": 1791531863.565608}
{"ep": "h1-01236", "task": "L3_046", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9415, "speedup": 0.9415, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.0, "calls": 3, "tokens_in": 29025, "tokens_out": 5050, "ctx_chars": 10384, "t_end": 1791532189.4975216, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9415, "lo95": 0.9392, "mean": 0.9476, "ev_only": 0.9501, "ref_ms": 4.05023, "cand_ms": 4.3018, "n_trials": 211, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0492, "r_wall_s": 65.68, "compile_s": 3.38, "r_error": "", "src_len": 3583, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7295, "tout": 3432, "ts": 1791532096.8420148, "chk": "ok", "code_len": 3583}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10839, "tout": 28, "ts": 1791532110.0857463, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10891, "tout": 1590, "ts": 1791532123.4481745, "chk": null, "code_len": 3583}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7295, "started": 1791532067.525147}
{"ep": "h1-01248", "task": "L2_082", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 73.3, "calls": 1, "tokens_in": 1780, "tokens_out": 1342, "ctx_chars": 0, "t_end": 1791532191.7710683, "error": "RuntimeError: Error building extension 'fused_tanh_pool': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_tanh_pool -DTORCH_API_INCLUDE_EXTENSION_H -I/", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 61.14, "compile_s": 61.13, "r_error": "RuntimeError: Error building extension 'fused_tanh_pool': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_tanh_pool -DTORCH_API_INCLUDE_EXTENSION_H -I/", "src_len": 2947, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1780, "tout": 1342, "ts": 1791532130.5843315, "chk": null, "code_len": 2947}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1780, "started": 1791532118.4919853}
{"ep": "h1-01205", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 4.4609, "speedup": 4.4609, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 269.3, "calls": 3, "tokens_in": 23545, "tokens_out": 11325, "ctx_chars": 6513, "t_end": 1791532201.0716095, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.4609, "lo95": 4.4415, "mean": 4.3343, "ev_only": 4.4487, "ref_ms": 2.29869, "cand_ms": 0.5153, "n_trials": 233, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8117, "r_wall_s": 40.6, "compile_s": 12.66, "r_error": "", "src_len": 5339, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4718, "tout": 5944, "ts": 1791531982.8887453, "chk": "no_custom_kernel", "code_len": 5461}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8025, "tout": 2794, "ts": 1791532037.4978428, "chk": "ok", "code_len": 5339}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10802, "tout": 2587, "ts": 1791532160.428108, "chk": null, "code_len": 5339}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 4718, "started": 1791531931.785698}
{"ep": "h1-01256", "task": "L2_058", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2348, "speedup": 1.2348, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 47.8, "calls": 3, "tokens_in": 22590, "tokens_out": 1783, "ctx_chars": 11393, "t_end": 1791532203.6431212, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2348, "lo95": 1.234, "mean": 1.2344, "ev_only": 1.2346, "ref_ms": 25.06861, "cand_ms": 20.30182, "n_trials": 53, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0354, "r_wall_s": 21.76, "compile_s": 2.64, "r_error": "", "src_len": 1614, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6820, "tout": 915, "ts": 1791532164.706732, "chk": "ok", "code_len": 1614}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7847, "tout": 52, "ts": 1791532174.530008, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7923, "tout": 816, "ts": 1791532181.4889748, "chk": null, "code_len": 1614}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6820, "started": 1791532155.8859231}
{"ep": "h1-01177", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.01, "speedup": 1.01, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 399.7, "calls": 4, "tokens_in": 21672, "tokens_out": 12011, "ctx_chars": 0, "t_end": 1791532203.8002644, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.01, "lo95": 1.0083, "mean": 1.0077, "ev_only": 1.0089, "ref_ms": 8.03666, "cand_ms": 7.95732, "n_trials": 156, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0036, "r_wall_s": 32.9, "compile_s": 13.78, "r_error": "", "src_len": 2121, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1783, "tout": 3576, "ts": 1791531834.3987813, "chk": "incorrect", "code_len": 4053}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4458, "tout": 3039, "ts": 1791531875.5088446, "chk": "incorrect", "code_len": 4100}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6955, "tout": 3902, "ts": 1791532110.1917326, "chk": "ok", "code_len": 2121}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8476, "tout": 1494, "ts": 1791532170.8480988, "chk": null, "code_len": 2121}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1783, "started": 1791531804.1065788}
{"ep": "h1-01251", "task": "L1_013", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.496, "speedup": 1.496, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 78.5, "calls": 2, "tokens_in": 5298, "tokens_out": 3952, "ctx_chars": 0, "t_end": 1791532205.4059334, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.496, "lo95": 1.4953, "mean": 1.4952, "ev_only": 1.4991, "ref_ms": 7.28476, "cand_ms": 4.86961, "n_trials": 199, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 27.84, "compile_s": 1.92, "r_error": "", "src_len": 2560, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1701, "tout": 2537, "ts": 1791532148.1271522, "chk": "ok", "code_len": 2560}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3597, "tout": 1415, "ts": 1791532177.3033948, "chk": null, "code_len": 2560}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1701, "started": 1791532126.93235}
{"ep": "h1-01189", "task": "L2_085", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.3596, "speedup": 3.3596, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 357.2, "calls": 2, "tokens_in": 9194, "tokens_out": 17660, "ctx_chars": 0, "t_end": 1791532207.3914568, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 3.3596, "lo95": 3.3471, "mean": 3.3403, "ev_only": 3.3867, "ref_ms": 4.73892, "cand_ms": 1.41057, "n_trials": 165, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 59.78, "compile_s": 11.89, "r_error": "", "src_len": 10057, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1917, "tout": 12832, "ts": 1791531962.9222164, "chk": "ok", "code_len": 10074}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7277, "tout": 4828, "ts": 1791532013.646108, "chk": null, "code_len": 10057}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1917, "started": 1791531850.1991634}
{"ep": "h1-01257", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0322, "speedup": 1.0322, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 49.1, "calls": 1, "tokens_in": 1706, "tokens_out": 1487, "ctx_chars": 0, "t_end": 1791532207.9389603, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0322, "lo95": 1.0315, "mean": 1.0319, "ev_only": 1.0329, "ref_ms": 8.23141, "cand_ms": 7.97493, "n_trials": 145, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0042, "r_wall_s": 35.68, "compile_s": 2.18, "r_error": "", "src_len": 1101, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1706, "tout": 1487, "ts": 1791532172.0957932, "chk": null, "code_len": 1101}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1706, "started": 1791532158.886459}
{"ep": "h1-01254", "task": "L2_025", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 64.4, "calls": 1, "tokens_in": 1584, "tokens_out": 946, "ctx_chars": 0, "t_end": 1791532210.563946, "error": "RuntimeError: Error building extension 'min_tanh_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=min_tanh_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 55.19, "compile_s": 55.17, "r_error": "RuntimeError: Error building extension 'min_tanh_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=min_tanh_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 1941, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1584, "tout": 946, "ts": 1791532155.3522036, "chk": null, "code_len": 1941}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1584, "started": 1791532146.1908824}
{"ep": "h1-01198", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.116, "speedup": 2.116, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 320.3, "calls": 2, "tokens_in": 8509, "tokens_out": 14594, "ctx_chars": 0, "t_end": 1791532213.6605403, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 2.116, "lo95": 2.1145, "mean": 2.1135, "ev_only": 2.1241, "ref_ms": 5.61097, "cand_ms": 2.65163, "n_trials": 215, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.999, "r_wall_s": 172.16, "compile_s": 21.79, "r_error": "", "src_len": 9766, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 9749, "ts": 1791531976.1527755, "chk": "ok", "code_len": 9766}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6899, "tout": 4845, "ts": 1791532040.6477718, "chk": null, "code_len": 9766}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1610, "started": 1791531893.3309162}
{"ep": "h1-01190", "task": "L1_077", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.1001, "speedup": 2.1001, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 361.2, "calls": 2, "tokens_in": 5984, "tokens_out": 5125, "ctx_chars": 0, "t_end": 1791532220.6779494, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.1001, "lo95": 2.0979, "mean": 2.0993, "ev_only": 2.0982, "ref_ms": 8.67007, "cand_ms": 4.12833, "n_trials": 149, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1742, "r_wall_s": 113.54, "compile_s": 2.98, "r_error": "", "src_len": 2782, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2023, "tout": 3734, "ts": 1791531894.123394, "chk": "ok", "code_len": 2782}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3961, "tout": 1391, "ts": 1791532106.1430984, "chk": null, "code_len": 2782}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2023, "started": 1791531859.5018167}
{"ep": "h1-01228", "task": "L1_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 10.0, "speedup": 12.904, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 177.6, "calls": 3, "tokens_in": 13878, "tokens_out": 2813, "ctx_chars": 4348, "t_end": 1791532223.0705147, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 12.904, "lo95": 12.872, "mean": 12.8056, "ev_only": 12.9133, "ref_ms": 10.07788, "cand_ms": 0.78099, "n_trials": 153, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.9918, "r_wall_s": 51.37, "compile_s": 2.17, "r_error": "", "src_len": 2462, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3529, "tout": 1515, "ts": 1791532059.4559982, "chk": "ok", "code_len": 2462}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5156, "tout": 13, "ts": 1791532160.7922418, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5193, "tout": 1285, "ts": 1791532171.246497, "chk": null, "code_len": 2462}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3529, "started": 1791532045.446935}
{"ep": "h1-01191", "task": "L3_004", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.4517, "speedup": 4.4517, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 367.0, "calls": 3, "tokens_in": 14599, "tokens_out": 9874, "ctx_chars": 0, "t_end": 1791532226.5324686, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 4.4517, "lo95": 4.4362, "mean": 4.3681, "ev_only": 4.5912, "ref_ms": 2.29104, "cand_ms": 0.51464, "n_trials": 188, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.7831, "r_wall_s": 190.12, "compile_s": 13.61, "r_error": "", "src_len": 5126, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2015, "tout": 4699, "ts": 1791531898.705211, "chk": "no_custom_kernel", "code_len": 5148}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4961, "tout": 2642, "ts": 1791531933.0768309, "chk": "ok", "code_len": 5126}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7623, "tout": 2533, "ts": 1791532036.2466571, "chk": null, "code_len": 5126}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2015, "started": 1791531859.5073676}
{"ep": "h1-01235", "task": "L2_063", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0043, "speedup": 1.0043, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 169.9, "calls": 1, "tokens_in": 6275, "tokens_out": 422, "ctx_chars": 10823, "t_end": 1791532233.7096918, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0043, "lo95": 1.0028, "mean": 1.007, "ev_only": 1.0045, "ref_ms": 8.03574, "cand_ms": 8.00118, "n_trials": 163, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 165.48, "compile_s": 2.89, "r_error": "", "src_len": 846, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6275, "tout": 422, "ts": 1791532068.1439168, "chk": null, "code_len": 846}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6275, "started": 1791532063.8317244}
{"ep": "h1-01224", "task": "L2_059", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1183, "speedup": 1.1183, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.2, "calls": 2, "tokens_in": 4876, "tokens_out": 4064, "ctx_chars": 0, "t_end": 1791532234.1133952, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.1183, "lo95": 1.1178, "mean": 1.1192, "ev_only": 1.1184, "ref_ms": 16.08497, "cand_ms": 14.38348, "n_trials": 74, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 127.45, "compile_s": 2.21, "r_error": "", "src_len": 2245, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1550, "tout": 2779, "ts": 1791532045.7589056, "chk": "ok", "code_len": 2245}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3326, "tout": 1285, "ts": 1791532106.5953066, "chk": null, "code_len": 2245}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1550, "started": 1791532020.9232762}
{"ep": "h1-01225", "task": "L3_038", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7783, "speedup": 0.7783, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 212.6, "calls": 2, "tokens_in": 12074, "tokens_out": 1732, "ctx_chars": 8224, "t_end": 1791532235.5931299, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7783, "lo95": 0.7734, "mean": 0.7899, "ev_only": 0.7778, "ref_ms": 79.70355, "cand_ms": 102.41155, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0, "r_wall_s": 150.85, "compile_s": 3.08, "r_error": "", "src_len": 1480, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5514, "tout": 934, "ts": 1791532032.249654, "chk": "ok", "code_len": 1521}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6560, "tout": 798, "ts": 1791532084.7036178, "chk": null, "code_len": 1480}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5514, "started": 1791532022.9659705}
{"ep": "h1-01178", "task": "L3_002", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5723, "speedup": 1.5723, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 433.8, "calls": 2, "tokens_in": 5463, "tokens_out": 5106, "ctx_chars": 0, "t_end": 1791532242.8429785, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.5723, "lo95": 1.5715, "mean": 1.5716, "ev_only": 1.5716, "ref_ms": 33.60395, "cand_ms": 21.37282, "n_trials": 38, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 117.22, "compile_s": 2.37, "r_error": "", "src_len": 2907, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1715, "tout": 3558, "ts": 1791531860.9808245, "chk": "ok", "code_len": 2907}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3748, "tout": 1548, "ts": 1791532125.5818148, "chk": null, "code_len": 2907}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1715, "started": 1791531829.3804593}
{"ep": "h1-01249", "task": "L2_097", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0276, "speedup": 1.0276, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 127.3, "calls": 2, "tokens_in": 6071, "tokens_out": 5818, "ctx_chars": 0, "t_end": 1791532247.8817456, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0276, "lo95": 1.0266, "mean": 1.023, "ev_only": 1.0305, "ref_ms": 8.35377, "cand_ms": 8.12979, "n_trials": 159, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0092, "r_wall_s": 63.01, "compile_s": 2.9, "r_error": "", "src_len": 4348, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1730, "tout": 3745, "ts": 1791532152.637466, "chk": "ok", "code_len": 4348}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4341, "tout": 2073, "ts": 1791532184.7511954, "chk": null, "code_len": 4348}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1730, "started": 1791532120.5790362}
{"ep": "h1-01253", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7874, "speedup": 0.7874, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 106.5, "calls": 2, "tokens_in": 12231, "tokens_out": 2589, "ctx_chars": 9033, "t_end": 1791532249.3670819, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7874, "lo95": 0.7865, "mean": 0.7869, "ev_only": 0.7907, "ref_ms": 3.70042, "cand_ms": 4.69974, "n_trials": 178, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0068, "r_wall_s": 53.65, "compile_s": 1.89, "r_error": "", "src_len": 1225, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 1880, "ts": 1791532181.3999922, "chk": "ok", "code_len": 1225}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6741, "tout": 709, "ts": 1791532195.613306, "chk": null, "code_len": 1225}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791532163.535585}
{"ep": "h1-01255", "task": "L2_098", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 7.2885, "speedup": 7.2885, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 97.2, "calls": 2, "tokens_in": 4584, "tokens_out": 2456, "ctx_chars": 0, "t_end": 1791532251.9488108, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.2885, "lo95": 7.2737, "mean": 6.9009, "ev_only": 7.4983, "ref_ms": 8.04406, "cand_ms": 1.10367, "n_trials": 172, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 66.96, "compile_s": 1.92, "r_error": "", "src_len": 1418, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1739, "tout": 1745, "ts": 1791532170.9416225, "chk": "ok", "code_len": 1418}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2845, "tout": 711, "ts": 1791532184.782994, "chk": null, "code_len": 1418}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1739, "started": 1791532154.7938006}
{"ep": "h1-01237", "task": "L1_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.917, "speedup": 0.917, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.5, "calls": 1, "tokens_in": 1562, "tokens_out": 1890, "ctx_chars": 0, "t_end": 1791532255.257036, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.917, "lo95": 0.9164, "mean": 0.9162, "ev_only": 0.9166, "ref_ms": 7.34769, "cand_ms": 8.01315, "n_trials": 148, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 142.44, "compile_s": 2.56, "r_error": "", "src_len": 3077, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1562, "tout": 1890, "ts": 1791532112.7426982, "chk": null, "code_len": 3077}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1562, "started": 1791532096.1285665}
{"ep": "h1-01139", "task": "L3_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7914, "speedup": 0.7914, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 648.7, "calls": 4, "tokens_in": 39464, "tokens_out": 9469, "ctx_chars": 6513, "t_end": 1791532261.2814462, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7914, "lo95": 0.7863, "mean": 0.8591, "ev_only": 0.7912, "ref_ms": 3.52457, "cand_ms": 4.45364, "n_trials": 164, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0035, "r_wall_s": 219.28, "compile_s": 9.78, "r_error": "", "src_len": 3081, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5546, "tout": 2921, "ts": 1791531657.7197046, "chk": "incorrect", "code_len": 5855}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8598, "tout": 2869, "ts": 1791531758.2401333, "chk": "incorrect", "code_len": 5232}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11598, "tout": 2015, "ts": 1791532018.398283, "chk": "ok", "code_len": 3081}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13722, "tout": 1664, "ts": 1791532041.9771478, "chk": null, "code_len": 3081}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5546, "started": 1791531632.9543328}
{"ep": "h1-01201", "task": "L2_073", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0893, "speedup": 1.0893, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 357.3, "calls": 3, "tokens_in": 20599, "tokens_out": 3104, "ctx_chars": 9590, "t_end": 1791532262.2309017, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0893, "lo95": 1.0888, "mean": 1.0891, "ev_only": 1.0872, "ref_ms": 5.60794, "cand_ms": 5.14811, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.5868, "r_wall_s": 202.69, "compile_s": 2.08, "r_error": "", "src_len": 3080, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5715, "tout": 1590, "ts": 1791531919.3362021, "chk": "ok", "code_len": 3176}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7417, "tout": 26, "ts": 1791532045.8418574, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7467, "tout": 1488, "ts": 1791532058.1065128, "chk": null, "code_len": 3080}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5715, "started": 1791531904.9293466}
{"ep": "h1-01187", "task": "L3_044", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.3788, "speedup": 1.3788, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 417.9, "calls": 4, "tokens_in": 24385, "tokens_out": 6507, "ctx_chars": 0, "t_end": 1791532264.2051046, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.3788, "lo95": 1.3758, "mean": 1.3777, "ev_only": 1.3788, "ref_ms": 75.30552, "cand_ms": 54.61541, "n_trials": 17, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0323, "r_wall_s": 80.33, "compile_s": 2.0, "r_error": "", "src_len": 3942, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3019, "tout": 2316, "ts": 1791531866.6950986, "chk": "runtime_error", "code_len": 3942}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5637, "tout": 2074, "ts": 1791532154.32506, "chk": "ok", "code_len": 3942}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7823, "tout": 59, "ts": 1791532166.802774, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7906, "tout": 2058, "ts": 1791532183.3313866, "chk": null, "code_len": 3942}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 3019, "started": 1791531846.3128273}
{"ep": "h1-01214", "task": "L1_050", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.3248, "speedup": 1.3248, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 306.8, "calls": 2, "tokens_in": 17767, "tokens_out": 11831, "ctx_chars": 13278, "t_end": 1791532265.3337407, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.3248, "lo95": 1.3241, "mean": 1.3292, "ev_only": 1.3219, "ref_ms": 5.29598, "cand_ms": 3.99754, "n_trials": 177, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9985, "r_wall_s": 105.75, "compile_s": 17.54, "r_error": "", "src_len": 5542, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7162, "tout": 8962, "ts": 1791532039.6691468, "chk": "ok", "code_len": 5592}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10605, "tout": 2869, "ts": 1791532159.0886176, "chk": null, "code_len": 5542}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7162, "started": 1791531958.491733}
{"ep": "h1-01246", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.2663, "speedup": 1.2663, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.8, "calls": 2, "tokens_in": 4951, "tokens_out": 3614, "ctx_chars": 0, "t_end": 1791532269.6744647, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2663, "lo95": 1.2636, "mean": 1.2626, "ev_only": 1.2671, "ref_ms": 17.56125, "cand_ms": 13.86803, "n_trials": 84, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0636, "r_wall_s": 64.85, "compile_s": 2.19, "r_error": "", "src_len": 2038, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1693, "tout": 2433, "ts": 1791532128.8879793, "chk": "ok", "code_len": 2038}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3258, "tout": 1181, "ts": 1791532203.6774933, "chk": null, "code_len": 2038}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1693, "started": 1791532106.8820682}
{"ep": "h1-01244", "task": "L2_020", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4491, "speedup": 1.4491, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 166.1, "calls": 2, "tokens_in": 13827, "tokens_out": 1418, "ctx_chars": 10756, "t_end": 1791532269.7355468, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4491, "lo95": 1.4486, "mean": 1.4498, "ev_only": 1.4488, "ref_ms": 13.97767, "cand_ms": 9.64551, "n_trials": 95, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0553, "r_wall_s": 89.43, "compile_s": 3.44, "r_error": "", "src_len": 1265, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6461, "tout": 793, "ts": 1791532111.1288228, "chk": "ok", "code_len": 1265}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7366, "tout": 625, "ts": 1791532179.4990375, "chk": null, "code_len": 1265}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6461, "started": 1791532103.609206}
{"ep": "h1-01240", "task": "L1_065", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.2045, "speedup": 2.2045, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.9, "calls": 1, "tokens_in": 6886, "tokens_out": 1134, "ctx_chars": 11175, "t_end": 1791532271.8861103, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 2.2045, "lo95": 2.2036, "mean": 2.2038, "ev_only": 2.204, "ref_ms": 44.39681, "cand_ms": 20.13958, "n_trials": 32, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 171.82, "compile_s": 3.06, "r_error": "", "src_len": 2305, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6886, "tout": 1134, "ts": 1791532099.1851118, "chk": null, "code_len": 2305}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6886, "started": 1791532089.0057266}
{"ep": "h1-01252", "task": "L2_037", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1926, "speedup": 1.1926, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 140.8, "calls": 1, "tokens_in": 1707, "tokens_out": 1695, "ctx_chars": 0, "t_end": 1791532273.7874422, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1926, "lo95": 1.1924, "mean": 1.1921, "ev_only": 1.1927, "ref_ms": 19.66625, "cand_ms": 16.48955, "n_trials": 62, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1199, "r_wall_s": 123.76, "compile_s": 40.5, "r_error": "", "src_len": 3327, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1707, "tout": 1695, "ts": 1791532149.124992, "chk": null, "code_len": 3327}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1707, "started": 1791532133.027068}
{"ep": "h1-01259", "task": "L1_088", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 6.3444, "speedup": 6.3444, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 125.6, "calls": 2, "tokens_in": 4029, "tokens_out": 1336, "ctx_chars": 0, "t_end": 1791532289.5772471, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.3444, "lo95": 6.309, "mean": 7.5408, "ev_only": 6.6804, "ref_ms": 3.63416, "cand_ms": 0.57282, "n_trials": 192, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 98.57, "compile_s": 2.12, "r_error": "", "src_len": 836, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1564, "tout": 789, "ts": 1791532170.7034338, "chk": "ok", "code_len": 836}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2465, "tout": 547, "ts": 1791532190.2803662, "chk": null, "code_len": 836}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1564, "started": 1791532163.940805}
{"ep": "h1-01245", "task": "L3_036", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.0834, "speedup": 0.0834, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 186.8, "calls": 2, "tokens_in": 11535, "tokens_out": 9120, "ctx_chars": 0, "t_end": 1791532290.5522451, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0834, "lo95": 0.0774, "mean": 0.0865, "ev_only": 0.0834, "ref_ms": 32.31458, "cand_ms": 387.66541, "n_trials": 10, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.142, "r_wall_s": 87.02, "compile_s": 14.72, "r_error": "", "src_len": 3195, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1964, "tout": 7495, "ts": 1791532166.549224, "chk": "ok", "code_len": 3195}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9571, "tout": 1625, "ts": 1791532203.420506, "chk": null, "code_len": 3195}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1964, "started": 1791532103.752374}
{"ep": "h1-01232", "task": "L3_044", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.2753, "speedup": 0.2753, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 238.3, "calls": 2, "tokens_in": 10276, "tokens_out": 11346, "ctx_chars": 0, "t_end": 1791532296.0558095, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.2753, "lo95": 0.2752, "mean": 0.2754, "ev_only": 0.2753, "ref_ms": 75.25862, "cand_ms": 273.34903, "n_trials": 13, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.8204, "r_wall_s": 91.66, "compile_s": 3.46, "r_error": "", "src_len": 6795, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3021, "tout": 7612, "ts": 1791532120.4493868, "chk": "ok", "code_len": 6795}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7255, "tout": 3734, "ts": 1791532203.97278, "chk": null, "code_len": 6795}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3021, "started": 1791532057.7228312}
{"ep": "h1-01200", "task": "L3_002", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.9452, "speedup": 0.9452, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 406.1, "calls": 3, "tokens_in": 16020, "tokens_out": 2366, "ctx_chars": 6513, "t_end": 1791532310.7833877, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9452, "lo95": 0.9447, "mean": 0.9449, "ev_only": 0.9448, "ref_ms": 33.7842, "cand_ms": 35.742, "n_trials": 37, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0012, "r_wall_s": 245.7, "compile_s": 3.53, "r_error": "", "src_len": 2305, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4416, "tout": 1237, "ts": 1791531916.1801858, "chk": "ok", "code_len": 2351}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5765, "tout": 50, "ts": 1791532056.0483716, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5839, "tout": 1079, "ts": 1791532065.0459929, "chk": null, "code_len": 2305}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4416, "started": 1791531904.7274027}
{"ep": "h1-01215", "task": "L3_019", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7709, "speedup": 0.7709, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 348.3, "calls": 2, "tokens_in": 12105, "tokens_out": 4688, "ctx_chars": 6513, "t_end": 1791532313.3907344, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7709, "lo95": 0.7654, "mean": 0.7812, "ev_only": 0.7715, "ref_ms": 3.76234, "cand_ms": 4.88071, "n_trials": 216, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0017, "r_wall_s": 285.88, "compile_s": 3.25, "r_error": "", "src_len": 2961, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5083, "tout": 3112, "ts": 1791531992.8853564, "chk": "ok", "code_len": 3068}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7022, "tout": 1576, "ts": 1791532027.490396, "chk": null, "code_len": 2961}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5083, "started": 1791531965.0654283}
{"ep": "h1-01242", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.1729, "speedup": 1.1729, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 219.8, "calls": 2, "tokens_in": 9636, "tokens_out": 16072, "ctx_chars": 0, "t_end": 1791532314.8230436, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1729, "lo95": 1.1719, "mean": 1.1709, "ev_only": 1.1746, "ref_ms": 5.25987, "cand_ms": 4.48447, "n_trials": 219, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0725, "r_wall_s": 60.97, "compile_s": 28.37, "r_error": "", "src_len": 9482, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1974, "tout": 11037, "ts": 1791532194.1504726, "chk": "ok", "code_len": 9482}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7662, "tout": 5035, "ts": 1791532253.3346174, "chk": null, "code_len": 9482}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1974, "started": 1791532095.0388193}
{"ep": "h1-01206", "task": "L3_033", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0266, "speedup": 1.0266, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 375.1, "calls": 2, "tokens_in": 8340, "tokens_out": 2805, "ctx_chars": 3355, "t_end": 1791532316.8672147, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0266, "lo95": 1.0262, "mean": 1.0266, "ev_only": 1.026, "ref_ms": 20.53384, "cand_ms": 20.00257, "n_trials": 73, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0013, "r_wall_s": 282.02, "compile_s": 14.19, "r_error": "", "src_len": 2450, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3294, "tout": 1640, "ts": 1791531978.5875518, "chk": "ok", "code_len": 2682}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5046, "tout": 1165, "ts": 1791532034.8114173, "chk": null, "code_len": 2450}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3294, "started": 1791531962.1358244}
{"ep": "h1-01260", "task": "L1_040", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.172, "speedup": 3.172, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.0, "calls": 2, "tokens_in": 8056, "tokens_out": 1713, "ctx_chars": 4348, "t_end": 1791532332.6840343, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.172, "lo95": 3.1684, "mean": 3.1619, "ev_only": 3.1702, "ref_ms": 10.13501, "cand_ms": 3.19518, "n_trials": 130, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 106.65, "compile_s": 3.7, "r_error": "", "src_len": 1629, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3529, "tout": 886, "ts": 1791532179.3489876, "chk": "ok", "code_len": 1616}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4527, "tout": 827, "ts": 1791532225.3532443, "chk": null, "code_len": 1629}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3529, "started": 1791532170.6526644}
{"ep": "h1-01263", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0375, "speedup": 1.0375, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 153.3, "calls": 2, "tokens_in": 4257, "tokens_out": 1761, "ctx_chars": 0, "t_end": 1791532334.4215019, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0375, "lo95": 1.0345, "mean": 1.0363, "ev_only": 1.0351, "ref_ms": 8.30631, "cand_ms": 8.00607, "n_trials": 178, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0041, "r_wall_s": 115.97, "compile_s": 3.15, "r_error": "", "src_len": 1041, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1706, "tout": 1127, "ts": 1791532191.6730182, "chk": "ok", "code_len": 1041}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2551, "tout": 634, "ts": 1791532218.3569646, "chk": null, "code_len": 1041}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1706, "started": 1791532181.1694577}
{"ep": "h1-01230", "task": "L2_073", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.5418, "speedup": 0.5418, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 317.7, "calls": 2, "tokens_in": 7615, "tokens_out": 17268, "ctx_chars": 0, "t_end": 1791532364.7828496, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.5418, "lo95": 0.5413, "mean": 0.5429, "ev_only": 0.5417, "ref_ms": 5.60799, "cand_ms": 10.34989, "n_trials": 144, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9967, "r_wall_s": 143.82, "compile_s": 15.64, "r_error": "", "src_len": 8288, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1610, "tout": 13358, "ts": 1791532169.9825656, "chk": "ok", "code_len": 8288}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6005, "tout": 3910, "ts": 1791532220.1508453, "chk": null, "code_len": 8288}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1610, "started": 1791532047.0543094}
{"ep": "h1-01239", "task": "L3_050", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.8641, "speedup": 1.8641, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 287.4, "calls": 3, "tokens_in": 15170, "tokens_out": 4034, "ctx_chars": 2425, "t_end": 1791532372.9357967, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.8641, "lo95": 1.8632, "mean": 1.8874, "ev_only": 1.865, "ref_ms": 12.641, "cand_ms": 6.78112, "n_trials": 121, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4906, "r_wall_s": 130.71, "compile_s": 8.27, "r_error": "", "src_len": 3141, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3398, "tout": 2341, "ts": 1791532108.5065155, "chk": "ok", "code_len": 3478}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5848, "tout": 52, "ts": 1791532225.8277714, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5924, "tout": 1641, "ts": 1791532242.0963485, "chk": null, "code_len": 3141}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3398, "started": 1791532085.5658462}
{"ep": "h1-01273", "task": "L2_070", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 194.4, "calls": 1, "tokens_in": 1668, "tokens_out": 861, "ctx_chars": 0, "t_end": 1791532399.8001115, "error": "RuntimeError: Error building extension 'fused_sig_scale_res': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_sig_scale_res -DTORCH_API_INCLUDE_EXTENSI", "f_status": "compile_error", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "cuda", "own_frac": null, "r_wall_s": 51.55, "compile_s": 51.53, "r_error": "RuntimeError: Error building extension 'fused_sig_scale_res': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_sig_scale_res -DTORCH_API_INCLUDE_EXTENSI", "src_len": 1720, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1668, "tout": 861, "ts": 1791532213.7094326, "chk": null, "code_len": 1720}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1668, "started": 1791532205.406173}
{"ep": "h1-01261", "task": "L2_024", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.5867, "speedup": 0.5867, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.8, "calls": 3, "tokens_in": 7492, "tokens_out": 1783, "ctx_chars": 0, "t_end": 1791532417.1122878, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.5867, "lo95": 0.5858, "mean": 0.5963, "ev_only": 0.5863, "ref_ms": 2.39471, "cand_ms": 4.08197, "n_trials": 207, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4888, "r_wall_s": 197.13, "compile_s": 3.19, "r_error": "", "src_len": 1560, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1749, "tout": 992, "ts": 1791532189.120464, "chk": "ok", "code_len": 1759}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2853, "tout": 13, "ts": 1791532213.03857, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 2890, "tout": 778, "ts": 1791532219.9232621, "chk": null, "code_len": 1560}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1749, "started": 1791532179.267016}
{"ep": "h1-01197", "task": "L3_036", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.3391, "speedup": 3.3391, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 526.9, "calls": 3, "tokens_in": 28477, "tokens_out": 17673, "ctx_chars": 8224, "t_end": 1791532418.9128265, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.3391, "lo95": 3.3125, "mean": 3.8806, "ev_only": 3.3432, "ref_ms": 32.66605, "cand_ms": 9.78294, "n_trials": 44, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 205.56, "compile_s": 74.34, "r_error": "", "src_len": 7208, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5510, "tout": 9892, "ts": 1791531981.852507, "chk": "no_custom_kernel", "code_len": 7231}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9606, "tout": 3937, "ts": 1791532080.8732648, "chk": "ok", "code_len": 7208}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13361, "tout": 3844, "ts": 1791532213.3040578, "chk": null, "code_len": 7208}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5510, "started": 1791531892.0125701}
{"ep": "h1-01138", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0545, "speedup": 1.0545, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 840.4, "calls": 5, "tokens_in": 41206, "tokens_out": 22459, "ctx_chars": 0, "t_end": 1791532449.865376, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0545, "lo95": 1.0543, "mean": 1.0543, "ev_only": 1.0549, "ref_ms": 15.87518, "cand_ms": 15.0542, "n_trials": 101, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0786, "r_wall_s": 228.29, "compile_s": 3.04, "r_error": "", "src_len": 3812, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2837, "tout": 6373, "ts": 1791531666.765528, "chk": "incorrect", "code_len": 3796}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5364, "tout": 8534, "ts": 1791531815.8091786, "chk": "incorrect", "code_len": 6446}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8975, "tout": 2795, "ts": 1791532006.265489, "chk": "ok", "code_len": 2999}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 10859, "tout": 2630, "ts": 1791532099.1830602, "chk": "ok", "code_len": 3812}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13171, "tout": 2127, "ts": 1791532220.7095263, "chk": null, "code_len": 3812}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "ok", null], "first_tin": 2837, "started": 1791531609.4796536}
{"ep": "h1-01250", "task": "L2_078", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.065, "speedup": 1.065, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 347.1, "calls": 2, "tokens_in": 5646, "tokens_out": 7905, "ctx_chars": 0, "t_end": 1791532467.7078888, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.065, "lo95": 1.0645, "mean": 1.0662, "ev_only": 1.0643, "ref_ms": 72.93367, "cand_ms": 68.48216, "n_trials": 18, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0127, "r_wall_s": 246.26, "compile_s": 16.26, "r_error": "", "src_len": 3629, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1699, "tout": 6191, "ts": 1791532179.9607008, "chk": "ok", "code_len": 3686}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3947, "tout": 1714, "ts": 1791532221.3384237, "chk": null, "code_len": 3629}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1699, "started": 1791532120.6189182}
{"ep": "h1-01081", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.1771, "speedup": 2.1771, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 1113.4, "calls": 5, "tokens_in": 33801, "tokens_out": 16405, "ctx_chars": 0, "t_end": 1791532508.1962183, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.1771, "lo95": 2.1754, "mean": 2.1745, "ev_only": 2.175, "ref_ms": 15.87344, "cand_ms": 7.29114, "n_trials": 85, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9949, "r_wall_s": 236.4, "compile_s": 12.05, "r_error": "", "src_len": 2875, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2837, "tout": 4155, "ts": 1791531430.8373046, "chk": "incorrect", "code_len": 2544}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4757, "tout": 3195, "ts": 1791531656.6516488, "chk": "runtime_error", "code_len": 2827}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6988, "tout": 2064, "ts": 1791531791.4833434, "chk": "incorrect", "code_len": 2727}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8688, "tout": 5402, "ts": 1791532027.8027534, "chk": "ok", "code_len": 2875}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 10531, "tout": 1589, "ts": 1791532270.8829362, "chk": null, "code_len": 2875}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "runtime_error", "incorrect", "ok", null], "first_tin": 2837, "started": 1791531394.7638557}
{"ep": "h1-01277", "task": "L2_070", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0249, "speedup": 1.0249, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 314.0, "calls": 2, "tokens_in": 4343, "tokens_out": 2026, "ctx_chars": 0, "t_end": 1791532527.6309037, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0249, "lo95": 1.0241, "mean": 1.0234, "ev_only": 1.0251, "ref_ms": 8.10691, "cand_ms": 7.91015, "n_trials": 159, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 117.9, "compile_s": 2.04, "r_error": "", "src_len": 1054, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1670, "tout": 1400, "ts": 1791532226.8582032, "chk": "ok", "code_len": 1054}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2673, "tout": 626, "ts": 1791532275.1001866, "chk": null, "code_len": 1054}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1670, "started": 1791532213.6607862}
{"ep": "h1-01279", "task": "L2_088", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0285, "speedup": 1.0285, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 310.3, "calls": 3, "tokens_in": 7830, "tokens_out": 2065, "ctx_chars": 0, "t_end": 1791532533.3744473, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0285, "lo95": 1.0261, "mean": 1.0305, "ev_only": 1.0292, "ref_ms": 8.55593, "cand_ms": 8.3186, "n_trials": 165, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0364, "r_wall_s": 94.25, "compile_s": 2.45, "r_error": "", "src_len": 1865, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1789, "tout": 1078, "ts": 1791532233.3892279, "chk": "ok", "code_len": 1912}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2979, "tout": 59, "ts": 1791532431.0202844, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3062, "tout": 928, "ts": 1791532439.0118268, "chk": null, "code_len": 1865}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1789, "started": 1791532223.0707507}
{"ep": "h1-01179", "task": "L3_024", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4529, "speedup": 1.4529, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 731.2, "calls": 3, "tokens_in": 30238, "tokens_out": 26261, "ctx_chars": 6513, "t_end": 1791532551.815969, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4529, "lo95": 1.4487, "mean": 1.4451, "ev_only": 1.4519, "ref_ms": 3.51205, "cand_ms": 2.41728, "n_trials": 183, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.034, "r_wall_s": 319.23, "compile_s": 76.92, "r_error": "", "src_len": 5140, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5548, "tout": 15134, "ts": 1791531953.620984, "chk": "incorrect", "code_len": 8496}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10774, "tout": 8467, "ts": 1791532102.9999454, "chk": "ok", "code_len": 5140}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13916, "tout": 2660, "ts": 1791532232.5381055, "chk": null, "code_len": 5140}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5548, "started": 1791531820.6468647}
{"ep": "h1-01153", "task": "L3_048", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.3647, "speedup": 0.3647, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 860.1, "calls": 4, "tokens_in": 27260, "tokens_out": 16213, "ctx_chars": 2425, "t_end": 1791532557.7863119, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.3647, "lo95": 0.3644, "mean": 0.365, "ev_only": 0.3648, "ref_ms": 15.89743, "cand_ms": 43.58797, "n_trials": 32, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9992, "r_wall_s": 287.9, "compile_s": 10.13, "r_error": "", "src_len": 3241, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3753, "tout": 3357, "ts": 1791531727.1804433, "chk": "incorrect", "code_len": 2987}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5867, "tout": 5424, "ts": 1791531920.202112, "chk": "incorrect", "code_len": 3150}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7836, "tout": 5811, "ts": 1791532043.7710109, "chk": "ok", "code_len": 3241}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9804, "tout": 1621, "ts": 1791532268.884354, "chk": null, "code_len": 3241}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 3753, "started": 1791531697.7116263}
{"ep": "h1-01243", "task": "L2_062", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0676, "speedup": 1.0676, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 457.4, "calls": 2, "tokens_in": 12001, "tokens_out": 2039, "ctx_chars": 8462, "t_end": 1791532557.9835536, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0676, "lo95": 1.0651, "mean": 1.0642, "ev_only": 1.0654, "ref_ms": 8.49037, "cand_ms": 7.95306, "n_trials": 129, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0043, "r_wall_s": 343.18, "compile_s": 3.47, "r_error": "", "src_len": 1650, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 1085, "ts": 1791532109.7742972, "chk": "ok", "code_len": 1650}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6599, "tout": 954, "ts": 1791532214.7059925, "chk": null, "code_len": 1650}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791532100.5848172}
{"ep": "h1-01229", "task": "L2_074", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2627, "speedup": 1.2627, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 513.8, "calls": 2, "tokens_in": 14265, "tokens_out": 2931, "ctx_chars": 10364, "t_end": 1791532560.7103722, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2627, "lo95": 1.2573, "mean": 1.2553, "ev_only": 1.2582, "ref_ms": 5.94445, "cand_ms": 4.70784, "n_trials": 213, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0421, "r_wall_s": 142.78, "compile_s": 3.22, "r_error": "", "src_len": 2109, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6397, "tout": 1884, "ts": 1791532063.9808676, "chk": "ok", "code_len": 2109}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7868, "tout": 1047, "ts": 1791532281.7846725, "chk": null, "code_len": 2109}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6397, "started": 1791532046.9133372}
{"ep": "h1-01272", "task": "L2_095", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0394, "speedup": 1.0394, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 360.7, "calls": 2, "tokens_in": 12164, "tokens_out": 1658, "ctx_chars": 9028, "t_end": 1791532564.4922645, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0394, "lo95": 1.0374, "mean": 1.038, "ev_only": 1.0374, "ref_ms": 8.27745, "cand_ms": 7.96335, "n_trials": 129, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 76.93, "compile_s": 3.0, "r_error": "", "src_len": 1222, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5538, "tout": 976, "ts": 1791532212.6796806, "chk": "ok", "code_len": 1222}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6626, "tout": 682, "ts": 1791532353.5918748, "chk": null, "code_len": 1222}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5538, "started": 1791532203.8005295}
{"ep": "h1-01172", "task": "L1_080", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.5658, "speedup": 0.5658, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 788.9, "calls": 2, "tokens_in": 15837, "tokens_out": 6500, "ctx_chars": 10864, "t_end": 1791532581.155533, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.5658, "lo95": 0.5648, "mean": 0.5657, "ev_only": 0.5658, "ref_ms": 20.28432, "cand_ms": 35.85132, "n_trials": 44, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9999, "r_wall_s": 505.55, "compile_s": 2.82, "r_error": "", "src_len": 3760, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6632, "tout": 4557, "ts": 1791531832.9187784, "chk": "ok", "code_len": 3760}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9205, "tout": 1943, "ts": 1791532074.8253424, "chk": null, "code_len": 3760}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6632, "started": 1791531792.2209964}
{"ep": "h1-01268", "task": "L2_055", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0906, "speedup": 1.0906, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 422.0, "calls": 2, "tokens_in": 14430, "tokens_out": 6680, "ctx_chars": 9898, "t_end": 1791532611.4739752, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0906, "lo95": 1.0898, "mean": 1.0933, "ev_only": 1.0908, "ref_ms": 16.10342, "cand_ms": 14.76603, "n_trials": 64, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2817, "r_wall_s": 99.38, "compile_s": 1.99, "r_error": "", "src_len": 3270, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6027, "tout": 4875, "ts": 1791532233.697339, "chk": "ok", "code_len": 3270}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8403, "tout": 1805, "ts": 1791532378.5215235, "chk": null, "code_len": 3270}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6027, "started": 1791532189.4977539}
{"ep": "h1-01241", "task": "L2_057", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 4.6086, "speedup": 4.6086, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 571.2, "calls": 3, "tokens_in": 13894, "tokens_out": 12804, "ctx_chars": 0, "t_end": 1791532663.9190094, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 4.6086, "lo95": 4.5963, "mean": 4.6289, "ev_only": 4.6515, "ref_ms": 6.31238, "cand_ms": 1.36969, "n_trials": 234, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 154.59, "compile_s": 11.04, "r_error": "", "src_len": 5433, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1559, "tout": 7146, "ts": 1791532157.418903, "chk": "no_custom_kernel", "code_len": 5513}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4752, "tout": 3049, "ts": 1791532210.688733, "chk": "ok", "code_len": 5433}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7583, "tout": 2609, "ts": 1791532373.2943609, "chk": null, "code_len": 5433}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1559, "started": 1791532092.7389276}
{"ep": "h1-01192", "task": "L1_065", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.2678, "speedup": 3.2678, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 825.2, "calls": 3, "tokens_in": 18877, "tokens_out": 20171, "ctx_chars": 0, "t_end": 1791532687.7725358, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.2678, "lo95": 3.2608, "mean": 3.3936, "ev_only": 3.2679, "ref_ms": 44.39022, "cand_ms": 13.58402, "n_trials": 28, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 462.04, "compile_s": 15.67, "r_error": "", "src_len": 7120, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2039, "tout": 12155, "ts": 1791531967.139333, "chk": "no_custom_kernel", "code_len": 7123}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6424, "tout": 4332, "ts": 1791532034.5806823, "chk": "ok", "code_len": 7120}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10414, "tout": 3684, "ts": 1791532224.818635, "chk": null, "code_len": 7120}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2039, "started": 1791531862.5813456}
{"ep": "h1-01264", "task": "L3_048", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 514.5, "calls": 1, "tokens_in": 2835, "tokens_out": 9639, "ctx_chars": 0, "t_end": 1791532696.4837275, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0, "lo95": null, "mean": null, "ev_only": null, "ref_ms": null, "cand_ms": null, "n_trials": null, "fast1": false, "flags": null, "backend": "triton", "own_frac": 0.6464, "r_wall_s": 138.94, "compile_s": 2.3, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 3354, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2835, "tout": 9639, "ts": 1791532286.7732458, "chk": null, "code_len": 3354}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2835, "started": 1791532181.9576502}
{"ep": "h1-01283", "task": "L2_020", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.4055, "speedup": 1.4055, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 465.6, "calls": 2, "tokens_in": 4624, "tokens_out": 2124, "ctx_chars": 0, "t_end": 1791532701.172648, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4055, "lo95": 1.3999, "mean": 1.4115, "ev_only": 1.409, "ref_ms": 14.0619, "cand_ms": 10.00484, "n_trials": 98, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.075, "r_wall_s": 204.0, "compile_s": 3.02, "r_error": "", "src_len": 1208, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1751, "tout": 1479, "ts": 1791532249.5848243, "chk": "ok", "code_len": 1208}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2873, "tout": 645, "ts": 1791532496.192205, "chk": null, "code_len": 1208}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1751, "started": 1791532235.5936573}
{"ep": "h1-01266", "task": "L1_016", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.6844, "speedup": 1.6844, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 517.4, "calls": 2, "tokens_in": 13035, "tokens_out": 4488, "ctx_chars": 9033, "t_end": 1791532701.5286715, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.6844, "lo95": 1.678, "mean": 1.7531, "ev_only": 1.6859, "ref_ms": 7.99004, "cand_ms": 4.74366, "n_trials": 98, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 136.13, "compile_s": 2.51, "r_error": "", "src_len": 2651, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5488, "tout": 2992, "ts": 1791532209.6241856, "chk": "ok", "code_len": 2704}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7547, "tout": 1496, "ts": 1791532295.314406, "chk": null, "code_len": 2651}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5488, "started": 1791532184.1327128}
{"ep": "h1-01267", "task": "L2_035", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.2736, "speedup": 1.2736, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 538.5, "calls": 2, "tokens_in": 13152, "tokens_out": 2155, "ctx_chars": 9835, "t_end": 1791532723.3509264, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2736, "lo95": 1.2692, "mean": 1.2718, "ev_only": 1.2731, "ref_ms": 17.55859, "cand_ms": 13.78634, "n_trials": 84, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.071, "r_wall_s": 313.28, "compile_s": 2.05, "r_error": "", "src_len": 1789, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5910, "tout": 1220, "ts": 1791532195.180073, "chk": "ok", "code_len": 1789}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7242, "tout": 935, "ts": 1791532276.5964959, "chk": null, "code_len": 1789}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5910, "started": 1791532184.8464315}
{"ep": "h1-01269", "task": "L2_058", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 12.7336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 543.5, "calls": 2, "tokens_in": 6357, "tokens_out": 6441, "ctx_chars": 0, "t_end": 1791532735.3206801, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 12.7336, "lo95": 12.7023, "mean": 13.0077, "ev_only": 12.7751, "ref_ms": 25.07, "cand_ms": 1.96881, "n_trials": 68, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 206.74, "compile_s": 17.62, "r_error": "", "src_len": 4948, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1755, "tout": 4126, "ts": 1791532226.8367867, "chk": "ok", "code_len": 5006}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4602, "tout": 2315, "ts": 1791532391.9673088, "chk": null, "code_len": 4948}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1755, "started": 1791532191.7713}
{"ep": "h1-01286", "task": "L2_032", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.1104, "speedup": 1.1104, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 486.1, "calls": 2, "tokens_in": 14372, "tokens_out": 2069, "ctx_chars": 11296, "t_end": 1791532735.4854708, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1104, "lo95": 1.1087, "mean": 1.1102, "ev_only": 1.1103, "ref_ms": 31.53729, "cand_ms": 28.40092, "n_trials": 45, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0481, "r_wall_s": 125.07, "compile_s": 1.91, "r_error": "", "src_len": 1227, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6639, "tout": 1423, "ts": 1791532262.147303, "chk": "ok", "code_len": 1227}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7733, "tout": 646, "ts": 1791532341.946246, "chk": null, "code_len": 1227}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6639, "started": 1791532249.3673203}
{"ep": "h1-01247", "task": "L3_034", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 27.6563, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 621.3, "calls": 3, "tokens_in": 13851, "tokens_out": 11347, "ctx_chars": 0, "t_end": 1791532736.8757823, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 27.6563, "lo95": 27.5568, "mean": 30.374, "ev_only": 28.0537, "ref_ms": 28.57749, "cand_ms": 1.03331, "n_trials": 47, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.8648, "r_wall_s": 212.49, "compile_s": 18.92, "r_error": "", "src_len": 4302, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2037, "tout": 6927, "ts": 1791532177.004779, "chk": "no_custom_kernel", "code_len": 4324}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4773, "tout": 2284, "ts": 1791532226.1616101, "chk": "ok", "code_len": 4302}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7041, "tout": 2136, "ts": 1791532390.0017033, "chk": null, "code_len": 4302}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2037, "started": 1791532115.561915}
{"ep": "h1-01284", "task": "L2_079", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4554, "speedup": 1.4554, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 529.5, "calls": 3, "tokens_in": 27616, "tokens_out": 5542, "ctx_chars": 10508, "t_end": 1791532772.299539, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4554, "lo95": 1.4522, "mean": 1.4511, "ev_only": 1.4628, "ref_ms": 2.17083, "cand_ms": 1.49158, "n_trials": 178, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1102, "r_wall_s": 331.19, "compile_s": 2.55, "r_error": "", "src_len": 2890, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6403, "tout": 4073, "ts": 1791532278.6557279, "chk": "ok", "code_len": 2890}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10588, "tout": 13, "ts": 1791532429.170364, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10625, "tout": 1456, "ts": 1791532441.0539463, "chk": null, "code_len": 2890}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6403, "started": 1791532242.843228}
{"ep": "h1-01188", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.4246, "speedup": 1.4246, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 952.3, "calls": 3, "tokens_in": 54452, "tokens_out": 32681, "ctx_chars": 6513, "t_end": 1791532799.555681, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4246, "lo95": 1.4204, "mean": 1.4374, "ev_only": 1.4246, "ref_ms": 8.66704, "cand_ms": 6.08394, "n_trials": 178, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.1588, "r_wall_s": 226.0, "compile_s": 4.16, "r_error": "", "src_len": 15612, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 10321, "tout": 14962, "ts": 1791531971.3283033, "chk": "incorrect", "code_len": 15704}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 18289, "tout": 10347, "ts": 1791532069.9454527, "chk": "ok", "code_len": 15612}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 25842, "tout": 7372, "ts": 1791532305.090029, "chk": null, "code_len": 15612}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 10321, "started": 1791531847.2943895}
{"ep": "h1-01219", "task": "L2_018", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0111, "speedup": 1.0111, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 813.4, "calls": 4, "tokens_in": 34659, "tokens_out": 8365, "ctx_chars": 9898, "t_end": 1791532802.693329, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0111, "lo95": 1.01, "mean": 1.0147, "ev_only": 1.0091, "ref_ms": 8.04344, "cand_ms": 7.95552, "n_trials": 155, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0028, "r_wall_s": 122.66, "compile_s": 3.2, "r_error": "", "src_len": 913, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6120, "tout": 2605, "ts": 1791532012.256127, "chk": "incorrect", "code_len": 2611}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7967, "tout": 3012, "ts": 1791532183.491514, "chk": "incorrect", "code_len": 2673}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9723, "tout": 2181, "ts": 1791532243.56483, "chk": "ok", "code_len": 913}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10849, "tout": 567, "ts": 1791532545.3072414, "chk": null, "code_len": 913}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6120, "started": 1791531989.336611}
{"ep": "h1-01274", "task": "L1_083", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 2.2462, "speedup": 2.2462, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 595.7, "calls": 2, "tokens_in": 5916, "tokens_out": 4514, "ctx_chars": 0, "t_end": 1791532803.1000597, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.2462, "lo95": 2.2413, "mean": 2.482, "ev_only": 2.235, "ref_ms": 2.36371, "cand_ms": 1.05232, "n_trials": 232, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 310.68, "compile_s": 15.63, "r_error": "", "src_len": 3419, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1921, "tout": 2823, "ts": 1791532232.0749617, "chk": "ok", "code_len": 3419}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3995, "tout": 1691, "ts": 1791532359.1226718, "chk": null, "code_len": 3419}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1921, "started": 1791532207.3916924}
{"ep": "h1-01271", "task": "L2_081", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0334, "speedup": 1.0334, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 603.8, "calls": 2, "tokens_in": 14087, "tokens_out": 1416, "ctx_chars": 10901, "t_end": 1791532807.4435856, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0334, "lo95": 1.0331, "mean": 1.0338, "ev_only": 1.0346, "ref_ms": 8.20936, "cand_ms": 7.94385, "n_trials": 127, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0033, "r_wall_s": 192.9, "compile_s": 1.96, "r_error": "", "src_len": 966, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6549, "tout": 877, "ts": 1791532232.3928509, "chk": "ok", "code_len": 966}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7538, "tout": 539, "ts": 1791532343.6790009, "chk": null, "code_len": 966}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6549, "started": 1791532224.1025152}
{"ep": "h1-01281", "task": "L1_006", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 0.7898, "speedup": 0.7898, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 593.1, "calls": 2, "tokens_in": 12163, "tokens_out": 3118, "ctx_chars": 9033, "t_end": 1791532826.7631438, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7898, "lo95": 0.7893, "mean": 0.7895, "ev_only": 0.7907, "ref_ms": 3.7137, "cand_ms": 4.70204, "n_trials": 184, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0067, "r_wall_s": 27.95, "compile_s": 1.98, "r_error": "", "src_len": 1104, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5490, "tout": 2212, "ts": 1791532255.0883331, "chk": "ok", "code_len": 1104}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6673, "tout": 906, "ts": 1791532663.8173301, "chk": null, "code_len": 1104}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5490, "started": 1791532233.7099497}
{"ep": "h1-01210", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.4782, "speedup": 0.4782, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 879.5, "calls": 2, "tokens_in": 7172, "tokens_out": 11298, "ctx_chars": 0, "t_end": 1791532829.1268823, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.4782, "lo95": 0.4773, "mean": 0.4787, "ev_only": 0.4782, "ref_ms": 20.1184, "cand_ms": 42.07367, "n_trials": 39, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0002, "r_wall_s": 218.73, "compile_s": 20.01, "r_error": "", "src_len": 5950, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1729, "tout": 8310, "ts": 1791532025.5764294, "chk": "ok", "code_len": 5950}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5443, "tout": 2988, "ts": 1791532340.6306095, "chk": null, "code_len": 5950}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1729, "started": 1791531949.6620035}
{"ep": "h1-01258", "task": "L3_046", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.2259, "speedup": 2.2259, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 669.0, "calls": 2, "tokens_in": 17453, "tokens_out": 8743, "ctx_chars": 10384, "t_end": 1791532831.8350194, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.2259, "lo95": 2.2238, "mean": 2.2187, "ev_only": 2.2394, "ref_ms": 4.01672, "cand_ms": 1.80456, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.4577, "r_wall_s": 258.12, "compile_s": 3.98, "r_error": "", "src_len": 4396, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7297, "tout": 6531, "ts": 1791532222.4011774, "chk": "ok", "code_len": 4495}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10156, "tout": 2212, "ts": 1791532304.1161134, "chk": null, "code_len": 4396}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7297, "started": 1791532162.84348}
{"ep": "h1-01276", "task": "L1_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.6736, "speedup": 0.6736, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 645.7, "calls": 3, "tokens_in": 9696, "tokens_out": 4456, "ctx_chars": 0, "t_end": 1791532856.2716253, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.6736, "lo95": 0.6732, "mean": 0.6736, "ev_only": 0.6732, "ref_ms": 7.53086, "cand_ms": 11.1799, "n_trials": 124, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 28.7, "compile_s": 2.02, "r_error": "", "src_len": 2666, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1565, "tout": 1601, "ts": 1791532225.7935305, "chk": "incorrect", "code_len": 2704}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3298, "tout": 1426, "ts": 1791532393.115313, "chk": "ok", "code_len": 2582}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4833, "tout": 1429, "ts": 1791532694.1971886, "chk": null, "code_len": 2666}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1565, "started": 1791532210.5641887}
{"ep": "h1-01262", "task": "L2_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 62.6554, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 676.5, "calls": 2, "tokens_in": 7224, "tokens_out": 11401, "ctx_chars": 0, "t_end": 1791532856.8396327, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 62.6554, "lo95": 62.1422, "mean": 61.6443, "ev_only": 62.5809, "ref_ms": 36.44337, "cand_ms": 0.58165, "n_trials": 38, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.0483, "r_wall_s": 26.13, "compile_s": 11.78, "r_error": "", "src_len": 6216, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1765, "tout": 8403, "ts": 1791532257.0669117, "chk": "ok", "code_len": 6216}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5459, "tout": 2998, "ts": 1791532830.6471105, "chk": null, "code_len": 6216}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1765, "started": 1791532180.3682902}
{"ep": "h1-01280", "task": "L2_027", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 3.9233, "speedup": 3.9233, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 631.0, "calls": 2, "tokens_in": 17428, "tokens_out": 11876, "ctx_chars": 11535, "t_end": 1791532857.5732045, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.9233, "lo95": 3.8807, "mean": 3.8978, "ev_only": 3.9347, "ref_ms": 20.06888, "cand_ms": 5.11533, "n_trials": 39, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0007, "r_wall_s": 25.98, "compile_s": 11.0, "r_error": "", "src_len": 6564, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6867, "tout": 8794, "ts": 1791532304.2349303, "chk": "ok", "code_len": 6564}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10561, "tout": 3082, "ts": 1791532831.534028, "chk": null, "code_len": 6564}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6867, "started": 1791532226.5327132}
{"ep": "h1-01265", "task": "L3_029", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.399, "speedup": 1.399, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 683.8, "calls": 2, "tokens_in": 23672, "tokens_out": 22432, "ctx_chars": 0, "t_end": 1791532867.4437375, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.399, "lo95": 1.3973, "mean": 1.4021, "ev_only": 1.4013, "ref_ms": 8.45983, "cand_ms": 6.04688, "n_trials": 173, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.156, "r_wall_s": 27.65, "compile_s": 12.34, "r_error": "", "src_len": 15752, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7618, "tout": 14625, "ts": 1791532302.9069722, "chk": "ok", "code_len": 15752}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 16054, "tout": 7807, "ts": 1791532705.8352323, "chk": null, "code_len": 15752}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7618, "started": 1791532183.6319604}
{"ep": "h1-01234", "task": "L3_036", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.089, "speedup": 0.089, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 902.0, "calls": 5, "tokens_in": 33230, "tokens_out": 9089, "ctx_chars": 0, "t_end": 1791532963.3658352, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.089, "lo95": 0.088, "mean": 0.0844, "ev_only": 0.089, "ref_ms": 31.76442, "cand_ms": 357.02981, "n_trials": 11, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.1603, "r_wall_s": 25.29, "compile_s": 10.54, "r_error": "", "src_len": 3746, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1964, "tout": 2055, "ts": 1791532080.6353576, "chk": "forbidden", "code_len": 4012}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4180, "tout": 1714, "ts": 1791532094.7439559, "chk": "compile_error", "code_len": 3786}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7160, "tout": 1697, "ts": 1791532174.2936018, "chk": "ok", "code_len": 3746}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8969, "tout": 1880, "ts": 1791532237.4130793, "chk": "incorrect", "code_len": 3918}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 10957, "tout": 1743, "ts": 1791532802.3989062, "chk": null, "code_len": 3746}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "compile_error", "ok", "incorrect", null], "first_tin": 1964, "started": 1791532061.3183026}
{"ep": "h1-01282", "task": "L1_072", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 2.8993, "speedup": 2.8993, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 816.6, "calls": 2, "tokens_in": 16938, "tokens_out": 9279, "ctx_chars": 11175, "t_end": 1791533050.6925519, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 2.8993, "lo95": 2.896, "mean": 2.8949, "ev_only": 2.9208, "ref_ms": 4.38859, "cand_ms": 1.51369, "n_trials": 209, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 34.55, "compile_s": 2.17, "r_error": "", "src_len": 4879, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7067, "tout": 6954, "ts": 1791532297.7767458, "chk": "ok", "code_len": 4879}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9871, "tout": 2325, "ts": 1791532744.8534572, "chk": null, "code_len": 4879}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7067, "started": 1791532234.113639}
{"ep": "h1-01278", "task": "L3_008", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.5701, "speedup": 1.5701, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 835.3, "calls": 2, "tokens_in": 11709, "tokens_out": 22695, "ctx_chars": 0, "t_end": 1791533055.9633105, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5701, "lo95": 1.5686, "mean": 1.568, "ev_only": 1.5737, "ref_ms": 5.24147, "cand_ms": 3.33829, "n_trials": 195, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0484, "r_wall_s": 56.23, "compile_s": 11.52, "r_error": "", "src_len": 14007, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1974, "tout": 15585, "ts": 1791532352.1131413, "chk": "ok", "code_len": 14007}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9735, "tout": 7110, "ts": 1791532864.2473927, "chk": null, "code_len": 14007}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1974, "started": 1791532220.6782064}
{"ep": "h1-01231", "task": "L1_016", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": true, "status": "ok", "score": 1.0024, "speedup": 1.0024, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 1012.5, "calls": 3, "tokens_in": 19322, "tokens_out": 2098, "ctx_chars": 9033, "t_end": 1791533067.564234, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0024, "lo95": 1.0003, "mean": 1.0004, "ev_only": 1.0016, "ref_ms": 8.02218, "cand_ms": 8.00266, "n_trials": 179, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 47.53, "compile_s": 2.0, "r_error": "", "src_len": 473, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5486, "tout": 807, "ts": 1791532064.8855345, "chk": "ok", "code_len": 698}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6402, "tout": 923, "ts": 1791532279.06351, "chk": "ok", "code_len": 473}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7434, "tout": 368, "ts": 1791532748.58687, "chk": null, "code_len": 473}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 5486, "started": 1791532055.0367243}
{"ep": "h1-01270", "task": "L3_049", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 10.0, "speedup": 10.762, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 872.4, "calls": 4, "tokens_in": 28500, "tokens_out": 16949, "ctx_chars": 0, "t_end": 1791533073.463072, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 10.762, "lo95": 10.6623, "mean": 10.1907, "ev_only": 10.9015, "ref_ms": 12.01343, "cand_ms": 1.11628, "n_trials": 129, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.751, "r_wall_s": 36.98, "compile_s": 13.48, "r_error": "", "src_len": 4655, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2677, "tout": 5605, "ts": 1791532252.1056426, "chk": "incorrect", "code_len": 4699}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5545, "tout": 4773, "ts": 1791532476.8421276, "chk": "incorrect", "code_len": 5105}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8757, "tout": 4198, "ts": 1791532606.1102343, "chk": "ok", "code_len": 4655}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11521, "tout": 2373, "ts": 1791532767.9223251, "chk": null, "code_len": 4655}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2677, "started": 1791532201.0721364}
{"ep": "h1-01285", "task": "L3_022", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 0.7141, "speedup": 0.7141, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 841.0, "calls": 2, "tokens_in": 12459, "tokens_out": 19033, "ctx_chars": 0, "t_end": 1791533088.9115396, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7141, "lo95": 0.7129, "mean": 0.7231, "ev_only": 0.7125, "ref_ms": 5.84951, "cand_ms": 8.19144, "n_trials": 159, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.5108, "r_wall_s": 32.05, "compile_s": 2.18, "r_error": "", "src_len": 10115, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3365, "tout": 13955, "ts": 1791532368.0698907, "chk": "ok", "code_len": 10115}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9094, "tout": 5078, "ts": 1791532786.1226254, "chk": null, "code_len": 10115}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3365, "started": 1791532247.8820045}
{"ep": "h1-01275", "task": "L2_018", "reader": "claude-opus-4-8", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 1.0087, "speedup": 1.0087, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 883.4, "calls": 5, "tokens_in": 17521, "tokens_out": 2981, "ctx_chars": 0, "t_end": 1791533091.2959569, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0087, "lo95": 1.0083, "mean": 1.0089, "ev_only": 1.0094, "ref_ms": 7.99495, "cand_ms": 7.92627, "n_trials": 126, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0028, "r_wall_s": 20.68, "compile_s": 2.03, "r_error": "", "src_len": 894, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1781, "tout": 788, "ts": 1791532216.9515874, "chk": "incorrect", "code_len": 1111}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 2703, "tout": 994, "ts": 1791532366.6141007, "chk": "incorrect", "code_len": 1090}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 3829, "tout": 507, "ts": 1791532784.9381514, "chk": "ok", "code_len": 894}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 4448, "tout": 265, "ts": 1791533066.5426233, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 4760, "tout": 427, "ts": 1791533070.5773644, "chk": null, "code_len": 894}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 1781, "started": 1791532207.9392135}
{"ep": "h1-01287", "task": "L3_038", "reader": "claude-opus-5-5", "arm": null, "policy": "store_onoff", "store": false, "status": "ok", "score": 3.6078, "speedup": 3.6078, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 848.4, "calls": 3, "tokens_in": 16682, "tokens_out": 15393, "ctx_chars": 0, "t_end": 1791533100.3956542, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 3.6078, "lo95": 3.6025, "mean": 3.6032, "ev_only": 3.6104, "ref_ms": 78.59009, "cand_ms": 21.78325, "n_trials": 22, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8485, "r_wall_s": 26.92, "compile_s": 11.36, "r_error": "", "src_len": 6521, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1972, "tout": 8771, "ts": 1791532329.859717, "chk": "no_custom_kernel", "code_len": 6543}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5729, "tout": 3469, "ts": 1791532753.211803, "chk": "ok", "code_len": 6521}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8981, "tout": 3153, "ts": 1791533073.4317179, "chk": null, "code_len": 6521}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1972, "started": 1791532251.9492574}