{"ep": "ok-00014", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 16.8, "calls": 1, "tokens_in": 1814, "tokens_out": 725, "ctx_chars": 495, "t_end": 1791522500.106733, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "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": 0.1188, "r_wall_s": 7.41, "compile_s": 1.86, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1218, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1814, "tout": 725, "ts": 1791522492.6700459, "chk": null, "code_len": 1218}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1814, "started": 1791522483.2871583}
{"ep": "ok-00026", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0286, "speedup": 1.0286, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 33.0, "calls": 1, "tokens_in": 2026, "tokens_out": 1537, "ctx_chars": 768, "t_end": 1791522516.2904186, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0286, "lo95": 1.028, "mean": 1.064, "ev_only": 1.0274, "ref_ms": 8.16184, "cand_ms": 7.93527, "n_trials": 124, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 18.64, "compile_s": 2.07, "r_error": "", "src_len": 1825, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2026, "tout": 1537, "ts": 1791522497.57481, "chk": null, "code_len": 1825}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2026, "started": 1791522483.294026}
{"ep": "ok-00019", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0968, "speedup": 1.0968, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 37.4, "calls": 1, "tokens_in": 7259, "tokens_out": 1129, "ctx_chars": 12103, "t_end": 1791522520.7314322, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0968, "lo95": 1.0959, "mean": 1.0964, "ev_only": 1.097, "ref_ms": 22.26372, "cand_ms": 20.29841, "n_trials": 56, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0328, "r_wall_s": 25.21, "compile_s": 1.86, "r_error": "", "src_len": 2090, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7259, "tout": 1129, "ts": 1791522495.3356254, "chk": null, "code_len": 2090}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7259, "started": 1791522483.2908738}
{"ep": "ok-00055", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0299, "speedup": 1.0299, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 46.6, "calls": 2, "tokens_in": 13671, "tokens_out": 1970, "ctx_chars": 10373, "t_end": 1791522529.8608897, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0299, "lo95": 1.0276, "mean": 1.0642, "ev_only": 1.0291, "ref_ms": 8.24729, "cand_ms": 8.00791, "n_trials": 69, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0044, "r_wall_s": 18.87, "compile_s": 2.04, "r_error": "", "src_len": 1797, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6270, "tout": 1019, "ts": 1791522492.5360649, "chk": "ok", "code_len": 1797}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7401, "tout": 951, "ts": 1791522510.896454, "chk": null, "code_len": 1797}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6270, "started": 1791522483.3103056}
{"ep": "ok-00021", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.1447, "speedup": 1.1447, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 47.2, "calls": 3, "tokens_in": 21194, "tokens_out": 1425, "ctx_chars": 10587, "t_end": 1791522530.4863293, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1447, "lo95": 0.8326, "mean": 0.9329, "ev_only": 1.1441, "ref_ms": 46.68808, "cand_ms": 40.78709, "n_trials": 23, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 19.96, "compile_s": 2.03, "r_error": "", "src_len": 910, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 898, "ts": 1791522495.701542, "chk": "ok", "code_len": 910}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7369, "tout": 70, "ts": 1791522506.1629193, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7463, "tout": 457, "ts": 1791522510.482417, "chk": null, "code_len": 910}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791522483.2913368}
{"ep": "ok-00003", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0268, "speedup": 1.0268, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 48.9, "calls": 3, "tokens_in": 24679, "tokens_out": 1872, "ctx_chars": 13736, "t_end": 1791522532.2121572, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0268, "lo95": 1.0265, "mean": 1.0493, "ev_only": 1.0251, "ref_ms": 8.15065, "cand_ms": 7.93774, "n_trials": 150, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0066, "r_wall_s": 21.29, "compile_s": 2.0, "r_error": "", "src_len": 1863, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7508, "tout": 934, "ts": 1791522492.8654685, "chk": "ok", "code_len": 1863}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8554, "tout": 39, "ts": 1791522503.2211313, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8617, "tout": 899, "ts": 1791522510.8502893, "chk": null, "code_len": 1863}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7508, "started": 1791522483.2772307}
{"ep": "ok-00047", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0276, "speedup": 1.0276, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 49.3, "calls": 2, "tokens_in": 16294, "tokens_out": 2084, "ctx_chars": 13736, "t_end": 1791522532.5892687, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0276, "lo95": 1.0269, "mean": 1.0308, "ev_only": 1.0273, "ref_ms": 8.22559, "cand_ms": 8.00451, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0044, "r_wall_s": 18.18, "compile_s": 1.99, "r_error": "", "src_len": 1718, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7510, "tout": 1162, "ts": 1791522494.402848, "chk": "ok", "code_len": 1718}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8784, "tout": 922, "ts": 1791522514.3130462, "chk": null, "code_len": 1718}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7510, "started": 1791522483.305612}
{"ep": "ok-00018", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.036, "speedup": 1.036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 49.5, "calls": 3, "tokens_in": 23871, "tokens_out": 1889, "ctx_chars": 12848, "t_end": 1791522532.7638211, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.036, "lo95": 1.0355, "mean": 1.0851, "ev_only": 1.0362, "ref_ms": 8.25461, "cand_ms": 7.96743, "n_trials": 163, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 19.51, "compile_s": 1.89, "r_error": "", "src_len": 1566, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7153, "tout": 1056, "ts": 1791522495.5211964, "chk": "ok", "code_len": 1566}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8321, "tout": 52, "ts": 1791522505.271971, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8397, "tout": 781, "ts": 1791522513.2265372, "chk": null, "code_len": 1566}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7153, "started": 1791522483.2903683}
{"ep": "ok-00043", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.8549, "speedup": 0.8549, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 50.2, "calls": 1, "tokens_in": 2489, "tokens_out": 2877, "ctx_chars": 495, "t_end": 1791522533.5353718, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.8549, "lo95": 0.7314, "mean": 0.8086, "ev_only": 0.8528, "ref_ms": 5.28378, "cand_ms": 6.1809, "n_trials": 167, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0687, "r_wall_s": 22.73, "compile_s": 2.0, "r_error": "", "src_len": 3501, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2489, "tout": 2877, "ts": 1791522510.7580185, "chk": null, "code_len": 3501}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2489, "started": 1791522483.3020773}
{"ep": "ok-00059", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0369, "speedup": 1.0369, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 63.5, "calls": 2, "tokens_in": 13179, "tokens_out": 2652, "ctx_chars": 9546, "t_end": 1791522546.8206828, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0369, "lo95": 1.0363, "mean": 1.0553, "ev_only": 1.0374, "ref_ms": 8.29228, "cand_ms": 7.99727, "n_trials": 148, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 14.63, "compile_s": 2.11, "r_error": "", "src_len": 1667, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5937, "tout": 1744, "ts": 1791522500.4074156, "chk": "ok", "code_len": 1667}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7242, "tout": 908, "ts": 1791522532.1197476, "chk": null, "code_len": 1667}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5937, "started": 1791522483.3120446}
{"ep": "ok-00005", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0077, "speedup": 1.0077, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 72.1, "calls": 2, "tokens_in": 5451, "tokens_out": 4869, "ctx_chars": 495, "t_end": 1791522555.4106357, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0077, "lo95": 1.0074, "mean": 1.0075, "ev_only": 1.0086, "ref_ms": 8.01966, "cand_ms": 7.9586, "n_trials": 152, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0068, "r_wall_s": 18.15, "compile_s": 2.06, "r_error": "", "src_len": 2722, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1740, "tout": 3110, "ts": 1791522511.7948325, "chk": "ok", "code_len": 2722}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3711, "tout": 1759, "ts": 1791522537.1854706, "chk": null, "code_len": 2722}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1740, "started": 1791522483.279987}
{"ep": "ok-00060", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.8224, "speedup": 0.8224, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.5, "calls": 3, "tokens_in": 11548, "tokens_out": 3872, "ctx_chars": 0, "t_end": 1791522556.7822351, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8224, "lo95": 0.7685, "mean": 0.7893, "ev_only": 0.8191, "ref_ms": 4.57818, "cand_ms": 5.56672, "n_trials": 197, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0676, "r_wall_s": 19.43, "compile_s": 2.07, "r_error": "", "src_len": 3618, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2356, "tout": 2102, "ts": 1791522503.6457222, "chk": "ok", "code_len": 3714}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4570, "tout": 28, "ts": 1791522522.938512, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4622, "tout": 1742, "ts": 1791522537.3275552, "chk": null, "code_len": 3618}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2356, "started": 1791522483.316529}
{"ep": "ok-00036", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0349, "speedup": 1.0349, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 79.5, "calls": 1, "tokens_in": 1933, "tokens_out": 1616, "ctx_chars": 495, "t_end": 1791522562.7600718, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0349, "lo95": 1.0347, "mean": 1.0347, "ev_only": 1.0355, "ref_ms": 8.21747, "cand_ms": 7.94032, "n_trials": 187, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0052, "r_wall_s": 62.54, "compile_s": 43.43, "r_error": "", "src_len": 2881, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1933, "tout": 1616, "ts": 1791522500.1794205, "chk": null, "code_len": 2881}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1933, "started": 1791522483.3002813}
{"ep": "ok-00006", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0144, "speedup": 1.0144, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.5, "calls": 3, "tokens_in": 24719, "tokens_out": 1891, "ctx_chars": 13736, "t_end": 1791522564.7713716, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0144, "lo95": 1.0115, "mean": 1.0165, "ev_only": 1.0194, "ref_ms": 8.21351, "cand_ms": 8.0967, "n_trials": 63, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0067, "r_wall_s": 40.9, "compile_s": 1.95, "r_error": "", "src_len": 1824, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7508, "tout": 938, "ts": 1791522493.334481, "chk": "ok", "code_len": 1865}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8558, "tout": 71, "ts": 1791522507.3761377, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8653, "tout": 882, "ts": 1791522523.6826916, "chk": null, "code_len": 1824}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7508, "started": 1791522483.2826643}
{"ep": "ok-00040", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0073, "speedup": 1.0073, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 84.5, "calls": 2, "tokens_in": 5999, "tokens_out": 5578, "ctx_chars": 495, "t_end": 1791522567.799137, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0073, "lo95": 1.0063, "mean": 1.0071, "ev_only": 1.0057, "ref_ms": 8.03864, "cand_ms": 7.98033, "n_trials": 144, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0097, "r_wall_s": 28.18, "compile_s": 2.77, "r_error": "", "src_len": 3815, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1740, "tout": 3657, "ts": 1791522517.0014882, "chk": "ok", "code_len": 3815}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4259, "tout": 1921, "ts": 1791522539.519679, "chk": null, "code_len": 3815}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1740, "started": 1791522483.3007977}
{"ep": "ok-00030", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.7417, "speedup": 0.7417, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 85.3, "calls": 2, "tokens_in": 10221, "tokens_out": 5148, "ctx_chars": 2425, "t_end": 1791522568.6350663, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7417, "lo95": 0.7392, "mean": 0.7464, "ev_only": 0.741, "ref_ms": 4.09732, "cand_ms": 5.5243, "n_trials": 199, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0695, "r_wall_s": 30.86, "compile_s": 2.34, "r_error": "", "src_len": 3133, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 3565, "ts": 1791522516.8927975, "chk": "ok", "code_len": 3133}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6949, "tout": 1583, "ts": 1791522537.7255583, "chk": null, "code_len": 3133}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3272, "started": 1791522483.2945848}
{"ep": "ok-00046", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.5948, "speedup": 1.5948, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 91.0, "calls": 2, "tokens_in": 5716, "tokens_out": 5113, "ctx_chars": 0, "t_end": 1791522574.3076105, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.5948, "lo95": 1.5931, "mean": 1.59, "ev_only": 1.5968, "ref_ms": 8.2073, "cand_ms": 5.14624, "n_trials": 185, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 35.74, "compile_s": 2.02, "r_error": "", "src_len": 3311, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 3275, "ts": 1791522512.0124972, "chk": "ok", "code_len": 3311}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3991, "tout": 1838, "ts": 1791522538.4892209, "chk": null, "code_len": 3311}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791522483.3049004}
{"ep": "ok-00058", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0134, "speedup": 1.0134, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 100.3, "calls": 3, "tokens_in": 28926, "tokens_out": 2880, "ctx_chars": 15603, "t_end": 1791522583.6062517, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0134, "lo95": 1.0129, "mean": 1.0133, "ev_only": 1.0126, "ref_ms": 29.73833, "cand_ms": 29.34593, "n_trials": 47, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.046, "r_wall_s": 55.64, "compile_s": 1.94, "r_error": "", "src_len": 2672, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8528, "tout": 1534, "ts": 1791522498.8312495, "chk": "ok", "code_len": 2825}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10174, "tout": 26, "ts": 1791522516.5677457, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10224, "tout": 1320, "ts": 1791522527.39375, "chk": null, "code_len": 2672}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 8528, "started": 1791522483.311022}
{"ep": "ok-00034", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9361, "speedup": 0.9361, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 102.0, "calls": 2, "tokens_in": 16862, "tokens_out": 4883, "ctx_chars": 12352, "t_end": 1791522585.3082094, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9361, "lo95": 0.9348, "mean": 0.936, "ev_only": 0.9358, "ref_ms": 29.77255, "cand_ms": 31.80464, "n_trials": 42, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0248, "r_wall_s": 46.21, "compile_s": 2.02, "r_error": "", "src_len": 3127, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7329, "tout": 3186, "ts": 1791522511.2515292, "chk": "ok", "code_len": 3127}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9533, "tout": 1697, "ts": 1791522538.5815077, "chk": null, "code_len": 3127}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7329, "started": 1791522483.2981524}
{"ep": "ok-00042", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0003, "speedup": 1.0003, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 113.2, "calls": 5, "tokens_in": 42878, "tokens_out": 3820, "ctx_chars": 12555, "t_end": 1791522596.5242388, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0003, "lo95": 0.9999, "mean": 1.0255, "ev_only": 0.9986, "ref_ms": 7.9421, "cand_ms": 7.93948, "n_trials": 154, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 24.3, "compile_s": 2.45, "r_error": "", "src_len": 919, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6871, "tout": 552, "ts": 1791522490.8006008, "chk": "incorrect", "code_len": 932}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7556, "tout": 726, "ts": 1791522506.8559263, "chk": "incorrect", "code_len": 970}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8415, "tout": 1072, "ts": 1791522531.3827288, "chk": "incorrect", "code_len": 953}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9620, "tout": 640, "ts": 1791522545.702915, "chk": "incorrect", "code_len": 1019}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 10416, "tout": 830, "ts": 1791522572.1992028, "chk": null, "code_len": 919}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 6871, "started": 1791522483.3032856}
{"ep": "ok-00038", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.996, "speedup": 0.996, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.5, "calls": 3, "tokens_in": 8360, "tokens_out": 3020, "ctx_chars": 0, "t_end": 1791522599.7578523, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.996, "lo95": 0.9949, "mean": 0.997, "ev_only": 0.9955, "ref_ms": 8.04692, "cand_ms": 8.07928, "n_trials": 139, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0172, "r_wall_s": 60.65, "compile_s": 2.76, "r_error": "", "src_len": 2805, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1605, "tout": 1642, "ts": 1791522501.0899968, "chk": "ok", "code_len": 2805}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3359, "tout": 13, "ts": 1791522527.892901, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3396, "tout": 1365, "ts": 1791522538.9628272, "chk": null, "code_len": 2805}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1605, "started": 1791522483.3011417}
{"ep": "ok-00069", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0329, "speedup": 1.0329, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 68.9, "calls": 3, "tokens_in": 25445, "tokens_out": 2793, "ctx_chars": 12848, "t_end": 1791522601.073693, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0329, "lo95": 1.0326, "mean": 1.0329, "ev_only": 1.0333, "ref_ms": 8.20891, "cand_ms": 7.94781, "n_trials": 204, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.006, "r_wall_s": 31.8, "compile_s": 2.03, "r_error": "", "src_len": 1832, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7153, "tout": 1833, "ts": 1791522549.259251, "chk": "ok", "code_len": 1832}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9098, "tout": 72, "ts": 1791522561.211511, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9194, "tout": 888, "ts": 1791522569.2394137, "chk": null, "code_len": 1832}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7153, "started": 1791522532.2125146}
{"ep": "ok-00007", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9395, "speedup": 0.9395, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 128.0, "calls": 2, "tokens_in": 6846, "tokens_out": 5231, "ctx_chars": 1383, "t_end": 1791522611.2329173, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9395, "lo95": 0.9384, "mean": 0.9397, "ev_only": 0.9395, "ref_ms": 29.6827, "cand_ms": 31.59437, "n_trials": 31, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0235, "r_wall_s": 69.76, "compile_s": 2.57, "r_error": "", "src_len": 3123, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2299, "tout": 3600, "ts": 1791522516.2693405, "chk": "ok", "code_len": 3123}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4547, "tout": 1631, "ts": 1791522540.823319, "chk": null, "code_len": 3123}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2299, "started": 1791522483.2827687}
{"ep": "ok-00065", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0207, "speedup": 1.0207, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 103.8, "calls": 3, "tokens_in": 28934, "tokens_out": 2927, "ctx_chars": 15603, "t_end": 1791522620.1396494, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0207, "lo95": 1.0205, "mean": 1.0206, "ev_only": 1.0205, "ref_ms": 29.8137, "cand_ms": 29.20902, "n_trials": 49, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0342, "r_wall_s": 60.19, "compile_s": 3.28, "r_error": "", "src_len": 2684, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8528, "tout": 1518, "ts": 1791522530.7516398, "chk": "ok", "code_len": 2684}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10158, "tout": 66, "ts": 1791522548.0166576, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10248, "tout": 1343, "ts": 1791522559.3769984, "chk": null, "code_len": 2684}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 8528, "started": 1791522516.290793}
{"ep": "ok-00010", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0238, "speedup": 1.0238, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 146.3, "calls": 1, "tokens_in": 1876, "tokens_out": 2072, "ctx_chars": 495, "t_end": 1791522629.5449462, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0238, "lo95": 1.0232, "mean": 1.0238, "ev_only": 1.0242, "ref_ms": 29.74116, "cand_ms": 29.05108, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0349, "r_wall_s": 125.43, "compile_s": 44.71, "r_error": "", "src_len": 4306, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1876, "tout": 2072, "ts": 1791522503.569742, "chk": null, "code_len": 4306}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1876, "started": 1791522483.2844481}
{"ep": "ok-00041", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0103, "speedup": 1.0103, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 148.5, "calls": 3, "tokens_in": 9756, "tokens_out": 6295, "ctx_chars": 1080, "t_end": 1791522631.7567506, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0103, "lo95": 1.0077, "mean": 1.0074, "ev_only": 1.0092, "ref_ms": 8.02467, "cand_ms": 7.94316, "n_trials": 134, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 45.47, "compile_s": 2.8, "r_error": "", "src_len": 983, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 1804, "ts": 1791522501.6893156, "chk": "incorrect", "code_len": 1385}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3297, "tout": 3914, "ts": 1791522559.7713914, "chk": "ok", "code_len": 983}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4341, "tout": 577, "ts": 1791522586.2579958, "chk": null, "code_len": 983}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2118, "started": 1791522483.3020465}
{"ep": "ok-00050", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0917, "speedup": 1.0917, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 156.8, "calls": 3, "tokens_in": 17132, "tokens_out": 5661, "ctx_chars": 2922, "t_end": 1791522640.0748832, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0917, "lo95": 0.9053, "mean": 0.9799, "ev_only": 1.0906, "ref_ms": 5.7639, "cand_ms": 5.27969, "n_trials": 199, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0862, "r_wall_s": 81.95, "compile_s": 15.94, "r_error": "", "src_len": 4998, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3403, "tout": 3315, "ts": 1791522516.391614, "chk": "ok", "code_len": 4998}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6830, "tout": 45, "ts": 1791522539.4353695, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6899, "tout": 2301, "ts": 1791522558.0673196, "chk": null, "code_len": 4998}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3403, "started": 1791522483.3074987}
{"ep": "ok-00024", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 55.4127, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 157.5, "calls": 2, "tokens_in": 7908, "tokens_out": 7550, "ctx_chars": 2016, "t_end": 1791522640.8244386, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 55.4127, "lo95": 54.9646, "mean": 53.4927, "ev_only": 57.4517, "ref_ms": 22.35679, "cand_ms": 0.40346, "n_trials": 59, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 78.73, "compile_s": 4.56, "r_error": "", "src_len": 4124, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2574, "tout": 5394, "ts": 1791522533.9435458, "chk": "ok", "code_len": 4124}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5334, "tout": 2156, "ts": 1791522561.8563507, "chk": null, "code_len": 4124}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2574, "started": 1791522483.2929533}
{"ep": "ok-00078", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0388, "speedup": 1.0388, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.8, "calls": 2, "tokens_in": 5279, "tokens_out": 3199, "ctx_chars": 495, "t_end": 1791522641.5607755, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0388, "lo95": 1.0374, "mean": 1.0915, "ev_only": 1.0391, "ref_ms": 8.2603, "cand_ms": 7.9519, "n_trials": 146, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.003, "r_wall_s": 20.88, "compile_s": 1.91, "r_error": "", "src_len": 1643, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1935, "tout": 2272, "ts": 1791522592.8171558, "chk": "ok", "code_len": 1643}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3344, "tout": 927, "ts": 1791522620.5715358, "chk": null, "code_len": 1643}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1935, "started": 1791522567.7994516}
{"ep": "ok-00009", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 35.1807, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 160.8, "calls": 2, "tokens_in": 6705, "tokens_out": 6586, "ctx_chars": 495, "t_end": 1791522644.1083026, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 35.1807, "lo95": 34.3429, "mean": 31.9649, "ev_only": 35.7023, "ref_ms": 22.34642, "cand_ms": 0.63519, "n_trials": 77, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.7709, "r_wall_s": 85.9, "compile_s": 15.87, "r_error": "", "src_len": 4231, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 4436, "ts": 1791522523.1453047, "chk": "ok", "code_len": 4231}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4743, "tout": 2150, "ts": 1791522557.9738796, "chk": null, "code_len": 4231}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791522483.2838738}
{"ep": "ok-00051", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7685, "speedup": 0.7685, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.8, "calls": 5, "tokens_in": 51261, "tokens_out": 9338, "ctx_chars": 6417, "t_end": 1791522663.0905032, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7685, "lo95": 0.7515, "mean": 0.7161, "ev_only": 0.768, "ref_ms": 32.05403, "cand_ms": 41.7114, "n_trials": 28, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0543, "r_wall_s": 31.81, "compile_s": 1.93, "r_error": "", "src_len": 4194, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5503, "tout": 2466, "ts": 1791522505.5800436, "chk": "incorrect", "code_len": 5118}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8102, "tout": 2757, "ts": 1791522540.5026805, "chk": "incorrect", "code_len": 5239}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 10991, "tout": 2173, "ts": 1791522574.0527954, "chk": "ok", "code_len": 4194}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13273, "tout": 72, "ts": 1791522615.9538188, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13392, "tout": 1870, "ts": 1791522631.1738527, "chk": null, "code_len": 4194}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5503, "started": 1791522483.3088472}
{"ep": "ok-00013", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 86.1153, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.6, "calls": 2, "tokens_in": 8456, "tokens_out": 8258, "ctx_chars": 2016, "t_end": 1791522671.8618617, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 86.1153, "lo95": 85.4176, "mean": 83.8362, "ev_only": 86.4494, "ref_ms": 22.28121, "cand_ms": 0.25874, "n_trials": 67, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 71.63, "compile_s": 18.88, "r_error": "", "src_len": 5560, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2574, "tout": 5535, "ts": 1791522530.7128236, "chk": "ok", "code_len": 5560}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5882, "tout": 2723, "ts": 1791522600.0211365, "chk": null, "code_len": 5560}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2574, "started": 1791522483.2861507}
{"ep": "ok-00075", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.991, "speedup": 0.991, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 124.1, "calls": 3, "tokens_in": 17718, "tokens_out": 3169, "ctx_chars": 7333, "t_end": 1791522680.8328228, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.991, "lo95": 0.9898, "mean": 0.9902, "ev_only": 0.993, "ref_ms": 8.08148, "cand_ms": 8.15487, "n_trials": 187, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0179, "r_wall_s": 78.3, "compile_s": 3.16, "r_error": "", "src_len": 3072, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4705, "tout": 1647, "ts": 1791522571.328278, "chk": "ok", "code_len": 3117}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6464, "tout": 61, "ts": 1791522590.5611875, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6549, "tout": 1461, "ts": 1791522602.4469724, "chk": null, "code_len": 3072}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4705, "started": 1791522556.7825656}
{"ep": "ok-00011", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 206.3, "calls": 1, "tokens_in": 1933, "tokens_out": 1684, "ctx_chars": 495, "t_end": 1791522689.5801542, "error": "RuntimeError: Error building extension 'lse_mish_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=lse_mish_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "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": 52.94, "compile_s": 52.93, "r_error": "RuntimeError: Error building extension 'lse_mish_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=lse_mish_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 3122, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1933, "tout": 1684, "ts": 1791522500.8122823, "chk": null, "code_len": 3122}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1933, "started": 1791522483.2861755}
{"ep": "ok-00020", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0739, "speedup": 1.0739, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 209.8, "calls": 1, "tokens_in": 7684, "tokens_out": 1137, "ctx_chars": 12888, "t_end": 1791522693.0847788, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0739, "lo95": 1.0717, "mean": 1.0763, "ev_only": 1.0744, "ref_ms": 22.39017, "cand_ms": 20.84908, "n_trials": 54, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0327, "r_wall_s": 64.48, "compile_s": 1.91, "r_error": "", "src_len": 2102, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7684, "tout": 1137, "ts": 1791522495.6963766, "chk": null, "code_len": 2102}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7684, "started": 1791522483.2905786}
{"ep": "ok-00049", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.035, "speedup": 1.035, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 211.9, "calls": 2, "tokens_in": 7098, "tokens_out": 7724, "ctx_chars": 495, "t_end": 1791522695.1831071, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.035, "lo95": 1.0326, "mean": 1.0343, "ev_only": 1.0349, "ref_ms": 29.78642, "cand_ms": 28.77795, "n_trials": 38, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0249, "r_wall_s": 125.03, "compile_s": 15.78, "r_error": "", "src_len": 5753, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1878, "tout": 4974, "ts": 1791522526.1211696, "chk": "ok", "code_len": 5753}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5220, "tout": 2750, "ts": 1791522569.5787067, "chk": null, "code_len": 5753}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1878, "started": 1791522483.306343}
{"ep": "ok-00084", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0235, "speedup": 1.0235, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 97.4, "calls": 2, "tokens_in": 13589, "tokens_out": 1838, "ctx_chars": 10373, "t_end": 1791522697.1168, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0235, "lo95": 1.0223, "mean": 1.0262, "ev_only": 1.0219, "ref_ms": 8.28166, "cand_ms": 8.09115, "n_trials": 148, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0066, "r_wall_s": 48.25, "compile_s": 13.33, "r_error": "", "src_len": 1852, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6268, "tout": 941, "ts": 1791522608.262569, "chk": "ok", "code_len": 1852}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7321, "tout": 897, "ts": 1791522648.686546, "chk": null, "code_len": 1852}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6268, "started": 1791522599.7582986}
{"ep": "ok-00002", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8215, "speedup": 0.8215, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 214.6, "calls": 2, "tokens_in": 162511, "tokens_out": 6717, "ctx_chars": 182830, "t_end": 1791522697.9005919, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8215, "lo95": 0.8097, "mean": 0.8339, "ev_only": 0.8209, "ref_ms": 16.6539, "cand_ms": 20.27288, "n_trials": 31, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0005, "r_wall_s": 89.65, "compile_s": 52.53, "r_error": "", "src_len": 7157, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79484, "tout": 3434, "ts": 1791522515.8136103, "chk": "ok", "code_len": 7199}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 83027, "tout": 3283, "ts": 1791522608.2266657, "chk": null, "code_len": 7157}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79484, "started": 1791522483.2783327}
{"ep": "ok-00082", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 23.7981, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 115.5, "calls": 2, "tokens_in": 14893, "tokens_out": 5763, "ctx_chars": 10255, "t_end": 1791522700.8173614, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 23.7981, "lo95": 22.6054, "mean": 23.1894, "ev_only": 24.2279, "ref_ms": 22.40987, "cand_ms": 0.94167, "n_trials": 74, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.8689, "r_wall_s": 52.17, "compile_s": 11.34, "r_error": "", "src_len": 2790, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6434, "tout": 4269, "ts": 1791522624.605342, "chk": "ok", "code_len": 2790}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8459, "tout": 1494, "ts": 1791522648.2395284, "chk": null, "code_len": 2790}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6434, "started": 1791522585.308567}
{"ep": "ok-00029", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9351, "speedup": 0.9351, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.6, "calls": 2, "tokens_in": 160423, "tokens_out": 4606, "ctx_chars": 182830, "t_end": 1791522700.9219406, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9351, "lo95": 0.931, "mean": 1.0732, "ev_only": 0.9389, "ref_ms": 4.07604, "cand_ms": 4.3589, "n_trials": 192, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0297, "r_wall_s": 124.79, "compile_s": 48.86, "r_error": "", "src_len": 4061, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78923, "tout": 2465, "ts": 1791522509.0169098, "chk": "ok", "code_len": 4251}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81500, "tout": 2141, "ts": 1791522576.1045227, "chk": null, "code_len": 4061}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78923, "started": 1791522483.2951677}
{"ep": "ok-00004", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 76.1003, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 220.8, "calls": 2, "tokens_in": 6942, "tokens_out": 8114, "ctx_chars": 495, "t_end": 1791522704.0354419, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 76.1003, "lo95": 73.8211, "mean": 77.1826, "ev_only": 84.732, "ref_ms": 22.32402, "cand_ms": 0.29335, "n_trials": 75, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 134.85, "compile_s": 14.87, "r_error": "", "src_len": 5064, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 5306, "ts": 1791522529.9320748, "chk": "ok", "code_len": 5064}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4980, "tout": 2808, "ts": 1791522568.9760926, "chk": null, "code_len": 5064}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791522483.278898}
{"ep": "ok-00063", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 221.3, "calls": 1, "tokens_in": 1723, "tokens_out": 1780, "ctx_chars": 0, "t_end": 1791522704.6368701, "error": "RuntimeError: Error building extension 'gn_hardtanh_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_hardtanh_mod -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": 67.94, "compile_s": 67.93, "r_error": "RuntimeError: Error building extension 'gn_hardtanh_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_hardtanh_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/", "src_len": 3661, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1723, "tout": 1780, "ts": 1791522500.6840656, "chk": null, "code_len": 3661}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1723, "started": 1791522483.3174539}
{"ep": "ok-00017", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.4589, "speedup": 0.4589, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 231.5, "calls": 3, "tokens_in": 23927, "tokens_out": 20161, "ctx_chars": 0, "t_end": 1791522714.7605784, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4589, "lo95": 0.3265, "mean": 0.4036, "ev_only": 0.4584, "ref_ms": 5.46183, "cand_ms": 11.90155, "n_trials": 146, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3644, "r_wall_s": 35.37, "compile_s": 5.69, "r_error": "", "src_len": 9052, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 10019, "ts": 1791522568.3224158, "chk": "runtime_error", "code_len": 9076}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8120, "tout": 5255, "ts": 1791522615.4620566, "chk": "ok", "code_len": 9052}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13179, "tout": 4887, "ts": 1791522679.3592446, "chk": null, "code_len": 9052}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 2628, "started": 1791522483.2892232}
{"ep": "ok-00044", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9427, "speedup": 0.9427, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 233.0, "calls": 5, "tokens_in": 60912, "tokens_out": 13536, "ctx_chars": 6513, "t_end": 1791522716.2842076, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9427, "lo95": 0.7949, "mean": 0.9699, "ev_only": 0.9418, "ref_ms": 29.09375, "cand_ms": 30.86151, "n_trials": 26, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0541, "r_wall_s": 43.18, "compile_s": 2.42, "r_error": "", "src_len": 4348, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 2770, "ts": 1791522507.4474401, "chk": "incorrect", "code_len": 5763}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8523, "tout": 3086, "ts": 1791522542.1072798, "chk": "incorrect", "code_len": 6084}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11743, "tout": 5590, "ts": 1791522603.0005949, "chk": "ok", "code_len": 4348}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 17442, "tout": 95, "ts": 1791522656.8424451, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 17584, "tout": 1995, "ts": 1791522673.074038, "chk": null, "code_len": 4348}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5620, "started": 1791522483.3044703}
{"ep": "ok-00012", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.037, "speedup": 1.037, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.2, "calls": 2, "tokens_in": 15548, "tokens_out": 2556, "ctx_chars": 12848, "t_end": 1791522720.5077996, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.037, "lo95": 1.0355, "mean": 1.0348, "ev_only": 1.0372, "ref_ms": 8.22822, "cand_ms": 7.9344, "n_trials": 79, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0019, "r_wall_s": 66.35, "compile_s": 33.71, "r_error": "", "src_len": 1553, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7155, "tout": 1683, "ts": 1791522500.249845, "chk": "ok", "code_len": 1553}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8393, "tout": 873, "ts": 1791522654.0531528, "chk": null, "code_len": 1553}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7155, "started": 1791522483.2852674}
{"ep": "ok-00045", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.4909, "speedup": 0.4909, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.5, "calls": 2, "tokens_in": 11874, "tokens_out": 21051, "ctx_chars": 495, "t_end": 1791522720.8523319, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4909, "lo95": 0.4866, "mean": 0.4724, "ev_only": 0.4888, "ref_ms": 6.67861, "cand_ms": 13.60548, "n_trials": 159, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4341, "r_wall_s": 48.14, "compile_s": 2.83, "r_error": "", "src_len": 10799, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2761, "tout": 15398, "ts": 1791522618.322477, "chk": "ok", "code_len": 10799}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9113, "tout": 5653, "ts": 1791522672.6797833, "chk": null, "code_len": 10799}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2761, "started": 1791522483.304553}
{"ep": "ok-00081", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.035, "speedup": 1.035, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 138.5, "calls": 3, "tokens_in": 21688, "tokens_out": 2739, "ctx_chars": 9546, "t_end": 1791522722.0662642, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.035, "lo95": 1.034, "mean": 1.0343, "ev_only": 1.0353, "ref_ms": 8.24386, "cand_ms": 7.96511, "n_trials": 66, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 70.98, "compile_s": 32.57, "r_error": "", "src_len": 1802, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5935, "tout": 1791, "ts": 1791522600.431377, "chk": "ok", "code_len": 1802}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7838, "tout": 53, "ts": 1791522643.0968406, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7915, "tout": 895, "ts": 1791522650.9215767, "chk": null, "code_len": 1802}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5935, "started": 1791522583.6065938}
{"ep": "ok-00037", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0233, "speedup": 1.0233, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 259.0, "calls": 2, "tokens_in": 163517, "tokens_out": 11977, "ctx_chars": 182830, "t_end": 1791522742.3147037, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0233, "lo95": 1.0178, "mean": 1.0237, "ev_only": 1.0236, "ref_ms": 16.53447, "cand_ms": 16.15819, "n_trials": 78, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0648, "r_wall_s": 102.5, "compile_s": 67.32, "r_error": "", "src_len": 8224, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79486, "tout": 7129, "ts": 1791522544.7310593, "chk": "ok", "code_len": 8287}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 84031, "tout": 4848, "ts": 1791522639.7024543, "chk": null, "code_len": 8224}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79486, "started": 1791522483.3012393}
{"ep": "ok-00027", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9826, "speedup": 0.9826, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.6, "calls": 2, "tokens_in": 163376, "tokens_out": 11696, "ctx_chars": 182830, "t_end": 1791522743.9129663, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9826, "lo95": 0.9768, "mean": 0.9862, "ev_only": 0.9826, "ref_ms": 16.20066, "cand_ms": 16.48797, "n_trials": 40, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.075, "r_wall_s": 102.03, "compile_s": 74.14, "r_error": "", "src_len": 8562, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79486, "tout": 6680, "ts": 1791522543.3048854, "chk": "ok", "code_len": 8503}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 83890, "tout": 5016, "ts": 1791522641.7704115, "chk": null, "code_len": 8562}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79486, "started": 1791522483.2952404}
{"ep": "ok-00039", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.7661, "speedup": 0.7661, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.5, "calls": 4, "tokens_in": 36018, "tokens_out": 20050, "ctx_chars": 495, "t_end": 1791522744.8177345, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7661, "lo95": 0.7608, "mean": 0.7209, "ev_only": 0.7674, "ref_ms": 17.22214, "cand_ms": 22.48026, "n_trials": 76, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0334, "r_wall_s": 32.25, "compile_s": 14.53, "r_error": "", "src_len": 3780, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3052, "tout": 9822, "ts": 1791522572.5529583, "chk": "incorrect", "code_len": 7768}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7355, "tout": 5322, "ts": 1791522632.6035407, "chk": "incorrect", "code_len": 8079}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11737, "tout": 2680, "ts": 1791522677.271422, "chk": "ok", "code_len": 3780}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13874, "tout": 2226, "ts": 1791522712.4943144, "chk": null, "code_len": 3780}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 3052, "started": 1791522483.301295}
{"ep": "ok-00016", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0022, "speedup": 1.0022, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 263.4, "calls": 5, "tokens_in": 405403, "tokens_out": 5861, "ctx_chars": 182830, "t_end": 1791522746.64231, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0022, "lo95": 1.0018, "mean": 1.0022, "ev_only": 1.0045, "ref_ms": 7.91286, "cand_ms": 7.89527, "n_trials": 117, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 90.69, "compile_s": 42.71, "r_error": "", "src_len": 900, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78248, "tout": 1055, "ts": 1791522496.3035026, "chk": "incorrect", "code_len": 1741}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 79436, "tout": 1589, "ts": 1791522535.7871165, "chk": "incorrect", "code_len": 1830}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 81158, "tout": 1223, "ts": 1791522560.9748573, "chk": "ok", "code_len": 912}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 82490, "tout": 1449, "ts": 1791522631.0340345, "chk": "ok", "code_len": 900}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 84071, "tout": 545, "ts": 1791522655.8445115, "chk": null, "code_len": 900}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "ok", null], "first_tin": 78248, "started": 1791522483.2878947}
{"ep": "ok-00061", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 6.5371, "speedup": 6.5371, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 263.9, "calls": 2, "tokens_in": 12557, "tokens_out": 20562, "ctx_chars": 2713, "t_end": 1791522747.2071915, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 6.5371, "lo95": 5.0478, "mean": 5.8722, "ev_only": 6.4902, "ref_ms": 5.62146, "cand_ms": 0.85994, "n_trials": 185, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 74.39, "compile_s": 21.15, "r_error": "", "src_len": 11062, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3326, "tout": 15218, "ts": 1791522616.8499732, "chk": "ok", "code_len": 11148}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9231, "tout": 5344, "ts": 1791522672.7888272, "chk": null, "code_len": 11062}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3326, "started": 1791522483.3168495}
{"ep": "ok-00062", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0286, "speedup": 1.0286, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 288.2, "calls": 2, "tokens_in": 5430, "tokens_out": 2628, "ctx_chars": 768, "t_end": 1791522771.5343864, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0286, "lo95": 1.0282, "mean": 1.0743, "ev_only": 1.028, "ref_ms": 8.15385, "cand_ms": 7.92678, "n_trials": 146, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0044, "r_wall_s": 84.63, "compile_s": 16.49, "r_error": "", "src_len": 1885, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2026, "tout": 1590, "ts": 1791522498.0338297, "chk": "ok", "code_len": 1885}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3404, "tout": 1038, "ts": 1791522686.8155255, "chk": null, "code_len": 1885}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2026, "started": 1791522483.316502}
{"ep": "ok-00102", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0232, "speedup": 1.0232, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 71.0, "calls": 3, "tokens_in": 20053, "tokens_out": 1834, "ctx_chars": 9950, "t_end": 1791522771.8113716, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0232, "lo95": 1.022, "mean": 1.054, "ev_only": 1.0258, "ref_ms": 8.2182, "cand_ms": 8.03172, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0061, "r_wall_s": 26.76, "compile_s": 1.89, "r_error": "", "src_len": 1848, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5980, "tout": 926, "ts": 1791522709.130332, "chk": "ok", "code_len": 1848}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7018, "tout": 13, "ts": 1791522737.3726444, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7055, "tout": 895, "ts": 1791522744.9592812, "chk": null, "code_len": 1848}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5980, "started": 1791522700.817684}
{"ep": "ok-00073", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.005, "speedup": 1.005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 229.0, "calls": 2, "tokens_in": 15306, "tokens_out": 5540, "ctx_chars": 10823, "t_end": 1791522775.8172796, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.005, "lo95": 0.9991, "mean": 1.0036, "ev_only": 1.0044, "ref_ms": 8.08895, "cand_ms": 8.04874, "n_trials": 131, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0119, "r_wall_s": 54.14, "compile_s": 17.12, "r_error": "", "src_len": 3771, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 3621, "ts": 1791522615.5354207, "chk": "ok", "code_len": 3936}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8942, "tout": 1919, "ts": 1791522721.6033003, "chk": null, "code_len": 3771}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6364, "started": 1791522567.163656}
{"ep": "ok-00083", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.549, "speedup": 0.549, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 199.1, "calls": 2, "tokens_in": 13575, "tokens_out": 9667, "ctx_chars": 5888, "t_end": 1791522795.584123, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.549, "lo95": 0.5473, "mean": 0.5452, "ev_only": 0.5481, "ref_ms": 3.2456, "cand_ms": 5.91145, "n_trials": 212, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3261, "r_wall_s": 68.14, "compile_s": 17.09, "r_error": "", "src_len": 5748, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5062, "tout": 6653, "ts": 1791522654.074369, "chk": "ok", "code_len": 5748}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8513, "tout": 3014, "ts": 1791522727.420691, "chk": null, "code_len": 5748}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5062, "started": 1791522596.5245116}
{"ep": "ok-00000", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.2525, "speedup": 1.2525, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 314.1, "calls": 2, "tokens_in": 12588, "tokens_out": 21942, "ctx_chars": 0, "t_end": 1791522797.3774645, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.2525, "lo95": 1.2497, "mean": 1.2208, "ev_only": 1.2509, "ref_ms": 3.35697, "cand_ms": 2.68018, "n_trials": 196, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4754, "r_wall_s": 98.24, "compile_s": 23.2, "r_error": "", "src_len": 14114, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 15166, "ts": 1791522633.2236342, "chk": "ok", "code_len": 14114}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9960, "tout": 6776, "ts": 1791522699.1104617, "chk": null, "code_len": 14114}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791522503.6441045}
{"ep": "ok-00028", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.8989, "speedup": 0.8989, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 323.8, "calls": 5, "tokens_in": 55478, "tokens_out": 12132, "ctx_chars": 5802, "t_end": 1791522807.1079402, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8989, "lo95": 0.8869, "mean": 0.9596, "ev_only": 0.898, "ref_ms": 33.55272, "cand_ms": 37.32746, "n_trials": 49, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.034, "r_wall_s": 35.25, "compile_s": 2.84, "r_error": "", "src_len": 3686, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 2857, "ts": 1791522508.0574784, "chk": "incorrect", "code_len": 5988}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8321, "tout": 2719, "ts": 1791522543.3503582, "chk": "incorrect", "code_len": 5650}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11173, "tout": 3034, "ts": 1791522579.39337, "chk": "incorrect", "code_len": 5805}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 14339, "tout": 1843, "ts": 1791522721.268356, "chk": "ok", "code_len": 3686}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 16314, "tout": 1679, "ts": 1791522771.838996, "chk": null, "code_len": 3686}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 5331, "started": 1791522483.2945416}
{"ep": "ok-00074", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0899, "speedup": 1.0899, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.9, "calls": 3, "tokens_in": 25395, "tokens_out": 2057, "ctx_chars": 12888, "t_end": 1791522816.308095, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0899, "lo95": 1.0891, "mean": 1.1232, "ev_only": 1.0888, "ref_ms": 22.44057, "cand_ms": 20.59024, "n_trials": 60, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0339, "r_wall_s": 60.22, "compile_s": 3.19, "r_error": "", "src_len": 2071, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7684, "tout": 1041, "ts": 1791522565.2945335, "chk": "ok", "code_len": 2071}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8837, "tout": 13, "ts": 1791522747.309451, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8874, "tout": 1003, "ts": 1791522755.677556, "chk": null, "code_len": 2071}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7684, "started": 1791522555.4109957}
{"ep": "ok-00086", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0242, "speedup": 1.0242, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 208.6, "calls": 3, "tokens_in": 12634, "tokens_out": 1854, "ctx_chars": 4565, "t_end": 1791522819.821208, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0242, "lo95": 1.0238, "mean": 1.0245, "ev_only": 1.0248, "ref_ms": 8.147, "cand_ms": 7.95474, "n_trials": 170, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0072, "r_wall_s": 135.59, "compile_s": 16.98, "r_error": "", "src_len": 1812, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3499, "tout": 938, "ts": 1791522649.3347816, "chk": "ok", "code_len": 1812}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4549, "tout": 13, "ts": 1791522676.4310925, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4586, "tout": 903, "ts": 1791522684.1580925, "chk": null, "code_len": 1812}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3499, "started": 1791522631.7196872}
{"ep": "ok-00080", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7994, "speedup": 0.7994, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 246.6, "calls": 2, "tokens_in": 11904, "tokens_out": 1344, "ctx_chars": 8224, "t_end": 1791522820.8988988, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7994, "lo95": 0.7962, "mean": 0.8329, "ev_only": 0.7994, "ref_ms": 31.8315, "cand_ms": 39.81826, "n_trials": 39, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 102.96, "compile_s": 17.74, "r_error": "", "src_len": 963, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 809, "ts": 1791522588.084905, "chk": "ok", "code_len": 963}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6411, "tout": 535, "ts": 1791522717.914422, "chk": null, "code_len": 963}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5493, "started": 1791522574.3080082}
{"ep": "ok-00057", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 10.7045, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 363.1, "calls": 3, "tokens_in": 29485, "tokens_out": 22752, "ctx_chars": 7992, "t_end": 1791522846.4371994, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 10.7045, "lo95": 10.2808, "mean": 13.0685, "ev_only": 10.8452, "ref_ms": 50.13448, "cand_ms": 4.6835, "n_trials": 32, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 82.59, "compile_s": 15.7, "r_error": "", "src_len": 8169, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 13520, "ts": 1791522605.1129923, "chk": "no_custom_kernel", "code_len": 8228}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9936, "tout": 4877, "ts": 1791522678.2233965, "chk": "ok", "code_len": 8169}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14218, "tout": 4355, "ts": 1791522763.822018, "chk": null, "code_len": 8169}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5331, "started": 1791522483.311115}
{"ep": "ok-00015", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.4471, "speedup": 1.4471, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 366.4, "calls": 2, "tokens_in": 12605, "tokens_out": 24687, "ctx_chars": 0, "t_end": 1791522849.707731, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4471, "lo95": 1.443, "mean": 1.542, "ev_only": 1.4502, "ref_ms": 3.43472, "cand_ms": 2.37347, "n_trials": 196, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4623, "r_wall_s": 145.19, "compile_s": 22.73, "r_error": "", "src_len": 13301, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 17819, "ts": 1791522637.8797748, "chk": "ok", "code_len": 13345}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9977, "tout": 6868, "ts": 1791522704.4867985, "chk": null, "code_len": 13301}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791522483.2879155}
{"ep": "ok-00112", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0279, "speedup": 1.0279, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 107.1, "calls": 3, "tokens_in": 25357, "tokens_out": 2718, "ctx_chars": 12848, "t_end": 1791522850.978513, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0279, "lo95": 1.0262, "mean": 0.9953, "ev_only": 1.0313, "ref_ms": 8.41136, "cand_ms": 8.18329, "n_trials": 147, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0048, "r_wall_s": 62.71, "compile_s": 16.12, "r_error": "", "src_len": 1779, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7153, "tout": 1795, "ts": 1791522760.039034, "chk": "ok", "code_len": 1779}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9060, "tout": 60, "ts": 1791522780.7891502, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9144, "tout": 863, "ts": 1791522788.232098, "chk": null, "code_len": 1779}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7153, "started": 1791522743.9133415}
{"ep": "ok-00093", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.1016, "speedup": 1.1016, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 211.3, "calls": 3, "tokens_in": 22803, "tokens_out": 2119, "ctx_chars": 11064, "t_end": 1791522855.3646047, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1016, "lo95": 1.101, "mean": 1.1315, "ev_only": 1.1007, "ref_ms": 22.25838, "cand_ms": 20.20547, "n_trials": 75, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0327, "r_wall_s": 127.4, "compile_s": 16.65, "r_error": "", "src_len": 2086, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6776, "tout": 1107, "ts": 1791522654.419356, "chk": "ok", "code_len": 2086}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7995, "tout": 13, "ts": 1791522719.3999305, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8032, "tout": 999, "ts": 1791522727.749237, "chk": null, "code_len": 2086}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6776, "started": 1791522644.1086295}
{"ep": "ok-00098", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 24.9015, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.7, "calls": 2, "tokens_in": 20564, "tokens_out": 7519, "ctx_chars": 16078, "t_end": 1791522857.7811618, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 24.9015, "lo95": 24.7728, "mean": 24.5191, "ev_only": 25.7776, "ref_ms": 22.43698, "cand_ms": 0.90103, "n_trials": 65, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 78.04, "compile_s": 17.89, "r_error": "", "src_len": 4311, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8865, "tout": 5319, "ts": 1791522750.1723278, "chk": "ok", "code_len": 4311}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11699, "tout": 2200, "ts": 1791522779.387264, "chk": null, "code_len": 4311}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 8865, "started": 1791522693.085139}
{"ep": "ok-00111", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 124.3, "calls": 1, "tokens_in": 1856, "tokens_out": 1820, "ctx_chars": 495, "t_end": 1791522866.5712187, "error": "RuntimeError: Error building extension 'gn_ht_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht_mod -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": 87.56, "compile_s": 87.54, "r_error": "RuntimeError: Error building extension 'gn_ht_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "src_len": 3703, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1856, "tout": 1820, "ts": 1791522778.9822612, "chk": null, "code_len": 3703}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1856, "started": 1791522762.6759937}
{"ep": "ok-00103", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0336, "speedup": 1.0336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 174.9, "calls": 3, "tokens_in": 17335, "tokens_out": 2665, "ctx_chars": 6481, "t_end": 1791522875.7793238, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0336, "lo95": 1.0328, "mean": 1.0705, "ev_only": 1.0337, "ref_ms": 8.27415, "cand_ms": 8.00546, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0049, "r_wall_s": 86.52, "compile_s": 18.72, "r_error": "", "src_len": 1838, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4520, "tout": 1757, "ts": 1791522716.9513392, "chk": "ok", "code_len": 1838}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6389, "tout": 13, "ts": 1791522781.5292804, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6426, "tout": 895, "ts": 1791522789.2346573, "chk": null, "code_len": 1838}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4520, "started": 1791522700.9223046}
{"ep": "ok-00107", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0265, "speedup": 1.0265, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.5, "calls": 2, "tokens_in": 4712, "tokens_out": 2341, "ctx_chars": 0, "t_end": 1791522880.8128936, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0265, "lo95": 1.0261, "mean": 1.0268, "ev_only": 1.0269, "ref_ms": 8.1887, "cand_ms": 7.97761, "n_trials": 131, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 87.69, "compile_s": 39.86, "r_error": "", "src_len": 1652, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 1470, "ts": 1791522728.49762, "chk": "ok", "code_len": 1652}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 2987, "tout": 871, "ts": 1791522793.0484824, "chk": null, "code_len": 1652}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791522716.2845163}
{"ep": "ok-00101", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9942, "speedup": 0.9942, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.0, "calls": 3, "tokens_in": 26080, "tokens_out": 2925, "ctx_chars": 14186, "t_end": 1791522884.8996856, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9942, "lo95": 0.9925, "mean": 0.9939, "ev_only": 0.9932, "ref_ms": 8.1131, "cand_ms": 8.16072, "n_trials": 112, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0099, "r_wall_s": 84.58, "compile_s": 47.55, "r_error": "", "src_len": 2885, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7602, "tout": 1479, "ts": 1791522715.2753582, "chk": "ok", "code_len": 3027}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9193, "tout": 68, "ts": 1791522789.0476031, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9285, "tout": 1378, "ts": 1791522800.2450314, "chk": null, "code_len": 2885}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7602, "started": 1791522697.9009893}
{"ep": "ok-00113", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0297, "speedup": 1.0297, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 151.8, "calls": 2, "tokens_in": 7211, "tokens_out": 4954, "ctx_chars": 2175, "t_end": 1791522896.6250224, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0297, "lo95": 1.0293, "mean": 1.0298, "ev_only": 1.0303, "ref_ms": 29.78052, "cand_ms": 28.92096, "n_trials": 40, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0212, "r_wall_s": 85.22, "compile_s": 2.86, "r_error": "", "src_len": 2888, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2546, "tout": 3090, "ts": 1791522772.1128905, "chk": "ok", "code_len": 2888}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4665, "tout": 1864, "ts": 1791522810.5445166, "chk": null, "code_len": 2888}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2546, "started": 1791522744.8182356}
{"ep": "ok-00095", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7683, "speedup": 0.7683, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 231.2, "calls": 3, "tokens_in": 10515, "tokens_out": 1761, "ctx_chars": 2270, "t_end": 1791522903.0664494, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7683, "lo95": 0.7476, "mean": 0.7455, "ev_only": 0.7683, "ref_ms": 48.49778, "cand_ms": 63.12611, "n_trials": 19, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 67.26, "compile_s": 15.61, "r_error": "", "src_len": 1452, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2738, "tout": 994, "ts": 1791522707.4779415, "chk": "ok", "code_len": 1452}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3841, "tout": 71, "ts": 1791522828.3342123, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3936, "tout": 696, "ts": 1791522835.696306, "chk": null, "code_len": 1452}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2738, "started": 1791522692.2834256}
{"ep": "ok-00123", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.025, "speedup": 1.025, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 84.4, "calls": 3, "tokens_in": 20940, "tokens_out": 1844, "ctx_chars": 10373, "t_end": 1791522904.2459195, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.025, "lo95": 1.0235, "mean": 1.0253, "ev_only": 1.0251, "ref_ms": 8.25479, "cand_ms": 8.05321, "n_trials": 137, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0065, "r_wall_s": 55.28, "compile_s": 20.23, "r_error": "", "src_len": 1854, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6268, "tout": 931, "ts": 1791522828.0923147, "chk": "ok", "code_len": 1854}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7311, "tout": 26, "ts": 1791522841.0521371, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7361, "tout": 887, "ts": 1791522848.7734668, "chk": null, "code_len": 1854}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6268, "started": 1791522819.8215363}
{"ep": "ok-00097", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.1575, "speedup": 0.1575, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.9, "calls": 4, "tokens_in": 31254, "tokens_out": 4804, "ctx_chars": 8224, "t_end": 1791522907.4362538, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.1575, "lo95": 0.1105, "mean": 0.1311, "ev_only": 0.1575, "ref_ms": 46.00294, "cand_ms": 292.12479, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2729, "r_wall_s": 63.87, "compile_s": 10.73, "r_error": "", "src_len": 2820, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 1860, "ts": 1791522712.8953173, "chk": "forbidden", "code_len": 2951}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7514, "tout": 1406, "ts": 1791522725.0262382, "chk": "ok", "code_len": 2820}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9032, "tout": 159, "ts": 1791522832.0293405, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9215, "tout": 1379, "ts": 1791522843.4540603, "chk": null, "code_len": 2820}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 5493, "started": 1791522689.580487}
{"ep": "ok-00109", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.2961, "speedup": 0.2961, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.8, "calls": 3, "tokens_in": 20908, "tokens_out": 4210, "ctx_chars": 7010, "t_end": 1791522908.6228547, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.2961, "lo95": 0.2923, "mean": 0.3326, "ev_only": 0.2964, "ref_ms": 3.3633, "cand_ms": 11.3577, "n_trials": 41, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0822, "r_wall_s": 77.93, "compile_s": 2.66, "r_error": "", "src_len": 4138, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5460, "tout": 2128, "ts": 1791522738.4447477, "chk": "ok", "code_len": 4195}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7700, "tout": 24, "ts": 1791522805.2442374, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7748, "tout": 2058, "ts": 1791522830.5844214, "chk": null, "code_len": 4138}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5460, "started": 1791522720.8526568}
{"ep": "ok-00064", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 7.2251, "speedup": 7.2251, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 413.9, "calls": 3, "tokens_in": 19730, "tokens_out": 20463, "ctx_chars": 696, "t_end": 1791522913.9848776, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.2251, "lo95": 7.1771, "mean": 7.7183, "ev_only": 7.223, "ref_ms": 31.89459, "cand_ms": 4.41443, "n_trials": 48, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9753, "r_wall_s": 122.73, "compile_s": 38.33, "r_error": "", "src_len": 7627, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2199, "tout": 12349, "ts": 1791522610.4061258, "chk": "no_custom_kernel", "code_len": 7706}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6769, "tout": 4261, "ts": 1791522675.9693244, "chk": "ok", "code_len": 7627}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10762, "tout": 3853, "ts": 1791522791.226403, "chk": null, "code_len": 7627}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2199, "started": 1791522500.1071281}
{"ep": "ok-00115", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.2954, "speedup": 0.2954, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 169.8, "calls": 3, "tokens_in": 19883, "tokens_out": 4115, "ctx_chars": 6059, "t_end": 1791522916.9843318, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.2954, "lo95": 0.2944, "mean": 0.3099, "ev_only": 0.2942, "ref_ms": 3.51006, "cand_ms": 11.88146, "n_trials": 139, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0738, "r_wall_s": 120.34, "compile_s": 41.41, "r_error": "", "src_len": 4023, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5136, "tout": 2094, "ts": 1791522764.643023, "chk": "ok", "code_len": 4134}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7342, "tout": 39, "ts": 1791522780.660453, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7405, "tout": 1982, "ts": 1791522796.6215792, "chk": null, "code_len": 4023}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5136, "started": 1791522747.2077055}
{"ep": "ok-00056", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 5.9022, "speedup": 5.9022, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 448.3, "calls": 3, "tokens_in": 30029, "tokens_out": 23860, "ctx_chars": 7644, "t_end": 1791522931.5927923, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 5.9022, "lo95": 5.8777, "mean": 5.9628, "ev_only": 5.8993, "ref_ms": 32.17441, "cand_ms": 5.45125, "n_trials": 50, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9907, "r_wall_s": 86.09, "compile_s": 24.73, "r_error": "", "src_len": 8790, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5260, "tout": 15087, "ts": 1791522622.1636114, "chk": "no_custom_kernel", "code_len": 8814}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10181, "tout": 4580, "ts": 1791522682.5410674, "chk": "ok", "code_len": 8790}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14588, "tout": 4193, "ts": 1791522845.391203, "chk": null, "code_len": 8790}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5260, "started": 1791522483.3097856}
{"ep": "ok-00108", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0341, "speedup": 1.0341, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.3, "calls": 2, "tokens_in": 11758, "tokens_out": 4582, "ctx_chars": 7221, "t_end": 1791522933.8262377, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0341, "lo95": 1.0336, "mean": 1.0338, "ev_only": 1.0338, "ref_ms": 29.72277, "cand_ms": 28.74269, "n_trials": 48, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0254, "r_wall_s": 159.54, "compile_s": 9.42, "r_error": "", "src_len": 2797, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4831, "tout": 2986, "ts": 1791522746.6392357, "chk": "ok", "code_len": 2797}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6927, "tout": 1596, "ts": 1791522773.7820337, "chk": null, "code_len": 2797}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4831, "started": 1791522720.50817}
{"ep": "ok-00094", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7912, "speedup": 0.7912, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 271.9, "calls": 3, "tokens_in": 16721, "tokens_out": 5295, "ctx_chars": 2169, "t_end": 1791522934.9558518, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7912, "lo95": 0.7888, "mean": 0.7962, "ev_only": 0.792, "ref_ms": 4.0341, "cand_ms": 5.09887, "n_trials": 192, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.069, "r_wall_s": 63.32, "compile_s": 33.1, "r_error": "", "src_len": 3537, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3083, "tout": 3599, "ts": 1791522698.1995065, "chk": "ok", "code_len": 3537}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6794, "tout": 26, "ts": 1791522857.6094556, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6844, "tout": 1670, "ts": 1791522871.5191703, "chk": null, "code_len": 3537}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3083, "started": 1791522663.0908492}
{"ep": "ok-00088", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.4971, "speedup": 1.4971, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 308.5, "calls": 4, "tokens_in": 51070, "tokens_out": 12877, "ctx_chars": 16078, "t_end": 1791522938.0846882, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4971, "lo95": 1.4965, "mean": 1.4948, "ev_only": 1.4971, "ref_ms": 22.26098, "cand_ms": 14.8696, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 88.64, "compile_s": 21.55, "r_error": "", "src_len": 4398, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8865, "tout": 5253, "ts": 1791522694.5706556, "chk": "runtime_error", "code_len": 4174}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11653, "tout": 2576, "ts": 1791522747.218284, "chk": "ok", "code_len": 4405}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 14052, "tout": 2724, "ts": 1791522781.5672898, "chk": "ok", "code_len": 4398}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 16500, "tout": 2324, "ts": 1791522849.1470675, "chk": null, "code_len": 4398}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "ok", null], "first_tin": 8865, "started": 1791522629.5452974}
{"ep": "ok-00066", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 9.9371, "speedup": 9.9371, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 418.5, "calls": 2, "tokens_in": 164618, "tokens_out": 22649, "ctx_chars": 182830, "t_end": 1791522939.2285764, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 9.9371, "lo95": 9.9035, "mean": 9.9977, "ev_only": 10.2195, "ref_ms": 3.94358, "cand_ms": 0.39685, "n_trials": 190, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0909, "r_wall_s": 140.03, "compile_s": 93.23, "r_error": "", "src_len": 12948, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78925, "tout": 15995, "ts": 1791522657.2138243, "chk": "ok", "code_len": 13001}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 85693, "tout": 6654, "ts": 1791522799.1702552, "chk": null, "code_len": 12948}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78925, "started": 1791522520.7317104}
{"ep": "ok-00085", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 7.0375, "speedup": 7.0375, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 340.3, "calls": 2, "tokens_in": 6730, "tokens_out": 9342, "ctx_chars": 0, "t_end": 1791522941.341395, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.0375, "lo95": 7.0321, "mean": 7.017, "ev_only": 7.058, "ref_ms": 8.25049, "cand_ms": 1.17236, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9958, "r_wall_s": 164.51, "compile_s": 17.72, "r_error": "", "src_len": 4492, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 6624, "ts": 1791522660.7215636, "chk": "ok", "code_len": 4492}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4928, "tout": 2718, "ts": 1791522776.8072562, "chk": null, "code_len": 4492}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791522601.0740256}
{"ep": "ok-00067", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0061, "speedup": 1.0061, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 417.6, "calls": 2, "tokens_in": 12097, "tokens_out": 4845, "ctx_chars": 7549, "t_end": 1791522947.4143362, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0061, "lo95": 1.0059, "mean": 1.006, "ev_only": 1.0046, "ref_ms": 8.06375, "cand_ms": 8.01488, "n_trials": 181, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0135, "r_wall_s": 60.89, "compile_s": 2.72, "r_error": "", "src_len": 3791, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4870, "tout": 2912, "ts": 1791522554.2586434, "chk": "ok", "code_len": 3791}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7227, "tout": 1933, "ts": 1791522752.2821195, "chk": null, "code_len": 3791}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4870, "started": 1791522529.861247}
{"ep": "ok-00054", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0038, "speedup": 1.0038, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 468.5, "calls": 4, "tokens_in": 17875, "tokens_out": 9878, "ctx_chars": 0, "t_end": 1791522951.7802815, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0038, "lo95": 1.0036, "mean": 1.0036, "ev_only": 1.0044, "ref_ms": 7.91819, "cand_ms": 7.88819, "n_trials": 178, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0003, "r_wall_s": 106.55, "compile_s": 21.69, "r_error": "", "src_len": 1522, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 3090, "ts": 1791522511.2825274, "chk": "incorrect", "code_len": 3454}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3912, "tout": 3682, "ts": 1791522575.448961, "chk": "incorrect", "code_len": 2171}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5532, "tout": 2125, "ts": 1791522726.3428664, "chk": "ok", "code_len": 1522}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6748, "tout": 981, "ts": 1791522845.1247134, "chk": null, "code_len": 1522}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1683, "started": 1791522483.3095715}
{"ep": "ok-00035", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 6.7208, "speedup": 6.7208, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 469.8, "calls": 3, "tokens_in": 28517, "tokens_out": 31708, "ctx_chars": 2713, "t_end": 1791522953.0926604, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 6.7208, "lo95": 6.7011, "mean": 6.7501, "ev_only": 6.8457, "ref_ms": 3.93498, "cand_ms": 0.58549, "n_trials": 179, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9927, "r_wall_s": 99.5, "compile_s": 38.99, "r_error": "", "src_len": 11379, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3326, "tout": 20196, "ts": 1791522659.1581469, "chk": "no_custom_kernel", "code_len": 11563}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9716, "tout": 5922, "ts": 1791522772.3423688, "chk": "ok", "code_len": 11379}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15475, "tout": 5590, "ts": 1791522853.4839232, "chk": null, "code_len": 11379}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 3326, "started": 1791522483.2995305}
{"ep": "ok-00033", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0049, "speedup": 1.0049, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 472.4, "calls": 4, "tokens_in": 322583, "tokens_out": 10962, "ctx_chars": 182830, "t_end": 1791522955.6919262, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0049, "lo95": 1.0046, "mean": 1.0049, "ev_only": 1.0043, "ref_ms": 7.91354, "cand_ms": 7.87528, "n_trials": 140, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0003, "r_wall_s": 114.0, "compile_s": 61.74, "r_error": "", "src_len": 1593, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78250, "tout": 3514, "ts": 1791522518.7148616, "chk": "incorrect", "code_len": 2793}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 80121, "tout": 4161, "ts": 1791522624.4557812, "chk": "incorrect", "code_len": 2129}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 81533, "tout": 1854, "ts": 1791522730.1778834, "chk": "ok", "code_len": 1593}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 82679, "tout": 1433, "ts": 1791522841.5826209, "chk": null, "code_len": 1593}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 78250, "started": 1791522483.2978652}
{"ep": "ok-00001", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 7.6973, "speedup": 7.6973, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 474.4, "calls": 3, "tokens_in": 21415, "tokens_out": 27334, "ctx_chars": 495, "t_end": 1791522957.6962829, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.6973, "lo95": 7.6867, "mean": 7.6719, "ev_only": 7.7213, "ref_ms": 31.83025, "cand_ms": 4.13525, "n_trials": 48, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9923, "r_wall_s": 93.37, "compile_s": 48.28, "r_error": "", "src_len": 9412, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2084, "tout": 17207, "ts": 1791522638.821052, "chk": "no_custom_kernel", "code_len": 9436}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7261, "tout": 5258, "ts": 1791522706.8192272, "chk": "ok", "code_len": 9412}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12070, "tout": 4869, "ts": 1791522864.2206385, "chk": null, "code_len": 9412}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2084, "started": 1791522483.2776632}
{"ep": "ok-00070", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9988, "speedup": 0.9988, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 435.4, "calls": 5, "tokens_in": 42825, "tokens_out": 3545, "ctx_chars": 12555, "t_end": 1791522968.030196, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9988, "lo95": 0.9984, "mean": 0.9992, "ev_only": 0.9974, "ref_ms": 7.94325, "cand_ms": 7.95278, "n_trials": 181, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 18.47, "compile_s": 2.66, "r_error": "", "src_len": 927, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6871, "tout": 620, "ts": 1791522538.9044714, "chk": "incorrect", "code_len": 1087}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7624, "tout": 734, "ts": 1791522556.5889635, "chk": "incorrect", "code_len": 935}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8491, "tout": 828, "ts": 1791522763.0171354, "chk": "incorrect", "code_len": 1013}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9452, "tout": 803, "ts": 1791522787.7899258, "chk": "ok", "code_len": 927}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 10387, "tout": 560, "ts": 1791522949.5107887, "chk": null, "code_len": 927}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 6871, "started": 1791522532.58962}
{"ep": "ok-00140", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0249, "speedup": 1.0249, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 54.4, "calls": 1, "tokens_in": 5935, "tokens_out": 3000, "ctx_chars": 9546, "t_end": 1791522971.3834198, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0249, "lo95": 1.0238, "mean": 1.0168, "ev_only": 1.0312, "ref_ms": 8.28092, "cand_ms": 8.07948, "n_trials": 158, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0049, "r_wall_s": 28.0, "compile_s": 2.07, "r_error": "", "src_len": 1773, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5935, "tout": 3000, "ts": 1791522943.3424666, "chk": null, "code_len": 1773}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5935, "started": 1791522916.9846134}
{"ep": "ok-00134", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0928, "speedup": 1.0928, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 75.9, "calls": 1, "tokens_in": 7259, "tokens_out": 1085, "ctx_chars": 12103, "t_end": 1791522972.5072634, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0928, "lo95": 1.0873, "mean": 1.0919, "ev_only": 1.0909, "ref_ms": 22.37865, "cand_ms": 20.47885, "n_trials": 75, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0328, "r_wall_s": 65.78, "compile_s": 3.07, "r_error": "", "src_len": 2107, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7259, "tout": 1085, "ts": 1791522906.5243912, "chk": null, "code_len": 2107}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7259, "started": 1791522896.6253443}
{"ep": "ok-00032", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9925, "speedup": 0.9925, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 493.1, "calls": 4, "tokens_in": 335688, "tokens_out": 13649, "ctx_chars": 182830, "t_end": 1791522976.4149857, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9925, "lo95": 0.9923, "mean": 0.9928, "ev_only": 0.9932, "ref_ms": 8.02673, "cand_ms": 8.08729, "n_trials": 188, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0227, "r_wall_s": 124.03, "compile_s": 20.99, "r_error": "", "src_len": 4427, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78172, "tout": 4092, "ts": 1791522524.271259, "chk": "incorrect", "code_len": 6692}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 82397, "tout": 3497, "ts": 1791522567.0544956, "chk": "ok", "code_len": 6410}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 86006, "tout": 2997, "ts": 1791522782.6694846, "chk": "ok", "code_len": 4427}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 89113, "tout": 3063, "ts": 1791522852.2274277, "chk": null, "code_len": 4427}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", null], "first_tin": 78172, "started": 1791522483.2960522}
{"ep": "ok-00122", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9491, "speedup": 0.9491, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.2, "calls": 1, "tokens_in": 2489, "tokens_out": 4195, "ctx_chars": 495, "t_end": 1791522977.4952312, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9491, "lo95": 0.9186, "mean": 1.1004, "ev_only": 0.9475, "ref_ms": 4.11525, "cand_ms": 4.33601, "n_trials": 222, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0265, "r_wall_s": 113.31, "compile_s": 75.52, "r_error": "", "src_len": 3267, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2489, "tout": 4195, "ts": 1791522863.9417214, "chk": null, "code_len": 3267}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2489, "started": 1791522816.308417}
{"ep": "ok-00133", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0359, "speedup": 1.0359, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 93.3, "calls": 2, "tokens_in": 10088, "tokens_out": 2570, "ctx_chars": 5518, "t_end": 1791522978.2448797, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0359, "lo95": 1.0352, "mean": 1.0347, "ev_only": 1.0367, "ref_ms": 8.26199, "cand_ms": 7.97563, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0035, "r_wall_s": 58.0, "compile_s": 3.92, "r_error": "", "src_len": 1487, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4076, "tout": 1824, "ts": 1791522902.8199859, "chk": "ok", "code_len": 1487}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6012, "tout": 746, "ts": 1791522920.2162433, "chk": null, "code_len": 1487}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4076, "started": 1791522884.9000502}
{"ep": "ok-00125", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9384, "speedup": 0.9384, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 132.1, "calls": 2, "tokens_in": 19313, "tokens_out": 5357, "ctx_chars": 15603, "t_end": 1791522978.4902904, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9384, "lo95": 0.9374, "mean": 0.9392, "ev_only": 0.9385, "ref_ms": 29.73137, "cand_ms": 31.68146, "n_trials": 48, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0187, "r_wall_s": 73.7, "compile_s": 2.0, "r_error": "", "src_len": 3128, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8530, "tout": 3518, "ts": 1791522876.9069204, "chk": "ok", "code_len": 3128}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10783, "tout": 1839, "ts": 1791522903.968419, "chk": null, "code_len": 3128}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 8530, "started": 1791522846.4375541}
{"ep": "ok-00092", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0351, "speedup": 1.0351, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 339.6, "calls": 4, "tokens_in": 19672, "tokens_out": 2852, "ctx_chars": 3968, "t_end": 1791522981.1291213, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0351, "lo95": 1.0348, "mean": 1.0456, "ev_only": 1.0347, "ref_ms": 8.21434, "cand_ms": 7.93596, "n_trials": 195, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0044, "r_wall_s": 135.55, "compile_s": 18.89, "r_error": "", "src_len": 1854, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3392, "tout": 974, "ts": 1791522651.617242, "chk": "runtime_error", "code_len": 1820}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4709, "tout": 946, "ts": 1791522741.8097079, "chk": "ok", "code_len": 1854}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5767, "tout": 13, "ts": 1791522804.682352, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5804, "tout": 919, "ts": 1791522845.4775763, "chk": null, "code_len": 1854}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 3392, "started": 1791522641.5611103}
{"ep": "ok-00099", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0026, "speedup": 1.0026, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 286.4, "calls": 4, "tokens_in": 36052, "tokens_out": 9421, "ctx_chars": 12555, "t_end": 1791522981.5669618, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0026, "lo95": 1.0024, "mean": 1.0025, "ev_only": 1.0048, "ref_ms": 7.9089, "cand_ms": 7.88825, "n_trials": 179, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 52.55, "compile_s": 5.96, "r_error": "", "src_len": 982, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6873, "tout": 1931, "ts": 1791522713.780919, "chk": "incorrect", "code_len": 1521}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8156, "tout": 3348, "ts": 1791522811.11906, "chk": "incorrect", "code_len": 2524}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9945, "tout": 3228, "ts": 1791522857.2560325, "chk": "ok", "code_len": 982}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11078, "tout": 914, "ts": 1791522928.9958906, "chk": null, "code_len": 982}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6873, "started": 1791522695.1835957}
{"ep": "ok-00106", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.2954, "speedup": 0.2954, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 268.5, "calls": 3, "tokens_in": 20075, "tokens_out": 4108, "ctx_chars": 6417, "t_end": 1791522983.2637372, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.2954, "lo95": 0.2946, "mean": 0.2957, "ev_only": 0.294, "ref_ms": 3.3077, "cand_ms": 11.19564, "n_trials": 124, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.08, "r_wall_s": 109.58, "compile_s": 32.01, "r_error": "", "src_len": 4040, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5212, "tout": 2089, "ts": 1791522731.79011, "chk": "ok", "code_len": 4084}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7413, "tout": 13, "ts": 1791522857.4557025, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7450, "tout": 2006, "ts": 1791522873.335585, "chk": null, "code_len": 4040}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5212, "started": 1791522714.7609363}
{"ep": "ok-00072", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.003, "speedup": 1.003, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 451.2, "calls": 4, "tokens_in": 35812, "tokens_out": 8147, "ctx_chars": 12555, "t_end": 1791522984.7466664, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.003, "lo95": 1.0023, "mean": 1.0008, "ev_only": 1.0044, "ref_ms": 7.90416, "cand_ms": 7.88078, "n_trials": 167, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0004, "r_wall_s": 59.49, "compile_s": 5.88, "r_error": "", "src_len": 966, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6873, "tout": 2555, "ts": 1791522556.0363963, "chk": "incorrect", "code_len": 2086}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8469, "tout": 3420, "ts": 1791522772.767585, "chk": "incorrect", "code_len": 1102}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9778, "tout": 1349, "ts": 1791522836.0781395, "chk": "ok", "code_len": 966}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10692, "tout": 823, "ts": 1791522925.2337153, "chk": null, "code_len": 966}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6873, "started": 1791522533.5357268}
{"ep": "ok-00079", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0002, "speedup": 1.0002, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 431.1, "calls": 5, "tokens_in": 28095, "tokens_out": 3471, "ctx_chars": 5534, "t_end": 1791522999.7391472, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0002, "lo95": 0.9989, "mean": 0.9951, "ev_only": 0.999, "ref_ms": 7.97838, "cand_ms": 7.97701, "n_trials": 132, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 32.3, "compile_s": 3.29, "r_error": "", "src_len": 922, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3925, "tout": 597, "ts": 1791522584.3696213, "chk": "incorrect", "code_len": 1074}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4655, "tout": 794, "ts": 1791522715.6340022, "chk": "incorrect", "code_len": 1162}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5582, "tout": 865, "ts": 1791522790.0355048, "chk": "incorrect", "code_len": 991}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 6580, "tout": 641, "ts": 1791522948.8608603, "chk": "ok", "code_len": 922}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7353, "tout": 574, "ts": 1791522967.3742342, "chk": null, "code_len": 922}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 3925, "started": 1791522568.6354048}
{"ep": "ok-00104", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0395, "speedup": 1.0395, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 299.0, "calls": 3, "tokens_in": 8309, "tokens_out": 2468, "ctx_chars": 0, "t_end": 1791523003.040992, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0395, "lo95": 1.0376, "mean": 1.0387, "ev_only": 1.0365, "ref_ms": 8.27066, "cand_ms": 7.95602, "n_trials": 146, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0047, "r_wall_s": 165.95, "compile_s": 62.1, "r_error": "", "src_len": 2276, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1800, "tout": 1324, "ts": 1791522717.3206782, "chk": "ok", "code_len": 2293}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3236, "tout": 13, "ts": 1791522827.2862139, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3273, "tout": 1131, "ts": 1791522836.9760458, "chk": null, "code_len": 2276}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1800, "started": 1791522704.0357504}
{"ep": "ok-00128", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.7745, "speedup": 0.7745, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 149.1, "calls": 4, "tokens_in": 36194, "tokens_out": 7164, "ctx_chars": 6513, "t_end": 1791523004.4703286, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7745, "lo95": 0.7688, "mean": 0.7731, "ev_only": 0.7765, "ref_ms": 17.04516, "cand_ms": 22.00854, "n_trials": 24, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0551, "r_wall_s": 44.61, "compile_s": 2.7, "r_error": "", "src_len": 4343, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 2783, "ts": 1791522878.3636625, "chk": "incorrect", "code_len": 5806}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8536, "tout": 2336, "ts": 1791522908.3697426, "chk": "ok", "code_len": 4343}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10981, "tout": 52, "ts": 1791522944.012056, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11057, "tout": 1993, "ts": 1791522959.8160872, "chk": null, "code_len": 4343}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 5620, "started": 1791522855.3649278}
{"ep": "ok-00087", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.1023, "speedup": 1.1023, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 387.1, "calls": 4, "tokens_in": 20474, "tokens_out": 5448, "ctx_chars": 0, "t_end": 1791523007.2303874, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1023, "lo95": 1.102, "mean": 1.1021, "ev_only": 1.1016, "ref_ms": 22.23951, "cand_ms": 20.17576, "n_trials": 66, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0164, "r_wall_s": 169.85, "compile_s": 15.75, "r_error": "", "src_len": 3912, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1827, "tout": 1896, "ts": 1791522637.9540029, "chk": "compile_error", "code_len": 3878}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4945, "tout": 1748, "ts": 1791522722.2058706, "chk": "ok", "code_len": 3912}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6805, "tout": 68, "ts": 1791522822.9657967, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6897, "tout": 1736, "ts": 1791522837.1070023, "chk": null, "code_len": 3912}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1827, "started": 1791522620.1399848}
{"ep": "ok-00130", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 84.1522, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 146.5, "calls": 2, "tokens_in": 6647, "tokens_out": 7073, "ctx_chars": 0, "t_end": 1791523013.0221066, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 84.1522, "lo95": 82.2288, "mean": 76.4514, "ev_only": 84.991, "ref_ms": 22.32441, "cand_ms": 0.26529, "n_trials": 65, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 59.08, "compile_s": 13.82, "r_error": "", "src_len": 5016, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1829, "tout": 4618, "ts": 1791522906.0917773, "chk": "ok", "code_len": 5016}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4818, "tout": 2455, "ts": 1791522953.7193909, "chk": null, "code_len": 5016}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1829, "started": 1791522866.5715234}
{"ep": "ok-00090", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9598, "speedup": 0.9598, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 377.7, "calls": 4, "tokens_in": 21049, "tokens_out": 5768, "ctx_chars": 495, "t_end": 1791523017.7976906, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9598, "lo95": 0.9588, "mean": 0.9582, "ev_only": 0.9601, "ref_ms": 8.03785, "cand_ms": 8.3742, "n_trials": 153, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0531, "r_wall_s": 125.51, "compile_s": 54.45, "r_error": "", "src_len": 3739, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1738, "tout": 2178, "ts": 1791522660.2667694, "chk": "compile_error", "code_len": 4142}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5134, "tout": 1793, "ts": 1791522774.7716017, "chk": "ok", "code_len": 3739}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7039, "tout": 75, "ts": 1791522877.929188, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7138, "tout": 1722, "ts": 1791522892.19906, "chk": null, "code_len": 3739}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1738, "started": 1791522640.0753388}
{"ep": "ok-00119", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0271, "speedup": 1.0271, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 226.4, "calls": 2, "tokens_in": 10840, "tokens_out": 2494, "ctx_chars": 7159, "t_end": 1791523021.9854088, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0271, "lo95": 1.0268, "mean": 1.0549, "ev_only": 1.0277, "ref_ms": 8.15282, "cand_ms": 7.93774, "n_trials": 159, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 61.65, "compile_s": 1.94, "r_error": "", "src_len": 1847, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4795, "tout": 1472, "ts": 1791522808.068247, "chk": "ok", "code_len": 1847}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6045, "tout": 1022, "ts": 1791522827.3489597, "chk": null, "code_len": 1847}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4795, "started": 1791522795.584466}
{"ep": "ok-00139", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0247, "speedup": 1.0247, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 108.8, "calls": 1, "tokens_in": 6268, "tokens_out": 945, "ctx_chars": 10373, "t_end": 1791523022.737189, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0247, "lo95": 1.0215, "mean": 1.0221, "ev_only": 1.0242, "ref_ms": 8.23499, "cand_ms": 8.03672, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0069, "r_wall_s": 100.0, "compile_s": 6.73, "r_error": "", "src_len": 1864, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6268, "tout": 945, "ts": 1791522922.6343868, "chk": null, "code_len": 1864}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6268, "started": 1791522913.9851987}
{"ep": "ok-00068", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 7.3374, "speedup": 7.3374, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 495.3, "calls": 4, "tokens_in": 48753, "tokens_out": 36328, "ctx_chars": 0, "t_end": 1791523025.7809284, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 7.3374, "lo95": 7.3042, "mean": 7.3968, "ev_only": 7.5204, "ref_ms": 4.10765, "cand_ms": 0.55982, "n_trials": 223, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 24.06, "compile_s": 14.56, "r_error": "", "src_len": 11020, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 17072, "ts": 1791522678.189051, "chk": "incorrect", "code_len": 11244}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9243, "tout": 6643, "ts": 1791522771.949495, "chk": "no_custom_kernel", "code_len": 11043}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 15462, "tout": 6578, "ts": 1791522939.6707797, "chk": "ok", "code_len": 11020}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 21690, "tout": 6035, "ts": 1791523001.6770117, "chk": null, "code_len": 11020}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "no_custom_kernel", "ok", null], "first_tin": 2358, "started": 1791522530.4866164}
{"ep": "ok-00116", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.994, "speedup": 0.994, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 256.9, "calls": 3, "tokens_in": 9874, "tokens_out": 4626, "ctx_chars": 0, "t_end": 1791523028.4595702, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.994, "lo95": 0.9884, "mean": 0.9877, "ev_only": 0.9929, "ref_ms": 8.13661, "cand_ms": 8.186, "n_trials": 198, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0263, "r_wall_s": 120.03, "compile_s": 62.17, "r_error": "", "src_len": 4912, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1605, "tout": 2399, "ts": 1791522792.9149334, "chk": "ok", "code_len": 5002}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4116, "tout": 13, "ts": 1791522890.6169202, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4153, "tout": 2214, "ts": 1791522908.3542497, "chk": null, "code_len": 4912}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1605, "started": 1791522771.5346906}
{"ep": "ok-00143", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0248, "speedup": 1.0248, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 93.7, "calls": 3, "tokens_in": 21074, "tokens_out": 1940, "ctx_chars": 10373, "t_end": 1791523028.6628232, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0248, "lo95": 1.0244, "mean": 1.0247, "ev_only": 1.0253, "ref_ms": 8.15801, "cand_ms": 7.96028, "n_trials": 174, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0068, "r_wall_s": 61.7, "compile_s": 2.47, "r_error": "", "src_len": 1853, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6268, "tout": 977, "ts": 1791522945.4645371, "chk": "ok", "code_len": 1941}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7357, "tout": 68, "ts": 1791522959.502358, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7449, "tout": 895, "ts": 1791522966.872972, "chk": null, "code_len": 1853}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6268, "started": 1791522934.9561932}
{"ep": "ok-00126", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0346, "speedup": 1.0346, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.1, "calls": 4, "tokens_in": 11178, "tokens_out": 2398, "ctx_chars": 0, "t_end": 1791523028.8122659, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0346, "lo95": 1.034, "mean": 1.064, "ev_only": 1.0348, "ref_ms": 8.28598, "cand_ms": 8.00862, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 23.43, "compile_s": 3.22, "r_error": "", "src_len": 1814, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1800, "tout": 444, "ts": 1791522856.0630782, "chk": "forbidden", "code_len": 135}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 2368, "tout": 972, "ts": 1791522864.8645923, "chk": "ok", "code_len": 1898}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3452, "tout": 82, "ts": 1791522997.7025306, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 3558, "tout": 900, "ts": 1791523005.3334587, "chk": null, "code_len": 1814}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 1800, "started": 1791522849.708069}
{"ep": "ok-00142", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.3038, "speedup": 0.3038, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 97.7, "calls": 3, "tokens_in": 23361, "tokens_out": 4210, "ctx_chars": 9125, "t_end": 1791523031.5237832, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.3038, "lo95": 0.3017, "mean": 0.3098, "ev_only": 0.3033, "ref_ms": 3.53546, "cand_ms": 11.63726, "n_trials": 133, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.081, "r_wall_s": 29.88, "compile_s": 2.21, "r_error": "", "src_len": 4134, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6279, "tout": 2123, "ts": 1791522960.9632304, "chk": "ok", "code_len": 4134}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8514, "tout": 30, "ts": 1791522985.0408826, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8568, "tout": 2057, "ts": 1791523001.6018445, "chk": null, "code_len": 4134}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6279, "started": 1791522933.8265734}
{"ep": "ok-00031", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 5.9579, "speedup": 5.9579, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 550.1, "calls": 3, "tokens_in": 31155, "tokens_out": 36193, "ctx_chars": 0, "t_end": 1791523033.4432817, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.9579, "lo95": 5.9238, "mean": 5.8848, "ev_only": 5.9789, "ref_ms": 4.02811, "cand_ms": 0.6761, "n_trials": 181, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 61.51, "compile_s": 19.94, "r_error": "", "src_len": 13978, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 20567, "ts": 1791522659.3590262, "chk": "no_custom_kernel", "code_len": 14253}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10549, "tout": 8244, "ts": 1791522806.7163212, "chk": "ok", "code_len": 13978}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 18248, "tout": 7382, "ts": 1791522971.4753242, "chk": null, "code_len": 13978}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2358, "started": 1791522483.2968712}
{"ep": "ok-00144", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0285, "speedup": 1.0285, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 95.4, "calls": 2, "tokens_in": 13807, "tokens_out": 2063, "ctx_chars": 10373, "t_end": 1791523033.4849708, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0285, "lo95": 1.0256, "mean": 1.0273, "ev_only": 1.0285, "ref_ms": 8.18791, "cand_ms": 7.96079, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 42.83, "compile_s": 3.58, "r_error": "", "src_len": 1733, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6270, "tout": 1155, "ts": 1791522966.9760816, "chk": "ok", "code_len": 1733}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7537, "tout": 908, "ts": 1791522990.5722353, "chk": null, "code_len": 1733}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6270, "started": 1791522958.4508204}
{"ep": "ok-00096", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9787, "speedup": 0.9787, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 353.0, "calls": 2, "tokens_in": 159076, "tokens_out": 4486, "ctx_chars": 182830, "t_end": 1791523033.7887454, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9787, "lo95": 0.9782, "mean": 0.9788, "ev_only": 0.9785, "ref_ms": 29.71643, "cand_ms": 30.36287, "n_trials": 30, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.08, "r_wall_s": 154.91, "compile_s": 48.94, "r_error": "", "src_len": 4629, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78310, "tout": 2344, "ts": 1791522704.4288602, "chk": "ok", "code_len": 4666}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 80766, "tout": 2142, "ts": 1791522878.2138727, "chk": null, "code_len": 4629}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78310, "started": 1791522680.8331165}
{"ep": "ok-00150", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 80.9, "calls": 1, "tokens_in": 1960, "tokens_out": 1730, "ctx_chars": 495, "t_end": 1791523036.555237, "error": "RuntimeError: Error building extension 'fused_pool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/us", "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": 64.73, "compile_s": 64.7, "r_error": "RuntimeError: Error building extension 'fused_pool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/us", "src_len": 3379, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1960, "tout": 1730, "ts": 1791522971.7824264, "chk": null, "code_len": 3379}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1960, "started": 1791522955.6922605}
{"ep": "ok-00077", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 9.3504, "speedup": 9.3504, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 476.8, "calls": 3, "tokens_in": 28101, "tokens_out": 21760, "ctx_chars": 7992, "t_end": 1791523041.618948, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 9.3504, "lo95": 9.3055, "mean": 9.5256, "ev_only": 9.3882, "ref_ms": 31.59379, "cand_ms": 3.37886, "n_trials": 30, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9994, "r_wall_s": 72.65, "compile_s": 20.5, "r_error": "", "src_len": 7328, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 13537, "ts": 1791522692.9885461, "chk": "no_custom_kernel", "code_len": 7362}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9458, "tout": 4195, "ts": 1791522854.2221143, "chk": "ok", "code_len": 7328}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13312, "tout": 4028, "ts": 1791522968.922417, "chk": null, "code_len": 7328}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5331, "started": 1791522564.7718909}
{"ep": "ok-00138", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 139.5, "calls": 1, "tokens_in": 2759, "tokens_out": 5292, "ctx_chars": 495, "t_end": 1791523048.1433172, "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": 0.1228, "r_wall_s": 94.51, "compile_s": 3.08, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 4692, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2759, "tout": 5292, "ts": 1791522953.5922992, "chk": null, "code_len": 4692}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2759, "started": 1791522908.6231449}
{"ep": "ok-00166", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 42.0, "calls": 1, "tokens_in": 2759, "tokens_out": 4107, "ctx_chars": 495, "t_end": 1791523049.2164626, "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": 0.0089, "r_wall_s": 7.98, "compile_s": 1.92, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 4475, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2759, "tout": 4107, "ts": 1791523041.1295648, "chk": null, "code_len": 4475}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2759, "started": 1791523007.230687}
{"ep": "ok-00153", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.009, "speedup": 1.009, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.9, "calls": 2, "tokens_in": 5518, "tokens_out": 5797, "ctx_chars": 0, "t_end": 1791523053.2461011, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.009, "lo95": 1.0085, "mean": 1.0312, "ev_only": 1.0076, "ref_ms": 8.0965, "cand_ms": 8.02452, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0119, "r_wall_s": 24.12, "compile_s": 2.11, "r_error": "", "src_len": 3393, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1607, "tout": 4084, "ts": 1791523008.0310473, "chk": "ok", "code_len": 3393}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3911, "tout": 1713, "ts": 1791523029.0333326, "chk": null, "code_len": 3393}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1607, "started": 1791522971.383707}
{"ep": "ok-00105", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 9.8036, "speedup": 9.8036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 348.7, "calls": 3, "tokens_in": 18847, "tokens_out": 19996, "ctx_chars": 0, "t_end": 1791523053.3700314, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 9.8036, "lo95": 9.4561, "mean": 9.2187, "ev_only": 9.8369, "ref_ms": 45.60278, "cand_ms": 4.65163, "n_trials": 41, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9764, "r_wall_s": 39.23, "compile_s": 13.26, "r_error": "", "src_len": 7611, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1951, "tout": 11974, "ts": 1791522813.644129, "chk": "no_custom_kernel", "code_len": 7575}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6447, "tout": 4225, "ts": 1791522863.0502124, "chk": "ok", "code_len": 7611}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10449, "tout": 3797, "ts": 1791523014.0952475, "chk": null, "code_len": 7611}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1951, "started": 1791522704.6372287}
{"ep": "ok-00048", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.007, "speedup": 0.007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 572.6, "calls": 3, "tokens_in": 250148, "tokens_out": 11729, "ctx_chars": 182830, "t_end": 1791523055.8733585, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.007, "lo95": 0.007, "mean": 0.0071, "ev_only": 0.007, "ref_ms": 31.69064, "cand_ms": 4498.91271, "n_trials": 12, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 306.03, "compile_s": 59.19, "r_error": "", "src_len": 5596, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78516, "tout": 5760, "ts": 1791522548.1187418, "chk": "tampered", "code_len": 6304}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 84359, "tout": 2802, "ts": 1791522637.3942602, "chk": "ok", "code_len": 5642}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 87273, "tout": 3167, "ts": 1791522749.8182817, "chk": null, "code_len": 5596}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["tampered", "ok", null], "first_tin": 78516, "started": 1791522483.3068898}
{"ep": "ok-00114", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.4889, "speedup": 1.4889, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 309.3, "calls": 2, "tokens_in": 160303, "tokens_out": 13215, "ctx_chars": 182830, "t_end": 1791523055.9335449, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4889, "lo95": 1.488, "mean": 1.4884, "ev_only": 1.4918, "ref_ms": 8.02174, "cand_ms": 5.38782, "n_trials": 197, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9779, "r_wall_s": 38.31, "compile_s": 2.57, "r_error": "", "src_len": 6055, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78174, "tout": 9387, "ts": 1791522830.003121, "chk": "ok", "code_len": 6055}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82129, "tout": 3828, "ts": 1791522881.3593516, "chk": null, "code_len": 6055}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78174, "started": 1791522746.6426153}
{"ep": "ok-00117", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0094, "speedup": 1.0094, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 285.0, "calls": 2, "tokens_in": 158478, "tokens_out": 7265, "ctx_chars": 182830, "t_end": 1791523056.846335, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0094, "lo95": 1.0074, "mean": 1.0081, "ev_only": 1.0077, "ref_ms": 7.98086, "cand_ms": 7.90681, "n_trials": 145, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0003, "r_wall_s": 139.02, "compile_s": 59.98, "r_error": "", "src_len": 1546, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78250, "tout": 3631, "ts": 1791522807.5728552, "chk": "incorrect", "code_len": 2747}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 80228, "tout": 3634, "ts": 1791522917.8015587, "chk": null, "code_len": 1546}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", null], "first_tin": 78250, "started": 1791522771.8116395}
{"ep": "ok-00022", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0046, "speedup": 1.0046, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 574.8, "calls": 3, "tokens_in": 10228, "tokens_out": 6854, "ctx_chars": 1080, "t_end": 1791523058.1362948, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0046, "lo95": 1.0045, "mean": 1.0047, "ev_only": 1.0046, "ref_ms": 7.95155, "cand_ms": 7.91488, "n_trials": 104, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 286.62, "compile_s": 2.83, "r_error": "", "src_len": 988, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 1918, "ts": 1791522501.926325, "chk": "incorrect", "code_len": 1647}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3553, "tout": 3701, "ts": 1791522566.890944, "chk": "ok", "code_len": 988}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4557, "tout": 1235, "ts": 1791522771.4687765, "chk": null, "code_len": 988}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2118, "started": 1791522483.2912092}
{"ep": "ok-00089", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.9032, "speedup": 0.9032, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 427.9, "calls": 4, "tokens_in": 34090, "tokens_out": 16100, "ctx_chars": 0, "t_end": 1791523059.6730924, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9032, "lo95": 0.9014, "mean": 0.9004, "ev_only": 0.9029, "ref_ms": 16.32875, "cand_ms": 18.07778, "n_trials": 74, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0335, "r_wall_s": 146.9, "compile_s": 4.7, "r_error": "", "src_len": 3779, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 6984, "ts": 1791522700.990686, "chk": "incorrect", "code_len": 6995}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6989, "tout": 4488, "ts": 1791522793.064487, "chk": "incorrect", "code_len": 7365}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11032, "tout": 2724, "ts": 1791522890.144575, "chk": "ok", "code_len": 3779}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13150, "tout": 1904, "ts": 1791522912.74359, "chk": null, "code_len": 3779}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2919, "started": 1791522631.7570755}
{"ep": "ok-00025", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7389, "speedup": 0.7389, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 576.9, "calls": 3, "tokens_in": 28405, "tokens_out": 14270, "ctx_chars": 6861, "t_end": 1791523060.231266, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7389, "lo95": 0.7337, "mean": 0.7418, "ev_only": 0.7394, "ref_ms": 16.39645, "cand_ms": 22.18997, "n_trials": 47, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.025, "r_wall_s": 256.73, "compile_s": 52.68, "r_error": "", "src_len": 3702, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5693, "tout": 9423, "ts": 1791522564.0947535, "chk": "incorrect", "code_len": 8368}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10370, "tout": 2988, "ts": 1791522766.6805856, "chk": "ok", "code_len": 3702}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12342, "tout": 1859, "ts": 1791522803.4752178, "chk": null, "code_len": 3702}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5693, "started": 1791522483.2931962}
{"ep": "ok-00091", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 6.3443, "speedup": 6.3443, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 427.3, "calls": 2, "tokens_in": 13497, "tokens_out": 24213, "ctx_chars": 2425, "t_end": 1791523068.1160061, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.3443, "lo95": 6.1974, "mean": 6.3241, "ev_only": 6.4439, "ref_ms": 4.00138, "cand_ms": 0.63071, "n_trials": 227, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 68.12, "compile_s": 50.36, "r_error": "", "src_len": 12437, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 17953, "ts": 1791522799.7528026, "chk": "ok", "code_len": 12708}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10223, "tout": 6260, "ts": 1791522999.9296596, "chk": null, "code_len": 12437}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3274, "started": 1791522640.824957}
{"ep": "ok-00132", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7471, "speedup": 0.7471, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 193.0, "calls": 4, "tokens_in": 37474, "tokens_out": 7089, "ctx_chars": 7010, "t_end": 1791523073.7756135, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7471, "lo95": 0.6399, "mean": 0.75, "ev_only": 0.7463, "ref_ms": 16.80064, "cand_ms": 22.4876, "n_trials": 22, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0381, "r_wall_s": 105.92, "compile_s": 4.43, "r_error": "", "src_len": 3809, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5751, "tout": 3083, "ts": 1791522905.9308443, "chk": "incorrect", "code_len": 6300}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8967, "tout": 2271, "ts": 1791522942.406743, "chk": "ok", "code_len": 3809}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11347, "tout": 38, "ts": 1791522954.024155, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11409, "tout": 1697, "ts": 1791522967.77019, "chk": null, "code_len": 3809}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 5751, "started": 1791522880.813212}
{"ep": "ok-00152", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0079, "speedup": 1.0079, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 105.8, "calls": 2, "tokens_in": 6090, "tokens_out": 4949, "ctx_chars": 768, "t_end": 1791523073.8059404, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0079, "lo95": 1.0072, "mean": 1.0094, "ev_only": 1.0082, "ref_ms": 8.10602, "cand_ms": 8.04253, "n_trials": 168, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0147, "r_wall_s": 21.71, "compile_s": 2.38, "r_error": "", "src_len": 3373, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1908, "tout": 3145, "ts": 1791522993.7538104, "chk": "ok", "code_len": 3373}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4182, "tout": 1804, "ts": 1791523052.0056012, "chk": null, "code_len": 3373}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1908, "started": 1791522968.0305085}
{"ep": "ok-00127", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.6665, "speedup": 0.6665, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 229.0, "calls": 2, "tokens_in": 13954, "tokens_out": 9598, "ctx_chars": 6513, "t_end": 1791523079.9593163, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6665, "lo95": 0.664, "mean": 0.6796, "ev_only": 0.6639, "ref_ms": 3.35441, "cand_ms": 5.03307, "n_trials": 185, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3409, "r_wall_s": 25.42, "compile_s": 3.15, "r_error": "", "src_len": 5417, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 6755, "ts": 1791522911.0012658, "chk": "ok", "code_len": 5417}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8623, "tout": 2843, "ts": 1791523054.3982, "chk": null, "code_len": 5417}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5331, "started": 1791522850.9788392}
{"ep": "ok-00110", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8087, "speedup": 0.8087, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 367.3, "calls": 2, "tokens_in": 163375, "tokens_out": 15331, "ctx_chars": 182830, "t_end": 1791523089.4103184, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.8087, "lo95": 0.8063, "mean": 0.8089, "ev_only": 0.8052, "ref_ms": 3.40227, "cand_ms": 4.20719, "n_trials": 185, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0218, "r_wall_s": 60.28, "compile_s": 49.77, "r_error": "", "src_len": 8861, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79195, "tout": 10482, "ts": 1791522812.038511, "chk": "ok", "code_len": 8861}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 84180, "tout": 4849, "ts": 1791523029.0816221, "chk": null, "code_len": 8861}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79195, "started": 1791522722.0665548}
{"ep": "ok-00156", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.006, "speedup": 1.006, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 126.5, "calls": 2, "tokens_in": 12059, "tokens_out": 5338, "ctx_chars": 7549, "t_end": 1791523103.9782429, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.006, "lo95": 1.0049, "mean": 1.0059, "ev_only": 1.0059, "ref_ms": 8.06346, "cand_ms": 8.01503, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0151, "r_wall_s": 71.44, "compile_s": 3.34, "r_error": "", "src_len": 3712, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4870, "tout": 3431, "ts": 1791523006.4908793, "chk": "ok", "code_len": 3712}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7189, "tout": 1907, "ts": 1791523032.4601986, "chk": null, "code_len": 3712}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4870, "started": 1791522977.4955523}
{"ep": "ok-00052", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 6.923, "speedup": 6.923, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 621.2, "calls": 4, "tokens_in": 48322, "tokens_out": 37910, "ctx_chars": 495, "t_end": 1791523104.5045383, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.923, "lo95": 6.8921, "mean": 6.8802, "ev_only": 6.8835, "ref_ms": 3.97791, "cand_ms": 0.57459, "n_trials": 223, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 151.62, "compile_s": 15.75, "r_error": "", "src_len": 11063, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2491, "tout": 19169, "ts": 1791522650.909492, "chk": "runtime_error", "code_len": 11303}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9246, "tout": 6309, "ts": 1791522742.6363144, "chk": "no_custom_kernel", "code_len": 10933}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 15219, "tout": 6469, "ts": 1791522863.2112157, "chk": "ok", "code_len": 11063}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 21366, "tout": 5963, "ts": 1791522952.843864, "chk": null, "code_len": 11063}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "no_custom_kernel", "ok", null], "first_tin": 2491, "started": 1791522483.3073683}
{"ep": "ok-00164", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0178, "speedup": 1.0178, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 103.9, "calls": 3, "tokens_in": 25195, "tokens_out": 2849, "ctx_chars": 12352, "t_end": 1791523106.9004986, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0178, "lo95": 1.0175, "mean": 1.0182, "ev_only": 1.0189, "ref_ms": 29.61607, "cand_ms": 29.0971, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0385, "r_wall_s": 64.16, "compile_s": 2.02, "r_error": "", "src_len": 2734, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1470, "ts": 1791523016.7933266, "chk": "ok", "code_len": 2734}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8909, "tout": 26, "ts": 1791523030.599033, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8959, "tout": 1353, "ts": 1791523042.1340094, "chk": null, "code_len": 2734}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7327, "started": 1791523003.0412688}
{"ep": "ok-00160", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.9947, "speedup": 0.9947, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 146.8, "calls": 3, "tokens_in": 22197, "tokens_out": 2755, "ctx_chars": 10823, "t_end": 1791523128.3339283, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9947, "lo95": 0.994, "mean": 0.9925, "ev_only": 0.9927, "ref_ms": 8.08346, "cand_ms": 8.12624, "n_trials": 171, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0129, "r_wall_s": 76.27, "compile_s": 3.2, "r_error": "", "src_len": 2729, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1425, "ts": 1791522994.3545346, "chk": "ok", "code_len": 2758}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7899, "tout": 13, "ts": 1791523041.1396194, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7936, "tout": 1317, "ts": 1791523051.9589007, "chk": null, "code_len": 2729}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791522981.567222}
{"ep": "ok-00100", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7431, "speedup": 0.7431, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 431.8, "calls": 4, "tokens_in": 41290, "tokens_out": 10400, "ctx_chars": 6417, "t_end": 1791523128.952004, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7431, "lo95": 0.6956, "mean": 0.8172, "ev_only": 0.7416, "ref_ms": 24.77812, "cand_ms": 33.34531, "n_trials": 59, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0347, "r_wall_s": 73.96, "compile_s": 3.78, "r_error": "", "src_len": 3722, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5503, "tout": 3160, "ts": 1791522723.1830044, "chk": "incorrect", "code_len": 6352}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8796, "tout": 3528, "ts": 1791522794.6793156, "chk": "incorrect", "code_len": 6773}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12458, "tout": 1966, "ts": 1791522974.0244837, "chk": "ok", "code_len": 3722}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14533, "tout": 1746, "ts": 1791523054.9630709, "chk": null, "code_len": 3722}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5503, "started": 1791522697.1171536}
{"ep": "ok-00175", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.8177, "speedup": 0.8177, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 98.3, "calls": 2, "tokens_in": 12647, "tokens_out": 4574, "ctx_chars": 6513, "t_end": 1791523129.8552778, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8177, "lo95": 0.8031, "mean": 0.7917, "ev_only": 0.8216, "ref_ms": 6.0466, "cand_ms": 7.39424, "n_trials": 222, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0017, "r_wall_s": 52.27, "compile_s": 5.89, "r_error": "", "src_len": 2961, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 2939, "ts": 1791523057.2203338, "chk": "ok", "code_len": 2961}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7316, "tout": 1635, "ts": 1791523077.5649467, "chk": null, "code_len": 2961}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5331, "started": 1791523031.5241287}
{"ep": "ok-00163", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.265, "speedup": 0.265, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 131.5, "calls": 3, "tokens_in": 20968, "tokens_out": 4228, "ctx_chars": 7010, "t_end": 1791523131.2796504, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.265, "lo95": 0.2529, "mean": 0.2834, "ev_only": 0.2641, "ref_ms": 5.04617, "cand_ms": 19.04077, "n_trials": 64, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0775, "r_wall_s": 56.14, "compile_s": 3.29, "r_error": "", "src_len": 4105, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5460, "tout": 2143, "ts": 1791523038.0864837, "chk": "ok", "code_len": 4218}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7715, "tout": 54, "ts": 1791523057.5701342, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7793, "tout": 2031, "ts": 1791523075.1172755, "chk": null, "code_len": 4105}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5460, "started": 1791523020.0929263}
{"ep": "ok-00076", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 5.6876, "speedup": 5.6876, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 568.5, "calls": 3, "tokens_in": 28531, "tokens_out": 19612, "ctx_chars": 7992, "t_end": 1791523131.2898655, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.6876, "lo95": 5.6757, "mean": 5.9389, "ev_only": 5.6827, "ref_ms": 32.24346, "cand_ms": 5.66909, "n_trials": 43, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9997, "r_wall_s": 161.51, "compile_s": 57.9, "r_error": "", "src_len": 7571, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 10999, "ts": 1791522659.3290749, "chk": "no_custom_kernel", "code_len": 7512}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9580, "tout": 4285, "ts": 1791522788.378686, "chk": "ok", "code_len": 7571}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13620, "tout": 4328, "ts": 1791522969.730912, "chk": null, "code_len": 7571}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5331, "started": 1791522562.7606168}
{"ep": "ok-00023", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 7.5814, "speedup": 7.5814, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 650.4, "calls": 3, "tokens_in": 28235, "tokens_out": 35531, "ctx_chars": 495, "t_end": 1791523133.6972919, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.5814, "lo95": 7.5407, "mean": 7.4873, "ev_only": 7.7545, "ref_ms": 3.91006, "cand_ms": 0.51574, "n_trials": 190, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 144.76, "compile_s": 17.77, "r_error": "", "src_len": 12136, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2491, "tout": 22175, "ts": 1791522682.8868384, "chk": "no_custom_kernel", "code_len": 12597}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9613, "tout": 6790, "ts": 1791522774.5721252, "chk": "ok", "code_len": 12136}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16131, "tout": 6566, "ts": 1791522988.8909018, "chk": null, "code_len": 12136}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2491, "started": 1791522483.2919338}
{"ep": "ok-00179", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0307, "speedup": 1.0307, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 98.7, "calls": 2, "tokens_in": 13204, "tokens_out": 2590, "ctx_chars": 9546, "t_end": 1791523135.2469788, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0307, "lo95": 1.0271, "mean": 1.0219, "ev_only": 1.031, "ref_ms": 8.36906, "cand_ms": 8.12006, "n_trials": 150, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.003, "r_wall_s": 63.84, "compile_s": 2.81, "r_error": "", "src_len": 1516, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5937, "tout": 1763, "ts": 1791523052.549122, "chk": "ok", "code_len": 1516}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7267, "tout": 827, "ts": 1791523071.3802605, "chk": null, "code_len": 1516}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5937, "started": 1791523036.5556066}
{"ep": "ok-00188", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 87.1, "calls": 1, "tokens_in": 1856, "tokens_out": 1824, "ctx_chars": 495, "t_end": 1791523145.1887238, "error": "RuntimeError: Error building extension 'gn_ht_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht_mod -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": 69.1, "compile_s": 69.09, "r_error": "RuntimeError: Error building extension 'gn_ht_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval", "src_len": 3620, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1856, "tout": 1824, "ts": 1791523076.0629828, "chk": null, "code_len": 3620}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1856, "started": 1791523058.1365876}
{"ep": "ok-00176", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0155, "speedup": 1.0155, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 127.2, "calls": 3, "tokens_in": 22555, "tokens_out": 2919, "ctx_chars": 10528, "t_end": 1791523160.6705284, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0155, "lo95": 1.0152, "mean": 1.0156, "ev_only": 1.0161, "ref_ms": 29.79562, "cand_ms": 29.33996, "n_trials": 48, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0441, "r_wall_s": 82.97, "compile_s": 3.34, "r_error": "", "src_len": 2772, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6419, "tout": 1512, "ts": 1791523047.130899, "chk": "ok", "code_len": 2772}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8043, "tout": 26, "ts": 1791523065.6507866, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8093, "tout": 1381, "ts": 1791523076.9169395, "chk": null, "code_len": 2772}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6419, "started": 1791523033.4436173}
{"ep": "ok-00193", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 97.4, "calls": 1, "tokens_in": 1827, "tokens_out": 1673, "ctx_chars": 0, "t_end": 1791523171.1731732, "error": "RuntimeError: Error building extension 'fused_pool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/us", "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": 82.11, "compile_s": 82.08, "r_error": "RuntimeError: Error building extension 'fused_pool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/us", "src_len": 3534, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1827, "tout": 1673, "ts": 1791523089.042484, "chk": null, "code_len": 3534}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1827, "started": 1791523073.806219}
{"ep": "ok-00177", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.426, "speedup": 1.426, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 142.5, "calls": 2, "tokens_in": 6030, "tokens_out": 6218, "ctx_chars": 0, "t_end": 1791523176.02505, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.426, "lo95": 1.4251, "mean": 1.4247, "ev_only": 1.424, "ref_ms": 8.19491, "cand_ms": 5.74691, "n_trials": 181, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 75.1, "compile_s": 44.6, "r_error": "", "src_len": 3709, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 4186, "ts": 1791523069.9771378, "chk": "ok", "code_len": 3709}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4305, "tout": 2032, "ts": 1791523100.8535821, "chk": null, "code_len": 3709}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791523033.4852624}
{"ep": "ok-00178", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.1279, "speedup": 0.1279, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 143.2, "calls": 3, "tokens_in": 23828, "tokens_out": 5013, "ctx_chars": 8224, "t_end": 1791523177.0280128, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.1279, "lo95": 0.1127, "mean": 0.1331, "ev_only": 0.1278, "ref_ms": 36.2313, "cand_ms": 283.22869, "n_trials": 9, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2716, "r_wall_s": 85.95, "compile_s": 22.7, "r_error": "", "src_len": 2821, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 3495, "ts": 1791523066.005976, "chk": "ok", "code_len": 2821}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9100, "tout": 111, "ts": 1791523078.958135, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9235, "tout": 1407, "ts": 1791523091.0570002, "chk": null, "code_len": 2821}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5493, "started": 1791523033.7891397}
{"ep": "ok-00196", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7446, "speedup": 0.7446, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 73.2, "calls": 2, "tokens_in": 13401, "tokens_out": 4714, "ctx_chars": 6513, "t_end": 1791523177.139953, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7446, "lo95": 0.7296, "mean": 0.6718, "ev_only": 0.745, "ref_ms": 17.14128, "cand_ms": 23.0223, "n_trials": 50, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0396, "r_wall_s": 26.75, "compile_s": 2.28, "r_error": "", "src_len": 3723, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5622, "tout": 2939, "ts": 1791523128.5945017, "chk": "ok", "code_len": 3789}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7779, "tout": 1775, "ts": 1791523150.3283439, "chk": null, "code_len": 3723}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5622, "started": 1791523103.9785695}
{"ep": "ok-00203", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0369, "speedup": 1.0369, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 47.9, "calls": 2, "tokens_in": 10043, "tokens_out": 2542, "ctx_chars": 5984, "t_end": 1791523179.1592295, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0369, "lo95": 1.0364, "mean": 1.0641, "ev_only": 1.0371, "ref_ms": 8.22329, "cand_ms": 7.9308, "n_trials": 154, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 15.37, "compile_s": 2.0, "r_error": "", "src_len": 1578, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4391, "tout": 1717, "ts": 1791523146.767479, "chk": "ok", "code_len": 1578}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5652, "tout": 825, "ts": 1791523163.688197, "chk": null, "code_len": 1578}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4391, "started": 1791523131.290067}
{"ep": "ok-00053", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 6.6474, "speedup": 6.6474, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 698.0, "calls": 3, "tokens_in": 27614, "tokens_out": 33190, "ctx_chars": 369, "t_end": 1791523181.292775, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.6474, "lo95": 5.532, "mean": 5.7838, "ev_only": 6.7562, "ref_ms": 6.93282, "cand_ms": 1.04294, "n_trials": 204, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 218.89, "compile_s": 15.52, "r_error": "", "src_len": 11317, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2478, "tout": 20873, "ts": 1791522666.9358356, "chk": "no_custom_kernel", "code_len": 11598}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9463, "tout": 6280, "ts": 1791522791.5067804, "chk": "ok", "code_len": 11317}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15673, "tout": 6037, "ts": 1791522962.358478, "chk": null, "code_len": 11317}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2478, "started": 1791522483.3089166}
{"ep": "ok-00131", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 73.0958, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 307.8, "calls": 2, "tokens_in": 7133, "tokens_out": 7944, "ctx_chars": 495, "t_end": 1791523183.5434299, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 73.0958, "lo95": 72.0749, "mean": 72.1488, "ev_only": 76.6825, "ref_ms": 22.34698, "cand_ms": 0.30572, "n_trials": 63, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 48.3, "compile_s": 12.16, "r_error": "", "src_len": 4980, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 5431, "ts": 1791522943.2193449, "chk": "ok", "code_len": 4980}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5171, "tout": 2513, "ts": 1791523135.0155492, "chk": null, "code_len": 4980}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791522896.1302235}
{"ep": "ok-00135", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.965, "speedup": 0.965, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 298.7, "calls": 3, "tokens_in": 242271, "tokens_out": 6826, "ctx_chars": 182830, "t_end": 1791523201.8110013, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.965, "lo95": 0.9645, "mean": 0.9664, "ev_only": 0.9638, "ref_ms": 8.21634, "cand_ms": 8.51427, "n_trials": 138, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 49.28, "compile_s": 3.66, "r_error": "", "src_len": 3677, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78290, "tout": 2499, "ts": 1791522928.7487876, "chk": "incorrect", "code_len": 3823}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 80921, "tout": 2027, "ts": 1791522992.2758992, "chk": "ok", "code_len": 3756}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 83060, "tout": 2300, "ts": 1791523152.43528, "chk": null, "code_len": 3677}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78290, "started": 1791522903.0667133}
{"ep": "ok-00172", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0212, "speedup": 1.0212, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.1, "calls": 2, "tokens_in": 16334, "tokens_out": 2939, "ctx_chars": 12352, "t_end": 1791523215.577902, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0212, "lo95": 1.0206, "mean": 1.0214, "ev_only": 1.0206, "ref_ms": 29.70693, "cand_ms": 29.0897, "n_trials": 34, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0339, "r_wall_s": 137.84, "compile_s": 3.21, "r_error": "", "src_len": 2747, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1568, "ts": 1791523043.199778, "chk": "ok", "code_len": 2798}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9007, "tout": 1371, "ts": 1791523077.064335, "chk": null, "code_len": 2747}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7327, "started": 1791523028.4599168}
{"ep": "ok-00157", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.4197, "speedup": 1.4197, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 240.0, "calls": 2, "tokens_in": 6229, "tokens_out": 6330, "ctx_chars": 495, "t_end": 1791523218.247179, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4197, "lo95": 1.4185, "mean": 1.4171, "ev_only": 1.4167, "ref_ms": 8.16272, "cand_ms": 5.7497, "n_trials": 209, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 42.02, "compile_s": 1.89, "r_error": "", "src_len": 3767, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1858, "tout": 3772, "ts": 1791523009.8244796, "chk": "ok", "code_len": 3767}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4371, "tout": 2558, "ts": 1791523176.0303395, "chk": null, "code_len": 3767}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1858, "started": 1791522978.2451756}
{"ep": "ok-00149", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 268.7, "calls": 5, "tokens_in": 36500, "tokens_out": 3779, "ctx_chars": 9192, "t_end": 1791523221.8165202, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 4, "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": 0.0018, "r_wall_s": 32.89, "compile_s": 2.34, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1026, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 615, "ts": 1791522959.167242, "chk": "incorrect", "code_len": 1079}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6379, "tout": 760, "ts": 1791523129.1727948, "chk": "incorrect", "code_len": 1141}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7272, "tout": 772, "ts": 1791523145.786117, "chk": "incorrect", "code_len": 1041}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8178, "tout": 706, "ts": 1791523161.2586086, "chk": "incorrect", "code_len": 1080}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9040, "tout": 926, "ts": 1791523188.818195, "chk": null, "code_len": 1026}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 5631, "started": 1791522953.0930197}
{"ep": "ok-00190", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0346, "speedup": 1.0346, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 170.4, "calls": 2, "tokens_in": 10960, "tokens_out": 2720, "ctx_chars": 6481, "t_end": 1791523230.6049516, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0346, "lo95": 1.034, "mean": 1.0727, "ev_only": 1.0341, "ref_ms": 8.26618, "cand_ms": 7.98971, "n_trials": 166, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0061, "r_wall_s": 42.08, "compile_s": 2.07, "r_error": "", "src_len": 1788, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4520, "tout": 1808, "ts": 1791523097.4320729, "chk": "ok", "code_len": 1788}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6440, "tout": 912, "ts": 1791523188.479701, "chk": null, "code_len": 1788}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4520, "started": 1791523080.5816605}
{"ep": "ok-00118", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0026, "speedup": 1.0026, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 457.3, "calls": 4, "tokens_in": 16587, "tokens_out": 8429, "ctx_chars": 495, "t_end": 1791523233.1640453, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0026, "lo95": 0.998, "mean": 1.0002, "ev_only": 1.0048, "ref_ms": 8.03891, "cand_ms": 8.0181, "n_trials": 141, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 28.66, "compile_s": 2.38, "r_error": "", "src_len": 965, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1816, "tout": 3046, "ts": 1791522802.3525136, "chk": "incorrect", "code_len": 2732}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3799, "tout": 2766, "ts": 1791522979.581386, "chk": "incorrect", "code_len": 1064}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5010, "tout": 1583, "ts": 1791523103.4616523, "chk": "ok", "code_len": 965}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5962, "tout": 1034, "ts": 1791523204.4468093, "chk": null, "code_len": 965}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1816, "started": 1791522775.8176026}
{"ep": "ok-00120", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 7.9082, "speedup": 7.9082, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 446.7, "calls": 3, "tokens_in": 250903, "tokens_out": 26858, "ctx_chars": 182830, "t_end": 1791523244.1212616, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 7.9082, "lo95": 7.8811, "mean": 7.8926, "ev_only": 7.9332, "ref_ms": 32.06048, "cand_ms": 4.05408, "n_trials": 47, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9994, "r_wall_s": 89.22, "compile_s": 54.4, "r_error": "", "src_len": 8643, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78518, "tout": 15922, "ts": 1791522941.695176, "chk": "no_custom_kernel", "code_len": 8646}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 83805, "tout": 5873, "ts": 1791523055.619506, "chk": "ok", "code_len": 8643}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 88580, "tout": 5063, "ts": 1791523154.861537, "chk": null, "code_len": 8643}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 78518, "started": 1791522797.37795}
{"ep": "ok-00186", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.9846, "speedup": 0.9846, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 192.2, "calls": 2, "tokens_in": 11646, "tokens_out": 3106, "ctx_chars": 7758, "t_end": 1791523248.1240866, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9846, "lo95": 0.9829, "mean": 0.9893, "ev_only": 0.9898, "ref_ms": 8.15185, "cand_ms": 8.27908, "n_trials": 161, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0163, "r_wall_s": 150.35, "compile_s": 47.19, "r_error": "", "src_len": 3044, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4947, "tout": 1640, "ts": 1791523070.598221, "chk": "ok", "code_len": 3178}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6699, "tout": 1466, "ts": 1791523097.6532776, "chk": null, "code_len": 3044}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4947, "started": 1791523055.933883}
{"ep": "ok-00187", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.946, "speedup": 0.946, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 194.5, "calls": 4, "tokens_in": 35004, "tokens_out": 6627, "ctx_chars": 5802, "t_end": 1791523251.3033795, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.946, "lo95": 0.7334, "mean": 0.9337, "ev_only": 0.9467, "ref_ms": 21.74299, "cand_ms": 22.98397, "n_trials": 34, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0393, "r_wall_s": 59.17, "compile_s": 1.98, "r_error": "", "src_len": 3672, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 3076, "ts": 1791523082.7244298, "chk": "incorrect", "code_len": 6297}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8540, "tout": 1884, "ts": 1791523167.6767125, "chk": "ok", "code_len": 3672}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10533, "tout": 43, "ts": 1791523178.4767754, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10600, "tout": 1624, "ts": 1791523192.0224347, "chk": null, "code_len": 3672}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 5331, "started": 1791523056.846678}
{"ep": "ok-00171", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0329, "speedup": 1.0329, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 230.8, "calls": 2, "tokens_in": 13614, "tokens_out": 4475, "ctx_chars": 8788, "t_end": 1791523256.6291919, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0329, "lo95": 1.0323, "mean": 1.0328, "ev_only": 1.0332, "ref_ms": 29.77097, "cand_ms": 28.82232, "n_trials": 35, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0241, "r_wall_s": 167.14, "compile_s": 14.62, "r_error": "", "src_len": 2924, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5761, "tout": 2886, "ts": 1791523052.9802098, "chk": "ok", "code_len": 2924}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7853, "tout": 1589, "ts": 1791523088.5563016, "chk": null, "code_len": 2924}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5761, "started": 1791523025.7812161}
{"ep": "ok-00169", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 41.4114, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 242.6, "calls": 2, "tokens_in": 15085, "tokens_out": 6122, "ctx_chars": 10255, "t_end": 1791523264.5830202, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 41.4114, "lo95": 37.4815, "mean": 40.276, "ev_only": 42.4982, "ref_ms": 22.37073, "cand_ms": 0.54021, "n_trials": 62, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 177.11, "compile_s": 12.63, "r_error": "", "src_len": 2978, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6434, "tout": 4589, "ts": 1791523064.7283673, "chk": "ok", "code_len": 3044}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8651, "tout": 1533, "ts": 1791523087.1889217, "chk": null, "code_len": 2978}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6434, "started": 1791523021.9857688}
{"ep": "ok-00198", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0386, "speedup": 1.0386, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.2, "calls": 2, "tokens_in": 7323, "tokens_out": 4812, "ctx_chars": 2175, "t_end": 1791523265.1355445, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0386, "lo95": 1.0384, "mean": 1.0383, "ev_only": 1.0389, "ref_ms": 29.67554, "cand_ms": 28.57255, "n_trials": 45, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0194, "r_wall_s": 74.13, "compile_s": 2.61, "r_error": "", "src_len": 3025, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2546, "tout": 3150, "ts": 1791523151.6355975, "chk": "ok", "code_len": 3025}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4777, "tout": 1662, "ts": 1791523190.476862, "chk": null, "code_len": 3025}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2546, "started": 1791523106.900831}
{"ep": "ok-00173", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0293, "speedup": 1.0293, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 244.1, "calls": 2, "tokens_in": 13655, "tokens_out": 4349, "ctx_chars": 8788, "t_end": 1791523272.7233534, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0293, "lo95": 1.0285, "mean": 1.0283, "ev_only": 1.0289, "ref_ms": 29.77648, "cand_ms": 28.92935, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0278, "r_wall_s": 191.26, "compile_s": 7.23, "r_error": "", "src_len": 2862, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5761, "tout": 2796, "ts": 1791523052.432574, "chk": "ok", "code_len": 2862}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7894, "tout": 1553, "ts": 1791523080.9381776, "chk": null, "code_len": 2862}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5761, "started": 1791523028.663084}
{"ep": "ok-00008", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0842, "speedup": 1.0842, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 808.6, "calls": 4, "tokens_in": 43727, "tokens_out": 25783, "ctx_chars": 0, "t_end": 1791523291.8509932, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0842, "lo95": 1.0768, "mean": 0.9846, "ev_only": 1.0837, "ref_ms": 16.80839, "cand_ms": 15.50287, "n_trials": 82, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0501, "r_wall_s": 208.07, "compile_s": 67.42, "r_error": "", "src_len": 5483, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 12729, "ts": 1791522593.2242205, "chk": "incorrect", "code_len": 10892}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8793, "tout": 6517, "ts": 1791522753.925201, "chk": "incorrect", "code_len": 11032}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 14436, "tout": 3818, "ts": 1791522920.2709186, "chk": "ok", "code_len": 5483}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 17579, "tout": 2719, "ts": 1791523083.7481766, "chk": null, "code_len": 5483}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2919, "started": 1791522483.2835126}
{"ep": "ok-00124", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.569, "speedup": 1.569, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 477.0, "calls": 4, "tokens_in": 329930, "tokens_out": 15544, "ctx_chars": 182830, "t_end": 1791523297.8715723, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.569, "lo95": 1.5615, "mean": 1.5705, "ev_only": 1.5767, "ref_ms": 8.38514, "cand_ms": 5.34412, "n_trials": 158, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 172.17, "compile_s": 32.22, "r_error": "", "src_len": 4511, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78369, "tout": 6130, "ts": 1791522877.028303, "chk": "incorrect", "code_len": 3887}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81237, "tout": 3061, "ts": 1791522911.0653844, "chk": "ok", "code_len": 4054}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 83763, "tout": 3403, "ts": 1791522969.793999, "chk": "ok", "code_len": 4511}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 86561, "tout": 2950, "ts": 1791523125.5955424, "chk": null, "code_len": 4511}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", null], "first_tin": 78369, "started": 1791522820.899154}
{"ep": "ok-00162", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0105, "speedup": 1.0105, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 313.3, "calls": 2, "tokens_in": 6581, "tokens_out": 6026, "ctx_chars": 768, "t_end": 1791523298.0796454, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0105, "lo95": 1.0086, "mean": 1.0102, "ev_only": 1.0097, "ref_ms": 8.09796, "cand_ms": 8.01372, "n_trials": 77, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0035, "r_wall_s": 207.2, "compile_s": 17.95, "r_error": "", "src_len": 4316, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1908, "tout": 3798, "ts": 1791523015.5355577, "chk": "ok", "code_len": 4316}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4673, "tout": 2228, "ts": 1791523090.7603385, "chk": null, "code_len": 4316}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1908, "started": 1791522984.7469854}
{"ep": "ok-00167", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9935, "speedup": 0.9935, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 297.3, "calls": 2, "tokens_in": 159198, "tokens_out": 4786, "ctx_chars": 182830, "t_end": 1791523310.3204117, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9935, "lo95": 0.9924, "mean": 0.9936, "ev_only": 0.9926, "ref_ms": 29.70486, "cand_ms": 29.8991, "n_trials": 44, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0643, "r_wall_s": 190.52, "compile_s": 88.13, "r_error": "", "src_len": 5005, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78310, "tout": 2466, "ts": 1791523036.9362917, "chk": "ok", "code_len": 5033}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 80888, "tout": 2320, "ts": 1791523119.2643833, "chk": null, "code_len": 5005}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78310, "started": 1791523013.022368}
{"ep": "ok-00185", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "no_custom_kernel", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 254.5, "calls": 1, "tokens_in": 2626, "tokens_out": 4228, "ctx_chars": 0, "t_end": 1791523310.3492928, "error": "none of the candidate's kernels ['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-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": 0.0, "r_wall_s": 215.03, "compile_s": 42.43, "r_error": "none of the candidate's kernels ['relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "src_len": 4313, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2626, "tout": 4228, "ts": 1791523095.2909448, "chk": null, "code_len": 4313}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2626, "started": 1791523055.873665}
{"ep": "ok-00206", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.019, "speedup": 1.019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 172.2, "calls": 3, "tokens_in": 18316, "tokens_out": 2926, "ctx_chars": 7245, "t_end": 1791523317.4335222, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.019, "lo95": 1.0185, "mean": 1.0192, "ev_only": 1.0199, "ref_ms": 29.80572, "cand_ms": 29.24894, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0369, "r_wall_s": 88.25, "compile_s": 2.53, "r_error": "", "src_len": 2635, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4949, "tout": 1604, "ts": 1791523160.2719479, "chk": "ok", "code_len": 2705}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6665, "tout": 13, "ts": 1791523217.864824, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6702, "tout": 1309, "ts": 1791523228.5830305, "chk": null, "code_len": 2635}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4949, "started": 1791523145.1890695}
{"ep": "ok-00148", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.0777, "speedup": 0.0777, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 366.8, "calls": 4, "tokens_in": 20066, "tokens_out": 6904, "ctx_chars": 495, "t_end": 1791523318.6084933, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0777, "lo95": 0.0773, "mean": 0.0774, "ev_only": 0.0777, "ref_ms": 31.43475, "cand_ms": 404.67718, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2298, "r_wall_s": 19.46, "compile_s": 1.94, "r_error": "", "src_len": 3389, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2082, "tout": 1886, "ts": 1791522969.8647451, "chk": "forbidden", "code_len": 3163}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4129, "tout": 1536, "ts": 1791522983.0944932, "chk": "runtime_error", "code_len": 3298}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6095, "tout": 1553, "ts": 1791523136.2655094, "chk": "ok", "code_len": 3311}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7760, "tout": 1929, "ts": 1791523299.1195407, "chk": null, "code_len": 3389}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "runtime_error", "ok", null], "first_tin": 2082, "started": 1791522951.7808332}
{"ep": "ok-00071", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.8607, "speedup": 0.8607, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 789.9, "calls": 4, "tokens_in": 59539, "tokens_out": 29197, "ctx_chars": 5888, "t_end": 1791523322.691258, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8607, "lo95": 0.8573, "mean": 0.8701, "ev_only": 0.8607, "ref_ms": 16.51098, "cand_ms": 19.18371, "n_trials": 75, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0372, "r_wall_s": 246.59, "compile_s": 20.32, "r_error": "", "src_len": 4833, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5353, "tout": 16370, "ts": 1791522674.5165887, "chk": "incorrect", "code_len": 12880}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 12562, "tout": 7162, "ts": 1791522850.685399, "chk": "incorrect", "code_len": 12873}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 19451, "tout": 3252, "ts": 1791523023.4487, "chk": "ok", "code_len": 4833}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 22173, "tout": 2413, "ts": 1791523076.079231, "chk": null, "code_len": 4833}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5353, "started": 1791522532.7640996}
{"ep": "ok-00210", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.2283, "speedup": 0.2283, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 154.9, "calls": 3, "tokens_in": 20224, "tokens_out": 4232, "ctx_chars": 6417, "t_end": 1791523331.9547932, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.2283, "lo95": 0.2209, "mean": 0.2561, "ev_only": 0.2287, "ref_ms": 3.36679, "cand_ms": 14.74921, "n_trials": 101, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0759, "r_wall_s": 71.79, "compile_s": 2.73, "r_error": "", "src_len": 4096, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5212, "tout": 2156, "ts": 1791523195.128477, "chk": "ok", "code_len": 4140}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7480, "tout": 28, "ts": 1791523243.4021912, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7532, "tout": 2048, "ts": 1791523260.1200156, "chk": null, "code_len": 4096}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5212, "started": 1791523177.028331}
{"ep": "ok-00211", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9931, "speedup": 0.9931, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.1, "calls": 3, "tokens_in": 22410, "tokens_out": 2950, "ctx_chars": 10823, "t_end": 1791523332.2331507, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9931, "lo95": 0.9913, "mean": 0.9957, "ev_only": 0.9955, "ref_ms": 8.0484, "cand_ms": 8.1043, "n_trials": 79, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0091, "r_wall_s": 80.65, "compile_s": 2.76, "r_error": "", "src_len": 2872, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1518, "ts": 1791523190.346531, "chk": "ok", "code_len": 2872}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7992, "tout": 40, "ts": 1791523239.761341, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8056, "tout": 1392, "ts": 1791523251.482, "chk": null, "code_len": 2872}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791523177.1402924}
{"ep": "ok-00207", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7664, "speedup": 0.7664, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 173.1, "calls": 2, "tokens_in": 13581, "tokens_out": 5820, "ctx_chars": 6513, "t_end": 1791523333.7692404, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7664, "lo95": 0.7598, "mean": 0.7959, "ev_only": 0.7668, "ref_ms": 16.65123, "cand_ms": 21.72724, "n_trials": 34, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0338, "r_wall_s": 102.29, "compile_s": 4.64, "r_error": "", "src_len": 4111, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5622, "tout": 3872, "ts": 1791523195.183631, "chk": "ok", "code_len": 4167}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7959, "tout": 1948, "ts": 1791523231.4270213, "chk": null, "code_len": 4111}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5622, "started": 1791523160.6708746}
{"ep": "ok-00194", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0319, "speedup": 1.0319, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.4, "calls": 2, "tokens_in": 5663, "tokens_out": 4899, "ctx_chars": 0, "t_end": 1791523335.4049542, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0319, "lo95": 1.0313, "mean": 1.0319, "ev_only": 1.0321, "ref_ms": 29.76143, "cand_ms": 28.84199, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0244, "r_wall_s": 50.98, "compile_s": 1.95, "r_error": "", "src_len": 3273, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1745, "tout": 3193, "ts": 1791523108.2517312, "chk": "ok", "code_len": 3273}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3918, "tout": 1706, "ts": 1791523283.8430054, "chk": null, "code_len": 3273}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1745, "started": 1791523079.9596443}
{"ep": "ok-00136", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.009, "speedup": 1.009, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 443.4, "calls": 4, "tokens_in": 26426, "tokens_out": 8995, "ctx_chars": 5630, "t_end": 1791523347.596343, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.009, "lo95": 1.0083, "mean": 1.0088, "ev_only": 1.0091, "ref_ms": 7.97472, "cand_ms": 7.90383, "n_trials": 158, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 46.95, "compile_s": 1.87, "r_error": "", "src_len": 919, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4087, "tout": 3006, "ts": 1791522931.6190286, "chk": "incorrect", "code_len": 2636}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5916, "tout": 2840, "ts": 1791523089.7080061, "chk": "incorrect", "code_len": 2678}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7713, "tout": 2527, "ts": 1791523281.835141, "chk": "ok", "code_len": 919}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8710, "tout": 622, "ts": 1791523300.5371091, "chk": null, "code_len": 919}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 4087, "started": 1791522904.246208}
{"ep": "ok-00168", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0295, "speedup": 1.0295, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 335.8, "calls": 2, "tokens_in": 10035, "tokens_out": 2702, "ctx_chars": 5984, "t_end": 1791523353.5884755, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0295, "lo95": 1.0283, "mean": 1.03, "ev_only": 1.0325, "ref_ms": 8.26157, "cand_ms": 8.0247, "n_trials": 132, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 237.46, "compile_s": 40.25, "r_error": "", "src_len": 1598, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4391, "tout": 1814, "ts": 1791523034.4570878, "chk": "ok", "code_len": 1598}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5644, "tout": 888, "ts": 1791523116.0977123, "chk": null, "code_len": 1598}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4391, "started": 1791523017.7981682}
{"ep": "ok-00151", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0008, "speedup": 1.0008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 396.9, "calls": 5, "tokens_in": 42402, "tokens_out": 5568, "ctx_chars": 9192, "t_end": 1791523354.5776508, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0008, "lo95": 0.9988, "mean": 1.0012, "ev_only": 1.0, "ref_ms": 7.97685, "cand_ms": 7.97045, "n_trials": 161, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 105.53, "compile_s": 3.32, "r_error": "", "src_len": 931, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 872, "ts": 1791522966.8951344, "chk": "incorrect", "code_len": 1505}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6636, "tout": 2080, "ts": 1791523138.571156, "chk": "incorrect", "code_len": 1552}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8849, "tout": 1158, "ts": 1791523158.5699687, "chk": "incorrect", "code_len": 1412}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 10141, "tout": 848, "ts": 1791523193.1058984, "chk": "incorrect", "code_len": 1382}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11145, "tout": 610, "ts": 1791523249.0048459, "chk": null, "code_len": 931}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 5631, "started": 1791522957.6966896}
{"ep": "ok-00145", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.8424, "speedup": 0.8424, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 416.6, "calls": 2, "tokens_in": 13203, "tokens_out": 6168, "ctx_chars": 6861, "t_end": 1791523355.8713827, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8424, "lo95": 0.8353, "mean": 0.9347, "ev_only": 0.8422, "ref_ms": 3.4706, "cand_ms": 4.11993, "n_trials": 195, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 276.4, "compile_s": 7.89, "r_error": "", "src_len": 3739, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 4174, "ts": 1791522975.8483484, "chk": "ok", "code_len": 3739}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7801, "tout": 1994, "ts": 1791523079.4476252, "chk": null, "code_len": 3739}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791522939.2289333}
{"ep": "ok-00208", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.7923, "speedup": 0.7923, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 185.4, "calls": 2, "tokens_in": 6379, "tokens_out": 1618, "ctx_chars": 1993, "t_end": 1791523356.601385, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7923, "lo95": 0.7822, "mean": 0.8425, "ev_only": 0.7922, "ref_ms": 32.32188, "cand_ms": 40.7955, "n_trials": 26, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 115.88, "compile_s": 17.32, "r_error": "", "src_len": 1463, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2698, "tout": 874, "ts": 1791523191.3756008, "chk": "ok", "code_len": 1463}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3681, "tout": 744, "ts": 1791523240.6146803, "chk": null, "code_len": 1463}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2698, "started": 1791523171.1735559}
{"ep": "ok-00195", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.0942, "speedup": 0.0942, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 268.7, "calls": 3, "tokens_in": 21093, "tokens_out": 3977, "ctx_chars": 8224, "t_end": 1791523358.1396544, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.0942, "lo95": 0.0922, "mean": 0.0938, "ev_only": 0.094, "ref_ms": 32.65574, "cand_ms": 346.75864, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2278, "r_wall_s": 22.62, "compile_s": 2.62, "r_error": "", "src_len": 3367, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 2127, "ts": 1791523110.1649754, "chk": "ok", "code_len": 3573}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7732, "tout": 112, "ts": 1791523321.3049269, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7868, "tout": 1738, "ts": 1791523335.4949107, "chk": null, "code_len": 3367}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5493, "started": 1791523089.4108648}
{"ep": "ok-00129", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0054, "speedup": 1.0054, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 503.3, "calls": 5, "tokens_in": 22763, "tokens_out": 8571, "ctx_chars": 1080, "t_end": 1791523361.0741527, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0054, "lo95": 1.0048, "mean": 1.0425, "ev_only": 1.0057, "ref_ms": 7.93789, "cand_ms": 7.89496, "n_trials": 135, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0004, "r_wall_s": 28.59, "compile_s": 1.98, "r_error": "", "src_len": 1008, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 2241, "ts": 1791522881.0688488, "chk": "incorrect", "code_len": 1636}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3450, "tout": 1841, "ts": 1791523049.62349, "chk": "incorrect", "code_len": 1665}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4727, "tout": 2434, "ts": 1791523102.3985643, "chk": "incorrect", "code_len": 1115}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 5770, "tout": 1405, "ts": 1791523318.7998297, "chk": "ok", "code_len": 1008}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 6698, "tout": 650, "ts": 1791523332.4556668, "chk": null, "code_len": 1008}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 2118, "started": 1791522857.7814846}
{"ep": "ok-00121", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 11.3442, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 556.4, "calls": 3, "tokens_in": 261535, "tokens_out": 41449, "ctx_chars": 182830, "t_end": 1791523363.4586294, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 11.3442, "lo95": 11.3013, "mean": 11.3856, "ev_only": 11.2896, "ref_ms": 4.06098, "cand_ms": 0.35798, "n_trials": 227, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9913, "r_wall_s": 69.79, "compile_s": 42.06, "r_error": "", "src_len": 14741, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78925, "tout": 24943, "ts": 1791523045.011364, "chk": "no_custom_kernel", "code_len": 14792}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 87329, "tout": 8298, "ts": 1791523156.6796038, "chk": "ok", "code_len": 14741}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 95281, "tout": 8208, "ts": 1791523293.6289666, "chk": null, "code_len": 14741}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 78925, "started": 1791522827.455416}
{"ep": "ok-00174", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.936, "speedup": 0.936, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 343.6, "calls": 2, "tokens_in": 19451, "tokens_out": 5761, "ctx_chars": 15603, "t_end": 1791523372.419432, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.936, "lo95": 0.9347, "mean": 0.9363, "ev_only": 0.9362, "ref_ms": 29.66648, "cand_ms": 31.69438, "n_trials": 46, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0179, "r_wall_s": 280.84, "compile_s": 20.51, "r_error": "", "src_len": 3434, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8530, "tout": 3568, "ts": 1791523060.4474814, "chk": "ok", "code_len": 3434}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10921, "tout": 2193, "ts": 1791523091.0232644, "chk": null, "code_len": 3434}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 8530, "started": 1791523028.8126297}
{"ep": "ok-00225", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.1666, "speedup": 1.1666, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 110.7, "calls": 3, "tokens_in": 13686, "tokens_out": 3854, "ctx_chars": 1884, "t_end": 1791523375.325506, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1666, "lo95": 1.1522, "mean": 0.9811, "ev_only": 1.165, "ref_ms": 5.67191, "cand_ms": 4.86212, "n_trials": 206, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.2833, "r_wall_s": 46.16, "compile_s": 2.07, "r_error": "", "src_len": 3377, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3057, "tout": 2092, "ts": 1791523304.820845, "chk": "ok", "code_len": 3377}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5261, "tout": 83, "ts": 1791523315.614395, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5368, "tout": 1679, "ts": 1791523329.0519965, "chk": null, "code_len": 3377}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3057, "started": 1791523284.9851665}
{"ep": "ok-00233", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 65.5, "calls": 1, "tokens_in": 1814, "tokens_out": 756, "ctx_chars": 495, "t_end": 1791523382.9582646, "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": 0.1187, "r_wall_s": 57.82, "compile_s": 2.03, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1111, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1814, "tout": 756, "ts": 1791523325.0291517, "chk": null, "code_len": 1111}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1814, "started": 1791523317.4339852}
{"ep": "ok-00199", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 8.057, "speedup": 8.057, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 258.3, "calls": 2, "tokens_in": 12093, "tokens_out": 21450, "ctx_chars": 0, "t_end": 1791523386.6458397, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 8.057, "lo95": 7.3325, "mean": 7.009, "ev_only": 8.171, "ref_ms": 4.95479, "cand_ms": 0.61497, "n_trials": 184, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 44.78, "compile_s": 14.71, "r_error": "", "src_len": 13562, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 14844, "ts": 1791523273.895058, "chk": "ok", "code_len": 13562}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9735, "tout": 6606, "ts": 1791523341.4730556, "chk": null, "code_len": 13562}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2358, "started": 1791523148.6803}
{"ep": "ok-00183", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.5701, "speedup": 1.5701, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 333.5, "calls": 2, "tokens_in": 159252, "tokens_out": 10271, "ctx_chars": 182830, "t_end": 1791523386.6969836, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.5701, "lo95": 1.5693, "mean": 1.5688, "ev_only": 1.5685, "ref_ms": 8.1691, "cand_ms": 5.20293, "n_trials": 189, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9782, "r_wall_s": 47.16, "compile_s": 2.33, "r_error": "", "src_len": 4224, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78292, "tout": 7209, "ts": 1791523119.2534986, "chk": "ok", "code_len": 4271}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 80960, "tout": 3062, "ts": 1791523339.4638062, "chk": null, "code_len": 4224}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78292, "started": 1791523053.2463737}
{"ep": "ok-00234", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.2988, "speedup": 0.2988, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 69.9, "calls": 1, "tokens_in": 5329, "tokens_out": 2119, "ctx_chars": 6513, "t_end": 1791523388.509498, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.2988, "lo95": 0.2949, "mean": 0.313, "ev_only": 0.2966, "ref_ms": 3.4932, "cand_ms": 11.69156, "n_trials": 113, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0817, "r_wall_s": 51.69, "compile_s": 2.92, "r_error": "", "src_len": 4181, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5329, "tout": 2119, "ts": 1791523336.7965872, "chk": null, "code_len": 4181}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5329, "started": 1791523318.6087792}
{"ep": "ok-00158", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.8996, "speedup": 0.8996, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 410.5, "calls": 3, "tokens_in": 16674, "tokens_out": 5611, "ctx_chars": 2425, "t_end": 1791523388.995004, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8996, "lo95": 0.8909, "mean": 0.8376, "ev_only": 0.8997, "ref_ms": 4.02012, "cand_ms": 4.469, "n_trials": 199, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0853, "r_wall_s": 292.36, "compile_s": 97.13, "r_error": "", "src_len": 4742, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 3287, "ts": 1791523010.659465, "chk": "ok", "code_len": 4742}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6671, "tout": 36, "ts": 1791523077.839453, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6731, "tout": 2288, "ts": 1791523096.6027792, "chk": null, "code_len": 4742}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3272, "started": 1791522978.4906192}
{"ep": "ok-00180", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0273, "speedup": 1.0273, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 351.5, "calls": 2, "tokens_in": 6048, "tokens_out": 5598, "ctx_chars": 495, "t_end": 1791523393.1516442, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0273, "lo95": 1.0268, "mean": 1.0273, "ev_only": 1.0274, "ref_ms": 29.6156, "cand_ms": 28.82746, "n_trials": 42, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0242, "r_wall_s": 61.04, "compile_s": 2.81, "r_error": "", "src_len": 3297, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1878, "tout": 3710, "ts": 1791523091.9417217, "chk": "ok", "code_len": 3297}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4170, "tout": 1888, "ts": 1791523331.275234, "chk": null, "code_len": 3297}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1878, "started": 1791523041.6192431}
{"ep": "ok-00155", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 7.6699, "speedup": 7.6699, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 423.4, "calls": 3, "tokens_in": 33451, "tokens_out": 28392, "ctx_chars": 10587, "t_end": 1791523399.796201, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.6699, "lo95": 7.6578, "mean": 7.6539, "ev_only": 7.6963, "ref_ms": 31.48639, "cand_ms": 4.10519, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9994, "r_wall_s": 86.24, "compile_s": 12.11, "r_error": "", "src_len": 8699, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 19284, "ts": 1791523155.1245022, "chk": "no_custom_kernel", "code_len": 8754}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11316, "tout": 4868, "ts": 1791523270.458602, "chk": "ok", "code_len": 8699}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15771, "tout": 4240, "ts": 1791523313.4519567, "chk": null, "code_len": 8699}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6364, "started": 1791522976.4154184}
{"ep": "ok-00227", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.9878, "speedup": 0.9878, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 128.1, "calls": 1, "tokens_in": 1743, "tokens_out": 1603, "ctx_chars": 0, "t_end": 1791523400.811481, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9878, "lo95": 0.987, "mean": 0.9891, "ev_only": 0.9893, "ref_ms": 29.81749, "cand_ms": 30.18591, "n_trials": 40, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.069, "r_wall_s": 112.44, "compile_s": 43.93, "r_error": "", "src_len": 3302, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1743, "tout": 1603, "ts": 1791523287.860055, "chk": null, "code_len": 3302}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1743, "started": 1791523272.723667}
{"ep": "ok-00231", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.797, "speedup": 0.797, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 93.8, "calls": 2, "tokens_in": 13109, "tokens_out": 5977, "ctx_chars": 6513, "t_end": 1791523404.1633108, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.797, "lo95": 0.7954, "mean": 0.7972, "ev_only": 0.7969, "ref_ms": 3.27812, "cand_ms": 4.11303, "n_trials": 203, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0034, "r_wall_s": 20.28, "compile_s": 3.4, "r_error": "", "src_len": 3778, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 4009, "ts": 1791523343.9778795, "chk": "ok", "code_len": 3778}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7778, "tout": 1968, "ts": 1791523383.8651135, "chk": null, "code_len": 3778}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5331, "started": 1791523310.3208039}
{"ep": "ok-00146", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0039, "speedup": 1.0039, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 462.9, "calls": 4, "tokens_in": 27594, "tokens_out": 9438, "ctx_chars": 5630, "t_end": 1791523404.2004766, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0039, "lo95": 1.0037, "mean": 1.004, "ev_only": 1.0047, "ref_ms": 7.91685, "cand_ms": 7.88585, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 92.02, "compile_s": 2.25, "r_error": "", "src_len": 982, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4087, "tout": 3087, "ts": 1791522968.4588022, "chk": "incorrect", "code_len": 2931}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6136, "tout": 2831, "ts": 1791523021.4912345, "chk": "incorrect", "code_len": 2975}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8148, "tout": 2811, "ts": 1791523083.8194432, "chk": "ok", "code_len": 982}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9223, "tout": 709, "ts": 1791523312.0693634, "chk": null, "code_len": 982}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 4087, "started": 1791522941.341661}
{"ep": "ok-00209", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0332, "speedup": 1.0332, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 228.2, "calls": 2, "tokens_in": 5118, "tokens_out": 2994, "ctx_chars": 495, "t_end": 1791523404.2517445, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0332, "lo95": 1.0326, "mean": 1.0493, "ev_only": 1.0322, "ref_ms": 8.15529, "cand_ms": 7.89353, "n_trials": 148, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 50.76, "compile_s": 2.16, "r_error": "", "src_len": 1946, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1858, "tout": 1900, "ts": 1791523193.9081736, "chk": "ok", "code_len": 1946}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3260, "tout": 1094, "ts": 1791523219.1668944, "chk": null, "code_len": 1946}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1858, "started": 1791523176.0253437}
{"ep": "ok-00147", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0191, "speedup": 1.0191, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 457.9, "calls": 3, "tokens_in": 25433, "tokens_out": 2996, "ctx_chars": 12352, "t_end": 1791523405.3343008, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0191, "lo95": 1.0187, "mean": 1.019, "ev_only": 1.0187, "ref_ms": 29.82747, "cand_ms": 29.26829, "n_trials": 49, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0396, "r_wall_s": 297.19, "compile_s": 45.62, "r_error": "", "src_len": 2735, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1577, "ts": 1791522962.0760655, "chk": "ok", "code_len": 2872}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9016, "tout": 50, "ts": 1791523096.5325067, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9090, "tout": 1369, "ts": 1791523107.6184363, "chk": null, "code_len": 2735}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7327, "started": 1791522947.414832}
{"ep": "ok-00220", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.7625, "speedup": 0.7625, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 178.6, "calls": 3, "tokens_in": 250628, "tokens_out": 10151, "ctx_chars": 182830, "t_end": 1791523411.7702777, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7625, "lo95": 0.7617, "mean": 0.763, "ev_only": 0.7613, "ref_ms": 8.23131, "cand_ms": 10.7958, "n_trials": 131, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9973, "r_wall_s": 43.61, "compile_s": 2.54, "r_error": "", "src_len": 3119, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78367, "tout": 6739, "ts": 1791523303.4048562, "chk": "incorrect", "code_len": 3110}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 85239, "tout": 1671, "ts": 1791523332.6559541, "chk": "ok", "code_len": 3119}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 87022, "tout": 1741, "ts": 1791523368.1338437, "chk": null, "code_len": 3119}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78367, "started": 1791523233.164305}
{"ep": "ok-00241", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.1015, "speedup": 1.1015, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 62.8, "calls": 1, "tokens_in": 6776, "tokens_out": 1049, "ctx_chars": 11064, "t_end": 1791523416.3626657, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1015, "lo95": 1.1011, "mean": 1.1018, "ev_only": 1.1015, "ref_ms": 22.25052, "cand_ms": 20.20059, "n_trials": 57, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0403, "r_wall_s": 51.93, "compile_s": 2.4, "r_error": "", "src_len": 2065, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6776, "tout": 1049, "ts": 1791523364.2140663, "chk": null, "code_len": 2065}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6776, "started": 1791523353.5888402}
{"ep": "ok-00232", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0366, "speedup": 1.0366, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 110.3, "calls": 2, "tokens_in": 10253, "tokens_out": 2972, "ctx_chars": 5984, "t_end": 1791523420.6576595, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0366, "lo95": 1.035, "mean": 1.0382, "ev_only": 1.0365, "ref_ms": 8.2535, "cand_ms": 7.96239, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0038, "r_wall_s": 76.68, "compile_s": 2.59, "r_error": "", "src_len": 1994, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4391, "tout": 1938, "ts": 1791523327.7695, "chk": "ok", "code_len": 1994}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5862, "tout": 1034, "ts": 1791523343.9541082, "chk": null, "code_len": 1994}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4391, "started": 1791523310.3495476}
{"ep": "ok-00141", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 3.6763, "speedup": 3.6763, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 491.4, "calls": 3, "tokens_in": 21451, "tokens_out": 26445, "ctx_chars": 696, "t_end": 1791523423.006627, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.6763, "lo95": 3.615, "mean": 4.1024, "ev_only": 3.6888, "ref_ms": 31.88235, "cand_ms": 8.67247, "n_trials": 52, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9968, "r_wall_s": 88.97, "compile_s": 15.67, "r_error": "", "src_len": 9073, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2199, "tout": 16975, "ts": 1791523092.8084762, "chk": "no_custom_kernel", "code_len": 9097}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7309, "tout": 5025, "ts": 1791523288.8561094, "chk": "ok", "code_len": 9073}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11943, "tout": 4445, "ts": 1791523334.0069718, "chk": null, "code_len": 9073}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2199, "started": 1791522931.5931225}
{"ep": "ok-00244", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 69.8, "calls": 1, "tokens_in": 1876, "tokens_out": 1876, "ctx_chars": 495, "t_end": 1791523426.441384, "error": "RuntimeError: Error building extension 'relu_gn_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_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": 48.98, "compile_s": 48.98, "r_error": "RuntimeError: Error building extension 'relu_gn_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "src_len": 3808, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1876, "tout": 1876, "ts": 1791523377.413947, "chk": null, "code_len": 3808}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1876, "started": 1791523356.6016643}
{"ep": "ok-00217", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0004, "speedup": 1.0004, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 210.1, "calls": 3, "tokens_in": 18408, "tokens_out": 3219, "ctx_chars": 7758, "t_end": 1791523428.3122525, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0004, "lo95": 1.0001, "mean": 1.0006, "ev_only": 1.001, "ref_ms": 8.02523, "cand_ms": 8.02232, "n_trials": 133, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0173, "r_wall_s": 48.65, "compile_s": 3.26, "r_error": "", "src_len": 3106, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4947, "tout": 1623, "ts": 1791523232.2358308, "chk": "ok", "code_len": 3106}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6682, "tout": 73, "ts": 1791523367.221883, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6779, "tout": 1523, "ts": 1791523379.581247, "chk": null, "code_len": 3106}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4947, "started": 1791523218.247515}
{"ep": "ok-00137", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.9997, "speedup": 0.9997, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 521.9, "calls": 5, "tokens_in": 25167, "tokens_out": 4516, "ctx_chars": 3492, "t_end": 1791523429.333555, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9997, "lo95": 0.9989, "mean": 0.9995, "ev_only": 0.9999, "ref_ms": 7.95174, "cand_ms": 7.95403, "n_trials": 152, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 62.28, "compile_s": 2.54, "r_error": "", "src_len": 874, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3009, "tout": 615, "ts": 1791522914.1480224, "chk": "incorrect", "code_len": 1074}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3757, "tout": 657, "ts": 1791523071.8266587, "chk": "incorrect", "code_len": 1123}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4547, "tout": 1762, "ts": 1791523105.6258035, "chk": "incorrect", "code_len": 1187}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 6442, "tout": 813, "ts": 1791523313.2785654, "chk": "incorrect", "code_len": 1080}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7412, "tout": 669, "ts": 1791523367.0274405, "chk": null, "code_len": 874}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 3009, "started": 1791522907.4365594}
{"ep": "ok-00216", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 4.3609, "speedup": 4.3609, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.9, "calls": 2, "tokens_in": 11616, "tokens_out": 16059, "ctx_chars": 2425, "t_end": 1791523431.435272, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.3609, "lo95": 4.3443, "mean": 4.3411, "ev_only": 4.474, "ref_ms": 4.0466, "cand_ms": 0.92794, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 46.04, "compile_s": 2.18, "r_error": "", "src_len": 8882, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 11495, "ts": 1791523315.409392, "chk": "ok", "code_len": 8882}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8342, "tout": 4564, "ts": 1791523385.3470218, "chk": null, "code_len": 8882}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3274, "started": 1791523215.5781784}
{"ep": "ok-00191", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0379, "speedup": 1.0379, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 366.4, "calls": 2, "tokens_in": 10394, "tokens_out": 2958, "ctx_chars": 6332, "t_end": 1791523434.476925, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0379, "lo95": 1.0374, "mean": 1.061, "ev_only": 1.0384, "ref_ms": 8.27072, "cand_ms": 7.96876, "n_trials": 155, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 62.93, "compile_s": 1.98, "r_error": "", "src_len": 1704, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4462, "tout": 2050, "ts": 1791523087.7506342, "chk": "ok", "code_len": 1704}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5932, "tout": 908, "ts": 1791523371.5012581, "chk": null, "code_len": 1704}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4462, "started": 1791523068.1163347}
{"ep": "ok-00235", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.4024, "speedup": 1.4024, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 114.8, "calls": 2, "tokens_in": 6123, "tokens_out": 6495, "ctx_chars": 0, "t_end": 1791523437.5083618, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4024, "lo95": 1.4001, "mean": 1.3995, "ev_only": 1.4049, "ref_ms": 8.35671, "cand_ms": 5.95884, "n_trials": 180, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 28.4, "compile_s": 3.08, "r_error": "", "src_len": 3912, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 4118, "ts": 1791523358.0616353, "chk": "ok", "code_len": 3912}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4321, "tout": 2377, "ts": 1791523409.0876572, "chk": null, "code_len": 3912}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791523322.6918416}
{"ep": "ok-00226", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 65.5399, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 173.5, "calls": 2, "tokens_in": 7064, "tokens_out": 7951, "ctx_chars": 495, "t_end": 1791523438.6261792, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 65.5399, "lo95": 63.7082, "mean": 59.2644, "ev_only": 68.6645, "ref_ms": 22.31762, "cand_ms": 0.34052, "n_trials": 76, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 87.49, "compile_s": 12.2, "r_error": "", "src_len": 4944, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1962, "tout": 5477, "ts": 1791523312.8324003, "chk": "ok", "code_len": 4944}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5102, "tout": 2474, "ts": 1791523350.8732178, "chk": null, "code_len": 4944}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1962, "started": 1791523265.1358716}
{"ep": "ok-00229", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0197, "speedup": 1.0197, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 141.1, "calls": 1, "tokens_in": 5681, "tokens_out": 4200, "ctx_chars": 9128, "t_end": 1791523438.9255524, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0197, "lo95": 1.0194, "mean": 1.0198, "ev_only": 1.02, "ref_ms": 29.64895, "cand_ms": 29.07549, "n_trials": 49, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.039, "r_wall_s": 102.94, "compile_s": 2.95, "r_error": "", "src_len": 2573, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5681, "tout": 4200, "ts": 1791523335.4652522, "chk": null, "code_len": 2573}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5681, "started": 1791523297.871946}
{"ep": "ok-00236", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.003, "speedup": 1.003, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 110.5, "calls": 2, "tokens_in": 11990, "tokens_out": 5224, "ctx_chars": 7261, "t_end": 1791523442.4291422, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.003, "lo95": 1.0003, "mean": 0.9897, "ev_only": 1.0047, "ref_ms": 8.16157, "cand_ms": 8.13748, "n_trials": 89, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0069, "r_wall_s": 33.9, "compile_s": 2.86, "r_error": "", "src_len": 3442, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4818, "tout": 3443, "ts": 1791523386.4970102, "chk": "ok", "code_len": 3532}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7172, "tout": 1781, "ts": 1791523408.4549654, "chk": null, "code_len": 3442}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4818, "started": 1791523352.4424193}
{"ep": "ok-00170", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.109, "speedup": 0.109, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 419.9, "calls": 4, "tokens_in": 19516, "tokens_out": 6147, "ctx_chars": 495, "t_end": 1791523442.6841068, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.109, "lo95": 0.1084, "mean": 0.1087, "ev_only": 0.1089, "ref_ms": 31.65386, "cand_ms": 290.40832, "n_trials": 12, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.3074, "r_wall_s": 104.55, "compile_s": 45.04, "r_error": "", "src_len": 4306, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2082, "tout": 2105, "ts": 1791523043.0440102, "chk": "forbidden", "code_len": 4149}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4348, "tout": 1987, "ts": 1791523077.3491, "chk": "ok", "code_len": 4483}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6447, "tout": 168, "ts": 1791523322.2738483, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6639, "tout": 1887, "ts": 1791523338.1104622, "chk": null, "code_len": 4306}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 2082, "started": 1791523022.7375443}
{"ep": "ok-00240", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0383, "speedup": 1.0383, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 96.8, "calls": 2, "tokens_in": 10021, "tokens_out": 2708, "ctx_chars": 5984, "t_end": 1791523444.392109, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0383, "lo95": 1.0362, "mean": 1.06, "ev_only": 1.0323, "ref_ms": 8.38074, "cand_ms": 8.07163, "n_trials": 204, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0036, "r_wall_s": 40.9, "compile_s": 2.18, "r_error": "", "src_len": 1630, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4391, "tout": 1842, "ts": 1791523369.0828402, "chk": "ok", "code_len": 1630}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5630, "tout": 866, "ts": 1791523403.4581265, "chk": null, "code_len": 1630}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4391, "started": 1791523347.596639}
{"ep": "ok-00165", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8048, "speedup": 0.8048, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 444.1, "calls": 3, "tokens_in": 260197, "tokens_out": 15495, "ctx_chars": 182830, "t_end": 1791523448.5672631, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8048, "lo95": 0.8005, "mean": 0.81, "ev_only": 0.8073, "ref_ms": 8.29428, "cand_ms": 10.30636, "n_trials": 113, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 107.38, "compile_s": 2.97, "r_error": "", "src_len": 3654, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78367, "tout": 11238, "ts": 1791523132.3029811, "chk": "ok", "code_len": 3735}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 89717, "tout": 2263, "ts": 1791523173.0968535, "chk": "incorrect", "code_len": 3652}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 92113, "tout": 1994, "ts": 1791523205.6456234, "chk": null, "code_len": 3654}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "incorrect", null], "first_tin": 78367, "started": 1791523004.4705884}
{"ep": "ok-00230", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.7887, "speedup": 0.7887, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 172.9, "calls": 3, "tokens_in": 18724, "tokens_out": 12929, "ctx_chars": 0, "t_end": 1791523470.9571586, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7887, "lo95": 0.7396, "mean": 0.8262, "ev_only": 0.7873, "ref_ms": 29.92426, "cand_ms": 37.94084, "n_trials": 49, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0334, "r_wall_s": 38.77, "compile_s": 9.51, "r_error": "", "src_len": 3550, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 8134, "ts": 1791523368.36082, "chk": "incorrect", "code_len": 7067}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6879, "tout": 3021, "ts": 1791523406.4645581, "chk": "ok", "code_len": 3629}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8926, "tout": 1774, "ts": 1791523432.1670218, "chk": null, "code_len": 3550}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2919, "started": 1791523298.0799966}
{"ep": "ok-00246", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.7831, "speedup": 0.7831, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 113.1, "calls": 2, "tokens_in": 6354, "tokens_out": 1606, "ctx_chars": 1993, "t_end": 1791523474.1909304, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7831, "lo95": 0.7771, "mean": 0.8198, "ev_only": 0.7828, "ref_ms": 48.88026, "cand_ms": 62.42185, "n_trials": 25, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 47.74, "compile_s": 15.39, "r_error": "", "src_len": 1487, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2698, "tout": 849, "ts": 1791523369.2852309, "chk": "ok", "code_len": 1487}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3656, "tout": 757, "ts": 1791523426.4206004, "chk": null, "code_len": 1487}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2698, "started": 1791523361.0745304}
{"ep": "ok-00189", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 7.4183, "speedup": 7.4183, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 419.9, "calls": 2, "tokens_in": 8936, "tokens_out": 18903, "ctx_chars": 696, "t_end": 1791523479.6190288, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.4183, "lo95": 7.1052, "mean": 8.7585, "ev_only": 7.4662, "ref_ms": 33.29368, "cand_ms": 4.48808, "n_trials": 40, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9978, "r_wall_s": 216.51, "compile_s": 11.68, "r_error": "", "src_len": 8104, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2199, "tout": 15008, "ts": 1791523194.7214243, "chk": "ok", "code_len": 8104}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6737, "tout": 3895, "ts": 1791523263.0662973, "chk": null, "code_len": 8104}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2199, "started": 1791523059.673427}
{"ep": "ok-00219", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.7936, "speedup": 0.7936, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 267.2, "calls": 4, "tokens_in": 35385, "tokens_out": 20132, "ctx_chars": 495, "t_end": 1791523497.7725852, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7936, "lo95": 0.7602, "mean": 0.7933, "ev_only": 0.7929, "ref_ms": 29.8774, "cand_ms": 37.64675, "n_trials": 45, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0336, "r_wall_s": 24.38, "compile_s": 2.87, "r_error": "", "src_len": 3753, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3052, "tout": 8174, "ts": 1791523306.1733801, "chk": "incorrect", "code_len": 7682}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7311, "tout": 5181, "ts": 1791523358.779726, "chk": "incorrect", "code_len": 7753}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11467, "tout": 4473, "ts": 1791523430.9079978, "chk": "ok", "code_len": 3753}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13555, "tout": 2304, "ts": 1791523473.2696514, "chk": null, "code_len": 3753}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 3052, "started": 1791523230.6052463}
{"ep": "ok-00192", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.345, "speedup": 0.345, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 440.0, "calls": 2, "tokens_in": 12092, "tokens_out": 22668, "ctx_chars": 495, "t_end": 1791523513.811524, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.345, "lo95": 0.3435, "mean": 0.3513, "ev_only": 0.3421, "ref_ms": 3.56674, "cand_ms": 10.33951, "n_trials": 114, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9979, "r_wall_s": 75.48, "compile_s": 19.05, "r_error": "", "src_len": 11490, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2761, "tout": 16658, "ts": 1791523216.702952, "chk": "ok", "code_len": 11506}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9331, "tout": 6010, "ts": 1791523438.302457, "chk": null, "code_len": 11490}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2761, "started": 1791523073.7759418}
{"ep": "ok-00181", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7079, "speedup": 0.7079, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 471.1, "calls": 5, "tokens_in": 53841, "tokens_out": 9405, "ctx_chars": 7010, "t_end": 1791523519.2296584, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7079, "lo95": 0.6525, "mean": 0.7229, "ev_only": 0.7067, "ref_ms": 23.41849, "cand_ms": 33.08023, "n_trials": 21, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0342, "r_wall_s": 72.16, "compile_s": 23.66, "r_error": "", "src_len": 3733, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5751, "tout": 2781, "ts": 1791523079.000183, "chk": "incorrect", "code_len": 5751}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8665, "tout": 2900, "ts": 1791523174.9634442, "chk": "incorrect", "code_len": 5881}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11698, "tout": 1994, "ts": 1791523230.5441167, "chk": "ok", "code_len": 3733}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13801, "tout": 78, "ts": 1791523432.979577, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13926, "tout": 1652, "ts": 1791523446.6737185, "chk": null, "code_len": 3733}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5751, "started": 1791523048.1436265}
{"ep": "ok-00222", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.9937, "speedup": 0.9937, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 271.2, "calls": 3, "tokens_in": 17313, "tokens_out": 2898, "ctx_chars": 7333, "t_end": 1791523519.3521426, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9937, "lo95": 0.9927, "mean": 0.9934, "ev_only": 0.9942, "ref_ms": 8.10346, "cand_ms": 8.15494, "n_trials": 151, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0175, "r_wall_s": 74.52, "compile_s": 20.52, "r_error": "", "src_len": 2884, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4705, "tout": 1444, "ts": 1791523260.177464, "chk": "ok", "code_len": 2884}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6261, "tout": 62, "ts": 1791523432.9859154, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6347, "tout": 1392, "ts": 1791523444.6875937, "chk": null, "code_len": 2884}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4705, "started": 1791523248.124415}
{"ep": "ok-00159", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0041, "speedup": 1.0041, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 545.8, "calls": 4, "tokens_in": 29340, "tokens_out": 7086, "ctx_chars": 9192, "t_end": 1791523526.974588, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0041, "lo95": 1.0032, "mean": 1.0232, "ev_only": 1.0044, "ref_ms": 7.92304, "cand_ms": 7.89065, "n_trials": 111, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 33.73, "compile_s": 3.69, "r_error": "", "src_len": 965, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5633, "tout": 1723, "ts": 1791522996.7650723, "chk": "incorrect", "code_len": 1511}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6903, "tout": 3503, "ts": 1791523093.9773552, "chk": "incorrect", "code_len": 993}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7957, "tout": 1245, "ts": 1791523206.2739491, "chk": "ok", "code_len": 965}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8847, "tout": 615, "ts": 1791523493.13908, "chk": null, "code_len": 965}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5633, "started": 1791522981.129459}
{"ep": "ok-00212", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0338, "speedup": 1.0338, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 348.0, "calls": 2, "tokens_in": 14400, "tokens_out": 3228, "ctx_chars": 9546, "t_end": 1791523527.1494594, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0338, "lo95": 1.0331, "mean": 1.0357, "ev_only": 1.0342, "ref_ms": 8.23481, "cand_ms": 7.96593, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0024, "r_wall_s": 173.71, "compile_s": 2.14, "r_error": "", "src_len": 1622, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5935, "tout": 2418, "ts": 1791523202.0960171, "chk": "ok", "code_len": 1622}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8465, "tout": 810, "ts": 1791523218.821976, "chk": null, "code_len": 1622}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5935, "started": 1791523179.1594934}
{"ep": "ok-00218", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.8032, "speedup": 0.8032, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 306.1, "calls": 2, "tokens_in": 13623, "tokens_out": 1339, "ctx_chars": 10587, "t_end": 1791523527.8849561, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8032, "lo95": 0.8006, "mean": 0.8412, "ev_only": 0.8034, "ref_ms": 31.92894, "cand_ms": 39.75091, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 34.61, "compile_s": 3.74, "r_error": "", "src_len": 962, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 790, "ts": 1791523231.0848505, "chk": "ok", "code_len": 962}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7261, "tout": 549, "ts": 1791523493.1719224, "chk": null, "code_len": 962}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6362, "started": 1791523221.8169222}
{"ep": "ok-00239", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.0931, "speedup": 0.0931, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.4, "calls": 5, "tokens_in": 24991, "tokens_out": 5852, "ctx_chars": 0, "t_end": 1791523550.8243237, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.0931, "lo95": 0.0926, "mean": 0.0933, "ev_only": 0.0931, "ref_ms": 31.2541, "cand_ms": 335.7612, "n_trials": 10, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3123, "r_wall_s": 114.31, "compile_s": 11.07, "r_error": "", "src_len": 2988, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1949, "tout": 1478, "ts": 1791523349.6808212, "chk": "forbidden", "code_len": 2583}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3588, "tout": 1438, "ts": 1791523379.2536688, "chk": "runtime_error", "code_len": 2940}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5406, "tout": 1469, "ts": 1791523399.4446816, "chk": "ok", "code_len": 2988}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6987, "tout": 27, "ts": 1791523424.605071, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7061, "tout": 1440, "ts": 1791523436.4878051, "chk": null, "code_len": 2988}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "runtime_error", "ok", "no_code", null], "first_tin": 1949, "started": 1791523335.4053185}
{"ep": "ok-00197", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.6333, "speedup": 0.6333, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 449.1, "calls": 3, "tokens_in": 19322, "tokens_out": 12222, "ctx_chars": 0, "t_end": 1791523553.6109896, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6333, "lo95": 0.6304, "mean": 0.6388, "ev_only": 0.6339, "ref_ms": 16.47123, "cand_ms": 26.00771, "n_trials": 53, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0587, "r_wall_s": 99.16, "compile_s": 22.57, "r_error": "", "src_len": 3960, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 6979, "ts": 1791523165.2125497, "chk": "incorrect", "code_len": 7145}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7070, "tout": 3211, "ts": 1791523221.1449058, "chk": "ok", "code_len": 3960}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9333, "tout": 2032, "ts": 1791523454.4299936, "chk": null, "code_len": 3960}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2919, "started": 1791523104.5048501}
{"ep": "ok-00238", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.9968, "speedup": 0.9968, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 224.7, "calls": 3, "tokens_in": 22431, "tokens_out": 2947, "ctx_chars": 10823, "t_end": 1791523558.432356, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9968, "lo95": 0.996, "mean": 0.9927, "ev_only": 0.9953, "ref_ms": 8.05284, "cand_ms": 8.07875, "n_trials": 172, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0172, "r_wall_s": 56.92, "compile_s": 4.41, "r_error": "", "src_len": 2884, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1542, "ts": 1791523347.1134286, "chk": "ok", "code_len": 2884}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8016, "tout": 13, "ts": 1791523490.0513315, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8053, "tout": 1392, "ts": 1791523501.275263, "chk": null, "code_len": 2884}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791523333.7695336}
{"ep": "ok-00263", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0086, "speedup": 1.0086, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 145.5, "calls": 2, "tokens_in": 12057, "tokens_out": 5096, "ctx_chars": 7549, "t_end": 1791523561.8485203, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0086, "lo95": 1.0053, "mean": 1.0089, "ev_only": 1.0085, "ref_ms": 8.08073, "cand_ms": 8.01189, "n_trials": 144, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0118, "r_wall_s": 62.08, "compile_s": 5.02, "r_error": "", "src_len": 3654, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4870, "tout": 3222, "ts": 1791523445.2866588, "chk": "ok", "code_len": 3654}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7187, "tout": 1874, "ts": 1791523499.611049, "chk": null, "code_len": 3654}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4870, "started": 1791523416.3630147}
{"ep": "ok-00260", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0074, "speedup": 1.0074, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.0, "calls": 2, "tokens_in": 15029, "tokens_out": 4863, "ctx_chars": 10823, "t_end": 1791523565.2653437, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0074, "lo95": 1.0068, "mean": 1.0089, "ev_only": 1.0073, "ref_ms": 8.03108, "cand_ms": 7.97184, "n_trials": 147, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0075, "r_wall_s": 55.07, "compile_s": 6.79, "r_error": "", "src_len": 3486, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 3048, "ts": 1791523446.349304, "chk": "ok", "code_len": 3486}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8665, "tout": 1815, "ts": 1791523509.9340398, "chk": null, "code_len": 3486}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6364, "started": 1791523404.252051}
{"ep": "ok-00205", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0026, "speedup": 1.0026, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 440.4, "calls": 4, "tokens_in": 16905, "tokens_out": 8480, "ctx_chars": 1080, "t_end": 1791523575.6605968, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0026, "lo95": 1.0018, "mean": 1.0023, "ev_only": 1.0052, "ref_ms": 8.01398, "cand_ms": 7.99327, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 147.94, "compile_s": 6.35, "r_error": "", "src_len": 1040, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 2585, "ts": 1791523158.1431026, "chk": "incorrect", "code_len": 2267}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3826, "tout": 2900, "ts": 1791523221.029119, "chk": "incorrect", "code_len": 1093}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4943, "tout": 2177, "ts": 1791523394.082913, "chk": "ok", "code_len": 1040}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6018, "tout": 818, "ts": 1791523427.694894, "chk": null, "code_len": 1040}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2118, "started": 1791523135.247304}
{"ep": "ok-00201", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.6197, "speedup": 0.6197, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 448.2, "calls": 5, "tokens_in": 58056, "tokens_out": 9848, "ctx_chars": 9125, "t_end": 1791523578.0336003, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.6197, "lo95": 0.6145, "mean": 0.6186, "ev_only": 0.6203, "ref_ms": 16.49179, "cand_ms": 26.61259, "n_trials": 52, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0591, "r_wall_s": 121.04, "compile_s": 22.97, "r_error": "", "src_len": 4176, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6570, "tout": 2675, "ts": 1791523151.509244, "chk": "incorrect", "code_len": 5597}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9378, "tout": 2853, "ts": 1791523184.757218, "chk": "incorrect", "code_len": 5717}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12364, "tout": 2337, "ts": 1791523217.4161384, "chk": "ok", "code_len": 4176}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14810, "tout": 77, "ts": 1791523441.5717719, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 14934, "tout": 1906, "ts": 1791523456.963574, "chk": null, "code_len": 4176}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 6570, "started": 1791523129.8556116}
{"ep": "ok-00182", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.99, "speedup": 0.99, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 530.8, "calls": 3, "tokens_in": 8914, "tokens_out": 3285, "ctx_chars": 0, "t_end": 1791523579.9691079, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.99, "lo95": 0.9897, "mean": 0.9898, "ev_only": 0.9901, "ref_ms": 29.6533, "cand_ms": 29.9531, "n_trials": 51, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.1203, "r_wall_s": 94.45, "compile_s": 45.29, "r_error": "", "src_len": 3295, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1743, "tout": 1704, "ts": 1791523074.0878105, "chk": "ok", "code_len": 3443}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3559, "tout": 29, "ts": 1791523335.6131282, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3612, "tout": 1552, "ts": 1791523348.0315535, "chk": null, "code_len": 3295}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1743, "started": 1791523049.2167478}
{"ep": "ok-00202", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9361, "speedup": 0.9361, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 452.4, "calls": 2, "tokens_in": 16615, "tokens_out": 4294, "ctx_chars": 12352, "t_end": 1791523583.703432, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9361, "lo95": 0.9346, "mean": 0.9359, "ev_only": 0.9364, "ref_ms": 29.68565, "cand_ms": 31.71207, "n_trials": 38, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0194, "r_wall_s": 318.6, "compile_s": 2.0, "r_error": "", "src_len": 2795, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7329, "tout": 2813, "ts": 1791523155.4269707, "chk": "ok", "code_len": 2795}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9286, "tout": 1481, "ts": 1791523264.5706115, "chk": null, "code_len": 2795}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7329, "started": 1791523131.2800329}
{"ep": "ok-00259", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0316, "speedup": 1.0316, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 186.6, "calls": 2, "tokens_in": 4769, "tokens_out": 2608, "ctx_chars": 0, "t_end": 1791523590.7697282, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0316, "lo95": 1.0315, "mean": 1.0314, "ev_only": 1.0322, "ref_ms": 8.14727, "cand_ms": 7.89733, "n_trials": 164, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 57.21, "compile_s": 17.76, "r_error": "", "src_len": 1639, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 1687, "ts": 1791523428.542442, "chk": "ok", "code_len": 1639}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3044, "tout": 921, "ts": 1791523533.4058363, "chk": null, "code_len": 1639}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791523404.2007513}
{"ep": "ok-00245", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7539, "speedup": 0.7539, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 233.2, "calls": 3, "tokens_in": 17811, "tokens_out": 6354, "ctx_chars": 2425, "t_end": 1791523591.323904, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7539, "lo95": 0.7212, "mean": 0.7448, "ev_only": 0.7599, "ref_ms": 4.00027, "cand_ms": 5.30607, "n_trials": 165, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0827, "r_wall_s": 87.6, "compile_s": 56.58, "r_error": "", "src_len": 4967, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 3856, "ts": 1791523397.2460678, "chk": "ok", "code_len": 5004}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7240, "tout": 35, "ts": 1791523483.7042606, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7299, "tout": 2463, "ts": 1791523503.6059148, "chk": null, "code_len": 4967}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3272, "started": 1791523358.139996}
{"ep": "ok-00266", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.8019, "speedup": 0.8019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 167.5, "calls": 2, "tokens_in": 13792, "tokens_out": 1493, "ctx_chars": 10587, "t_end": 1791523593.9711185, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8019, "lo95": 0.8009, "mean": 0.8029, "ev_only": 0.8019, "ref_ms": 31.5206, "cand_ms": 39.30768, "n_trials": 37, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 62.4, "compile_s": 17.37, "r_error": "", "src_len": 909, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 959, "ts": 1791523437.921809, "chk": "ok", "code_len": 909}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7430, "tout": 534, "ts": 1791523531.4658587, "chk": null, "code_len": 909}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6362, "started": 1791523426.441927}
{"ep": "ok-00204", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 7.2861, "speedup": 7.2861, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 460.6, "calls": 3, "tokens_in": 18778, "tokens_out": 23012, "ctx_chars": 0, "t_end": 1791523594.304637, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.2861, "lo95": 7.2717, "mean": 7.2823, "ev_only": 7.3088, "ref_ms": 31.47919, "cand_ms": 4.32045, "n_trials": 44, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9742, "r_wall_s": 143.18, "compile_s": 37.13, "r_error": "", "src_len": 8026, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1951, "tout": 14970, "ts": 1791523265.6160462, "chk": "no_custom_kernel", "code_len": 8050}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6409, "tout": 4297, "ts": 1791523312.267208, "chk": "ok", "code_len": 8026}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10418, "tout": 3745, "ts": 1791523451.0932431, "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": 1951, "started": 1791523133.6976347}
{"ep": "ok-00161", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7583, "speedup": 0.7583, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 613.4, "calls": 5, "tokens_in": 56533, "tokens_out": 11028, "ctx_chars": 6417, "t_end": 1791523596.667747, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7583, "lo95": 0.7536, "mean": 0.7551, "ev_only": 0.7581, "ref_ms": 16.28718, "cand_ms": 21.47799, "n_trials": 52, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0617, "r_wall_s": 157.36, "compile_s": 21.28, "r_error": "", "src_len": 4356, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5503, "tout": 3122, "ts": 1791523008.757435, "chk": "incorrect", "code_len": 6353}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8758, "tout": 3581, "ts": 1791523183.5040057, "chk": "incorrect", "code_len": 6774}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12473, "tout": 2258, "ts": 1791523218.9314408, "chk": "ok", "code_len": 4356}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14840, "tout": 72, "ts": 1791523423.4224591, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 14959, "tout": 1995, "ts": 1791523439.2833245, "chk": null, "code_len": 4356}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5503, "started": 1791522983.264079}
{"ep": "ok-00262", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.5378, "speedup": 0.5378, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 185.6, "calls": 2, "tokens_in": 13702, "tokens_out": 10331, "ctx_chars": 5888, "t_end": 1791523597.3779156, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.5378, "lo95": 0.5371, "mean": 0.5388, "ev_only": 0.5364, "ref_ms": 3.30376, "cand_ms": 6.14363, "n_trials": 198, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3285, "r_wall_s": 55.83, "compile_s": 9.85, "r_error": "", "src_len": 5984, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5062, "tout": 7237, "ts": 1791523487.7308383, "chk": "ok", "code_len": 5984}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8640, "tout": 3094, "ts": 1791523541.4326284, "chk": null, "code_len": 5984}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5062, "started": 1791523411.7705653}
{"ep": "ok-00213", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.7319, "speedup": 1.7319, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 416.9, "calls": 3, "tokens_in": 245548, "tokens_out": 16753, "ctx_chars": 182830, "t_end": 1791523598.1815896, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.7319, "lo95": 1.7268, "mean": 1.7303, "ev_only": 1.7337, "ref_ms": 31.70619, "cand_ms": 18.30673, "n_trials": 25, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9574, "r_wall_s": 140.28, "compile_s": 70.6, "r_error": "", "src_len": 5879, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78518, "tout": 9873, "ts": 1791523270.3192387, "chk": "no_custom_kernel", "code_len": 5883}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81936, "tout": 3674, "ts": 1791523346.8353179, "chk": "ok", "code_len": 5879}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 85094, "tout": 3206, "ts": 1791523457.8758147, "chk": null, "code_len": 5879}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 78518, "started": 1791523181.2930918}
{"ep": "ok-00214", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7164, "speedup": 0.7164, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 417.8, "calls": 3, "tokens_in": 17491, "tokens_out": 4848, "ctx_chars": 2922, "t_end": 1791523601.3713338, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7164, "lo95": 0.7149, "mean": 0.6925, "ev_only": 0.7158, "ref_ms": 3.9806, "cand_ms": 5.55657, "n_trials": 184, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0676, "r_wall_s": 168.2, "compile_s": 11.69, "r_error": "", "src_len": 2747, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3403, "tout": 3504, "ts": 1791523215.825124, "chk": "ok", "code_len": 2747}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7019, "tout": 26, "ts": 1791523422.2618487, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7069, "tout": 1318, "ts": 1791523433.1528432, "chk": null, "code_len": 2747}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3403, "started": 1791523183.5437725}
{"ep": "ok-00271", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7612, "speedup": 0.7612, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 173.5, "calls": 3, "tokens_in": 26819, "tokens_out": 11543, "ctx_chars": 6861, "t_end": 1791523611.0281396, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7612, "lo95": 0.5965, "mean": 0.7607, "ev_only": 0.76, "ref_ms": 28.7263, "cand_ms": 37.73605, "n_trials": 35, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0335, "r_wall_s": 25.69, "compile_s": 4.06, "r_error": "", "src_len": 3734, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5693, "tout": 6836, "ts": 1791523496.1119485, "chk": "incorrect", "code_len": 6729}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9483, "tout": 2701, "ts": 1791523546.3125374, "chk": "ok", "code_len": 3734}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11643, "tout": 2006, "ts": 1791523585.3099484, "chk": null, "code_len": 3734}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5693, "started": 1791523437.5086832}
{"ep": "ok-00280", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0347, "speedup": 1.0347, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 137.7, "calls": 3, "tokens_in": 14972, "tokens_out": 3206, "ctx_chars": 3968, "t_end": 1791523617.3581371, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0347, "lo95": 1.0326, "mean": 1.0903, "ev_only": 1.0353, "ref_ms": 8.38261, "cand_ms": 8.10125, "n_trials": 122, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 37.76, "compile_s": 4.24, "r_error": "", "src_len": 1823, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3392, "tout": 2246, "ts": 1791523500.036543, "chk": "ok", "code_len": 1823}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5750, "tout": 56, "ts": 1791523572.0123296, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5830, "tout": 904, "ts": 1791523579.5664353, "chk": null, "code_len": 1823}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3392, "started": 1791523479.619335}
{"ep": "ok-00253", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.295, "speedup": 0.295, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 231.0, "calls": 3, "tokens_in": 21030, "tokens_out": 4325, "ctx_chars": 7010, "t_end": 1791523619.5507984, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.295, "lo95": 0.2943, "mean": 0.2979, "ev_only": 0.293, "ref_ms": 3.34138, "cand_ms": 11.32757, "n_trials": 146, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0758, "r_wall_s": 182.5, "compile_s": 16.34, "r_error": "", "src_len": 4217, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5460, "tout": 2183, "ts": 1791523406.8716977, "chk": "ok", "code_len": 4217}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7755, "tout": 36, "ts": 1791523420.0435736, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7815, "tout": 2106, "ts": 1791523436.9939885, "chk": null, "code_len": 4217}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5460, "started": 1791523388.510032}
{"ep": "ok-00264", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0118, "speedup": 1.0118, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 199.7, "calls": 2, "tokens_in": 8609, "tokens_out": 4192, "ctx_chars": 3636, "t_end": 1791523620.3970876, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0118, "lo95": 1.0073, "mean": 1.0777, "ev_only": 1.0106, "ref_ms": 8.16388, "cand_ms": 8.06875, "n_trials": 117, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.007, "r_wall_s": 48.15, "compile_s": 2.99, "r_error": "", "src_len": 3080, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3285, "tout": 2633, "ts": 1791523442.6291132, "chk": "ok", "code_len": 3080}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5324, "tout": 1559, "ts": 1791523572.048349, "chk": null, "code_len": 3080}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3285, "started": 1791523420.6579933}
{"ep": "ok-00250", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.8342, "speedup": 0.8342, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 238.5, "calls": 2, "tokens_in": 15412, "tokens_out": 7195, "ctx_chars": 9125, "t_end": 1791523621.4512205, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8342, "lo95": 0.7705, "mean": 0.7698, "ev_only": 0.8362, "ref_ms": 6.12988, "cand_ms": 7.34833, "n_trials": 185, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0026, "r_wall_s": 43.37, "compile_s": 3.66, "r_error": "", "src_len": 4375, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6281, "tout": 4748, "ts": 1791523421.7632256, "chk": "ok", "code_len": 4375}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9131, "tout": 2447, "ts": 1791523577.9993968, "chk": null, "code_len": 4375}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6281, "started": 1791523382.9586022}
{"ep": "ok-00215", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7504, "speedup": 0.7504, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 420.3, "calls": 2, "tokens_in": 9604, "tokens_out": 4404, "ctx_chars": 2922, "t_end": 1791523622.1250296, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7504, "lo95": 0.7485, "mean": 0.7507, "ev_only": 0.75, "ref_ms": 3.96739, "cand_ms": 5.28727, "n_trials": 169, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0693, "r_wall_s": 18.85, "compile_s": 2.27, "r_error": "", "src_len": 3559, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3403, "tout": 2686, "ts": 1791523248.4073482, "chk": "ok", "code_len": 3559}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6201, "tout": 1718, "ts": 1791523468.640709, "chk": null, "code_len": 3559}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3403, "started": 1791523222.213668}
{"ep": "ok-00268", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.3036, "speedup": 0.3036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 204.3, "calls": 3, "tokens_in": 20376, "tokens_out": 4094, "ctx_chars": 6513, "t_end": 1791523633.6237955, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.3036, "lo95": 0.3015, "mean": 0.3117, "ev_only": 0.3013, "ref_ms": 3.39291, "cand_ms": 11.17388, "n_trials": 134, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0766, "r_wall_s": 90.16, "compile_s": 9.95, "r_error": "", "src_len": 4079, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5329, "tout": 2064, "ts": 1791523446.5900304, "chk": "ok", "code_len": 4079}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7505, "tout": 13, "ts": 1791523527.1783159, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7542, "tout": 2017, "ts": 1791523543.3584552, "chk": null, "code_len": 4079}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5329, "started": 1791523429.3340564}
{"ep": "ok-00272", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.8263, "speedup": 0.8263, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 197.1, "calls": 4, "tokens_in": 23007, "tokens_out": 5156, "ctx_chars": 1884, "t_end": 1791523635.71782, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8263, "lo95": 0.8225, "mean": 0.9266, "ev_only": 0.827, "ref_ms": 3.95232, "cand_ms": 4.78316, "n_trials": 164, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.6479, "r_wall_s": 23.89, "compile_s": 2.31, "r_error": "", "src_len": 3354, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3057, "tout": 1911, "ts": 1791523456.9574556, "chk": "runtime_error", "code_len": 3388}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5477, "tout": 1617, "ts": 1791523571.5770245, "chk": "ok", "code_len": 3354}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7206, "tout": 37, "ts": 1791523597.0220363, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7267, "tout": 1591, "ts": 1791523611.784854, "chk": null, "code_len": 3354}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 3057, "started": 1791523438.6264927}
{"ep": "ok-00276", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0254, "speedup": 1.0254, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 195.6, "calls": 2, "tokens_in": 16373, "tokens_out": 2490, "ctx_chars": 13736, "t_end": 1791523640.032609, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0254, "lo95": 1.0226, "mean": 1.025, "ev_only": 1.0261, "ref_ms": 8.1808, "cand_ms": 7.97786, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0044, "r_wall_s": 90.28, "compile_s": 6.38, "r_error": "", "src_len": 1798, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7510, "tout": 1496, "ts": 1791523456.2895346, "chk": "ok", "code_len": 1798}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8863, "tout": 994, "ts": 1791523549.5974424, "chk": null, "code_len": 1798}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7510, "started": 1791523444.3924477}
{"ep": "ok-00296", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 58.9, "calls": 1, "tokens_in": 2917, "tokens_out": 5180, "ctx_chars": 0, "t_end": 1791523642.6181307, "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": 0.0344, "r_wall_s": 17.6, "compile_s": 2.69, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 5940, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2917, "tout": 5180, "ts": 1791523624.9762437, "chk": null, "code_len": 5940}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2917, "started": 1791523583.703727}
{"ep": "ok-00228", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9241, "speedup": 0.9241, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 356.0, "calls": 2, "tokens_in": 5684, "tokens_out": 5092, "ctx_chars": 0, "t_end": 1791523647.8840601, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9241, "lo95": 0.9237, "mean": 0.9241, "ev_only": 0.9246, "ref_ms": 8.1853, "cand_ms": 8.85779, "n_trials": 178, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 211.21, "compile_s": 13.89, "r_error": "", "src_len": 3170, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 3335, "ts": 1791523325.6450064, "chk": "ok", "code_len": 3170}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3959, "tout": 1757, "ts": 1791523436.6019487, "chk": null, "code_len": 3170}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791523291.8516712}
{"ep": "ok-00275", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 205.9, "calls": 1, "tokens_in": 2759, "tokens_out": 3903, "ctx_chars": 495, "t_end": 1791523648.5532286, "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": 0.1072, "r_wall_s": 37.0, "compile_s": 2.0, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 3827, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2759, "tout": 3903, "ts": 1791523476.5613623, "chk": null, "code_len": 3827}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2759, "started": 1791523442.6843703}
{"ep": "ok-00270", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 68.9751, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.3, "calls": 2, "tokens_in": 15274, "tokens_out": 7932, "ctx_chars": 9324, "t_end": 1791523651.7318203, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 68.9751, "lo95": 67.9043, "mean": 71.0093, "ev_only": 77.5359, "ref_ms": 22.35772, "cand_ms": 0.32414, "n_trials": 67, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 121.63, "compile_s": 16.51, "r_error": "", "src_len": 4857, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6118, "tout": 5509, "ts": 1791523481.2214932, "chk": "ok", "code_len": 4857}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9156, "tout": 2423, "ts": 1791523529.809709, "chk": null, "code_len": 4857}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6118, "started": 1791523434.4771898}
{"ep": "ok-00237", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0181, "speedup": 1.0181, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 320.4, "calls": 3, "tokens_in": 18126, "tokens_out": 2841, "ctx_chars": 7245, "t_end": 1791523652.6789663, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0181, "lo95": 1.0179, "mean": 1.0182, "ev_only": 1.0185, "ref_ms": 29.5745, "cand_ms": 29.04811, "n_trials": 55, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0417, "r_wall_s": 143.15, "compile_s": 5.31, "r_error": "", "src_len": 2632, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4949, "tout": 1509, "ts": 1791523346.5595014, "chk": "ok", "code_len": 2716}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6570, "tout": 13, "ts": 1791523498.050991, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6607, "tout": 1319, "ts": 1791523508.9934256, "chk": null, "code_len": 2632}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4949, "started": 1791523332.2334678}
{"ep": "ok-00267", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0367, "speedup": 1.0367, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 229.6, "calls": 2, "tokens_in": 15660, "tokens_out": 2867, "ctx_chars": 12848, "t_end": 1791523657.8689332, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0367, "lo95": 1.0363, "mean": 1.0577, "ev_only": 1.0358, "ref_ms": 8.23351, "cand_ms": 7.94238, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0037, "r_wall_s": 42.54, "compile_s": 9.21, "r_error": "", "src_len": 1753, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7155, "tout": 1918, "ts": 1791523446.3361437, "chk": "ok", "code_len": 1753}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8505, "tout": 949, "ts": 1791523615.2999017, "chk": null, "code_len": 1753}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7155, "started": 1791523428.312638}
{"ep": "ok-00255", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0972, "speedup": 1.0972, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 266.1, "calls": 3, "tokens_in": 24335, "tokens_out": 2169, "ctx_chars": 12121, "t_end": 1791523659.2639272, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0972, "lo95": 1.0942, "mean": 1.0974, "ev_only": 1.0965, "ref_ms": 22.34289, "cand_ms": 20.36347, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0411, "r_wall_s": 59.88, "compile_s": 2.07, "r_error": "", "src_len": 2085, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7260, "tout": 1147, "ts": 1791523426.4455955, "chk": "ok", "code_len": 2085}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8519, "tout": 13, "ts": 1791523458.1972685, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8556, "tout": 1009, "ts": 1791523466.5257401, "chk": null, "code_len": 2085}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7260, "started": 1791523413.509256}
{"ep": "ok-00223", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 7.766, "speedup": 7.766, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 408.1, "calls": 2, "tokens_in": 14520, "tokens_out": 28600, "ctx_chars": 4637, "t_end": 1791523659.374505, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 7.766, "lo95": 7.7462, "mean": 7.732, "ev_only": 7.716, "ref_ms": 4.30325, "cand_ms": 0.55411, "n_trials": 196, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0197, "r_wall_s": 83.94, "compile_s": 21.76, "r_error": "", "src_len": 11039, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4068, "tout": 22903, "ts": 1791523459.9098237, "chk": "ok", "code_len": 11174}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10452, "tout": 5697, "ts": 1791523575.412923, "chk": null, "code_len": 11039}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4068, "started": 1791523251.3036928}
{"ep": "ok-00200", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.9978, "speedup": 0.9978, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 530.5, "calls": 5, "tokens_in": 44333, "tokens_out": 9332, "ctx_chars": 6127, "t_end": 1791523659.4877014, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9978, "lo95": 0.9974, "mean": 1.0269, "ev_only": 0.9981, "ref_ms": 7.92794, "cand_ms": 7.94577, "n_trials": 188, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 32.03, "compile_s": 2.95, "r_error": "", "src_len": 931, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4216, "tout": 2816, "ts": 1791523154.1042018, "chk": "incorrect", "code_len": 1148}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7165, "tout": 2061, "ts": 1791523207.9517205, "chk": "incorrect", "code_len": 1187}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9359, "tout": 1809, "ts": 1791523385.5448294, "chk": "incorrect", "code_len": 1098}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 11302, "tout": 833, "ts": 1791523402.9861436, "chk": "incorrect", "code_len": 1128}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 12291, "tout": 1813, "ts": 1791523627.4107847, "chk": null, "code_len": 931}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 4216, "started": 1791523128.9523537}
{"ep": "ok-00282", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.2971, "speedup": 0.2971, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 147.6, "calls": 3, "tokens_in": 20129, "tokens_out": 4393, "ctx_chars": 6059, "t_end": 1791523661.4056728, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.2971, "lo95": 0.2963, "mean": 0.2985, "ev_only": 0.296, "ref_ms": 3.35628, "cand_ms": 11.29632, "n_trials": 111, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0741, "r_wall_s": 39.32, "compile_s": 2.44, "r_error": "", "src_len": 4314, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5136, "tout": 2224, "ts": 1791523531.9963977, "chk": "ok", "code_len": 4363}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7472, "tout": 25, "ts": 1791523605.137188, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7521, "tout": 2144, "ts": 1791523622.0409324, "chk": null, "code_len": 4314}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5136, "started": 1791523513.811885}
{"ep": "ok-00258", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.792, "speedup": 0.792, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 257.5, "calls": 2, "tokens_in": 12785, "tokens_out": 4174, "ctx_chars": 6861, "t_end": 1791523661.7016683, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.792, "lo95": 0.7911, "mean": 0.7941, "ev_only": 0.7927, "ref_ms": 3.36036, "cand_ms": 4.24263, "n_trials": 221, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0016, "r_wall_s": 42.2, "compile_s": 11.51, "r_error": "", "src_len": 3007, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 2527, "ts": 1791523443.1735966, "chk": "ok", "code_len": 3007}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7383, "tout": 1647, "ts": 1791523619.4772995, "chk": null, "code_len": 3007}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791523404.1636298}
{"ep": "ok-00254", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 31.8385, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 274.0, "calls": 2, "tokens_in": 14383, "tokens_out": 5593, "ctx_chars": 9324, "t_end": 1791523662.9505305, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 31.8385, "lo95": 31.4401, "mean": 30.6914, "ev_only": 32.1089, "ref_ms": 22.36664, "cand_ms": 0.7025, "n_trials": 70, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.7947, "r_wall_s": 59.5, "compile_s": 2.46, "r_error": "", "src_len": 2840, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6118, "tout": 4071, "ts": 1791523427.0502625, "chk": "ok", "code_len": 2840}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8265, "tout": 1522, "ts": 1791523468.7761662, "chk": null, "code_len": 2840}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6118, "started": 1791523388.9956863}
{"ep": "ok-00274", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0067, "speedup": 1.0067, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 225.7, "calls": 2, "tokens_in": 5985, "tokens_out": 4410, "ctx_chars": 768, "t_end": 1791523668.1537814, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0067, "lo95": 1.0061, "mean": 1.0077, "ev_only": 1.0064, "ref_ms": 8.02429, "cand_ms": 7.97098, "n_trials": 167, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0079, "r_wall_s": 40.88, "compile_s": 3.18, "r_error": "", "src_len": 3212, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1908, "tout": 2756, "ts": 1791523466.301274, "chk": "ok", "code_len": 3212}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4077, "tout": 1654, "ts": 1791523627.1711488, "chk": null, "code_len": 3212}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1908, "started": 1791523442.429439}
{"ep": "ok-00314", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 40.5, "calls": 1, "tokens_in": 1681, "tokens_out": 709, "ctx_chars": 0, "t_end": 1791523683.1582408, "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": 0.118, "r_wall_s": 33.09, "compile_s": 2.14, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1152, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1681, "tout": 709, "ts": 1791523650.018676, "chk": null, "code_len": 1152}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1681, "started": 1791523642.6184323}
{"ep": "ok-00273", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9969, "speedup": 0.9969, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 262.2, "calls": 4, "tokens_in": 26653, "tokens_out": 4345, "ctx_chars": 7273, "t_end": 1791523701.124356, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9969, "lo95": 0.9963, "mean": 0.9974, "ev_only": 0.9956, "ref_ms": 8.04508, "cand_ms": 8.07015, "n_trials": 147, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0177, "r_wall_s": 55.97, "compile_s": 2.93, "r_error": "", "src_len": 2863, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4686, "tout": 1473, "ts": 1791523451.749742, "chk": "ok", "code_len": 2888}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6271, "tout": 1424, "ts": 1791523579.5265713, "chk": "ok", "code_len": 2863}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7807, "tout": 58, "ts": 1791523633.842924, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7889, "tout": 1390, "ts": 1791523645.063949, "chk": null, "code_len": 2863}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", "no_code", null], "first_tin": 4686, "started": 1791523438.9258873}
{"ep": "ok-00248", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7465, "speedup": 0.7465, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 333.4, "calls": 3, "tokens_in": 28310, "tokens_out": 13477, "ctx_chars": 6513, "t_end": 1791523705.83467, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7465, "lo95": 0.744, "mean": 0.7127, "ev_only": 0.747, "ref_ms": 16.53209, "cand_ms": 22.14693, "n_trials": 55, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0387, "r_wall_s": 54.88, "compile_s": 1.98, "r_error": "", "src_len": 3621, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5622, "tout": 8809, "ts": 1791523448.3100603, "chk": "incorrect", "code_len": 8149}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10249, "tout": 2930, "ts": 1791523596.429031, "chk": "ok", "code_len": 3686}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12439, "tout": 1738, "ts": 1791523650.9114556, "chk": null, "code_len": 3621}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5622, "started": 1791523372.4197974}
{"ep": "ok-00293", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 44.0461, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 135.0, "calls": 2, "tokens_in": 7207, "tokens_out": 5840, "ctx_chars": 2016, "t_end": 1791523710.6751, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 44.0461, "lo95": 43.4474, "mean": 41.4825, "ev_only": 44.0597, "ref_ms": 22.34368, "cand_ms": 0.50728, "n_trials": 68, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 66.99, "compile_s": 2.78, "r_error": "", "src_len": 2795, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2574, "tout": 4356, "ts": 1791523615.910071, "chk": "ok", "code_len": 2795}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4633, "tout": 1484, "ts": 1791523643.4601145, "chk": null, "code_len": 2795}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2574, "started": 1791523575.6610844}
{"ep": "ok-00265", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 84.3033, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 289.1, "calls": 2, "tokens_in": 6750, "tokens_out": 6599, "ctx_chars": 0, "t_end": 1791523712.0857096, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 84.3033, "lo95": 82.4719, "mean": 81.4402, "ev_only": 85.8625, "ref_ms": 22.44975, "cand_ms": 0.2663, "n_trials": 56, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 86.83, "compile_s": 28.7, "r_error": "", "src_len": 4986, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1829, "tout": 4112, "ts": 1791523457.9474485, "chk": "ok", "code_len": 5020}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4921, "tout": 2487, "ts": 1791523624.8480535, "chk": null, "code_len": 4986}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1829, "started": 1791523423.0069456}
{"ep": "ok-00243", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 37.5352, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 362.4, "calls": 2, "tokens_in": 160458, "tokens_out": 9081, "ctx_chars": 182830, "t_end": 1791523718.243387, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 37.5352, "lo95": 36.9994, "mean": 36.9155, "ev_only": 39.3025, "ref_ms": 22.44808, "cand_ms": 0.59805, "n_trials": 58, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 131.33, "compile_s": 67.14, "r_error": "", "src_len": 6165, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78396, "tout": 5702, "ts": 1791523405.0750227, "chk": "ok", "code_len": 6165}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82062, "tout": 3379, "ts": 1791523586.517944, "chk": null, "code_len": 6165}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78396, "started": 1791523355.871656}
{"ep": "ok-00289", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.3908, "speedup": 0.3908, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 170.4, "calls": 2, "tokens_in": 14223, "tokens_out": 11306, "ctx_chars": 5888, "t_end": 1791523723.966933, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.3908, "lo95": 0.3854, "mean": 0.3901, "ev_only": 0.3893, "ref_ms": 5.61829, "cand_ms": 14.37762, "n_trials": 162, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.354, "r_wall_s": 37.61, "compile_s": 2.01, "r_error": "", "src_len": 6787, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5062, "tout": 7681, "ts": 1791523619.8680534, "chk": "ok", "code_len": 6787}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9161, "tout": 3625, "ts": 1791523686.3300064, "chk": null, "code_len": 6787}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5062, "started": 1791523553.611247}
{"ep": "ok-00277", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 71.3513, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 275.7, "calls": 2, "tokens_in": 160195, "tokens_out": 8862, "ctx_chars": 182830, "t_end": 1791523724.2426527, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 71.3513, "lo95": 70.572, "mean": 74.1907, "ev_only": 79.1522, "ref_ms": 22.47274, "cand_ms": 0.31496, "n_trials": 77, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 131.27, "compile_s": 63.39, "r_error": "", "src_len": 5475, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78396, "tout": 5885, "ts": 1791523500.419487, "chk": "ok", "code_len": 5475}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81799, "tout": 2977, "ts": 1791523592.6273627, "chk": null, "code_len": 5475}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78396, "started": 1791523448.5675392}
{"ep": "ok-00252", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0104, "speedup": 1.0104, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 342.6, "calls": 5, "tokens_in": 42580, "tokens_out": 9486, "ctx_chars": 0, "t_end": 1791523729.251558, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0104, "lo95": 0.9812, "mean": 1.0725, "ev_only": 1.0088, "ref_ms": 7.79991, "cand_ms": 7.71936, "n_trials": 219, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.1, "r_wall_s": 42.85, "compile_s": 11.78, "r_error": "", "src_len": 4514, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2356, "tout": 2720, "ts": 1791523412.0855048, "chk": "compile_error", "code_len": 4592}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6214, "tout": 2258, "ts": 1791523494.0029194, "chk": "compile_error", "code_len": 4589}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9732, "tout": 2233, "ts": 1791523578.6726093, "chk": "ok", "code_len": 4514}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 12077, "tout": 77, "ts": 1791523668.641951, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 12201, "tout": 2198, "ts": 1791523686.3740518, "chk": null, "code_len": 4514}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "compile_error", "ok", "no_code", null], "first_tin": 2356, "started": 1791523386.6972835}
{"ep": "ok-00306", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0349, "speedup": 1.0349, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.4, "calls": 2, "tokens_in": 13170, "tokens_out": 2901, "ctx_chars": 9546, "t_end": 1791523733.7735803, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0349, "lo95": 1.0343, "mean": 1.035, "ev_only": 1.0355, "ref_ms": 8.21487, "cand_ms": 7.93819, "n_trials": 197, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0025, "r_wall_s": 52.53, "compile_s": 6.13, "r_error": "", "src_len": 1596, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5937, "tout": 2013, "ts": 1791523635.939101, "chk": "ok", "code_len": 1596}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7233, "tout": 888, "ts": 1791523681.1981735, "chk": null, "code_len": 1596}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5937, "started": 1791523617.3584871}
{"ep": "ok-00307", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0348, "speedup": 1.0348, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.3, "calls": 3, "tokens_in": 19550, "tokens_out": 3767, "ctx_chars": 6481, "t_end": 1791523735.8136024, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0348, "lo95": 1.0343, "mean": 1.0344, "ev_only": 1.0333, "ref_ms": 8.22456, "cand_ms": 7.94819, "n_trials": 111, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.003, "r_wall_s": 53.45, "compile_s": 5.15, "r_error": "", "src_len": 1775, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4520, "tout": 2837, "ts": 1791523645.3699908, "chk": "ok", "code_len": 1775}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7469, "tout": 68, "ts": 1791523675.0108404, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7561, "tout": 862, "ts": 1791523682.3208988, "chk": null, "code_len": 1775}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4520, "started": 1791523619.5511255}
{"ep": "ok-00269", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.7573, "speedup": 0.7573, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 310.2, "calls": 2, "tokens_in": 8404, "tokens_out": 3935, "ctx_chars": 1884, "t_end": 1791523741.6105683, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7573, "lo95": 0.7553, "mean": 0.7561, "ev_only": 0.7544, "ref_ms": 4.01022, "cand_ms": 5.29554, "n_trials": 216, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0687, "r_wall_s": 56.4, "compile_s": 2.97, "r_error": "", "src_len": 3605, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3057, "tout": 2178, "ts": 1791523451.7006497, "chk": "ok", "code_len": 3693}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5347, "tout": 1757, "ts": 1791523551.7625647, "chk": null, "code_len": 3605}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3057, "started": 1791523431.4355612}
{"ep": "ok-00224", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 8.9801, "speedup": 8.9801, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 486.6, "calls": 3, "tokens_in": 18179, "tokens_out": 22478, "ctx_chars": 495, "t_end": 1791523743.2742653, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 8.9801, "lo95": 8.9498, "mean": 8.9472, "ev_only": 9.017, "ref_ms": 32.04083, "cand_ms": 3.56798, "n_trials": 48, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9851, "r_wall_s": 45.79, "compile_s": 18.6, "r_error": "", "src_len": 7136, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2084, "tout": 14774, "ts": 1791523392.3422706, "chk": "no_custom_kernel", "code_len": 7160}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6142, "tout": 4152, "ts": 1791523468.9843075, "chk": "ok", "code_len": 7136}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9953, "tout": 3552, "ts": 1791523563.8985753, "chk": null, "code_len": 7136}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2084, "started": 1791523256.629678}
{"ep": "ok-00298", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 48.5782, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 156.6, "calls": 2, "tokens_in": 14443, "tokens_out": 5977, "ctx_chars": 9324, "t_end": 1791523747.9723067, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 48.5782, "lo95": 48.2132, "mean": 47.4813, "ev_only": 48.5391, "ref_ms": 22.27525, "cand_ms": 0.45854, "n_trials": 68, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 81.3, "compile_s": 2.87, "r_error": "", "src_len": 2964, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6118, "tout": 4518, "ts": 1791523639.63167, "chk": "ok", "code_len": 3022}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8325, "tout": 1459, "ts": 1791523666.4436483, "chk": null, "code_len": 2964}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6118, "started": 1791523591.3242018}
{"ep": "ok-00297", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0109, "speedup": 1.0109, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.5, "calls": 3, "tokens_in": 22472, "tokens_out": 2801, "ctx_chars": 10528, "t_end": 1791523754.2523994, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0109, "lo95": 1.0098, "mean": 1.0108, "ev_only": 1.0118, "ref_ms": 29.74044, "cand_ms": 29.41974, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0527, "r_wall_s": 65.73, "compile_s": 2.06, "r_error": "", "src_len": 2617, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6419, "tout": 1471, "ts": 1791523612.7031496, "chk": "ok", "code_len": 2704}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8002, "tout": 25, "ts": 1791523676.8379598, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8051, "tout": 1305, "ts": 1791523687.6049645, "chk": null, "code_len": 2617}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6419, "started": 1791523590.7700932}
{"ep": "ok-00249", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.6615, "speedup": 0.6615, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 381.5, "calls": 3, "tokens_in": 34324, "tokens_out": 18986, "ctx_chars": 9125, "t_end": 1791523756.852117, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.6615, "lo95": 0.6577, "mean": 0.6815, "ev_only": 0.662, "ref_ms": 16.08957, "cand_ms": 24.32427, "n_trials": 35, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0556, "r_wall_s": 107.19, "compile_s": 2.09, "r_error": "", "src_len": 4090, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6572, "tout": 13611, "ts": 1791523494.5766504, "chk": "incorrect", "code_len": 11261}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 12706, "tout": 3026, "ts": 1791523600.9612134, "chk": "ok", "code_len": 4090}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15046, "tout": 2349, "ts": 1791523649.6223054, "chk": null, "code_len": 4090}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 6572, "started": 1791523375.3258572}
{"ep": "ok-00257", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0972, "speedup": 1.0972, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 356.9, "calls": 2, "tokens_in": 17754, "tokens_out": 3339, "ctx_chars": 12888, "t_end": 1791523757.7494357, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0972, "lo95": 1.096, "mean": 1.0976, "ev_only": 1.0972, "ref_ms": 22.25146, "cand_ms": 20.28053, "n_trials": 63, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0326, "r_wall_s": 132.07, "compile_s": 26.25, "r_error": "", "src_len": 2198, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7684, "tout": 2274, "ts": 1791523420.216997, "chk": "ok", "code_len": 2198}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10070, "tout": 1065, "ts": 1791523625.345954, "chk": null, "code_len": 2198}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7684, "started": 1791523400.811732}
{"ep": "ok-00301", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.1128, "speedup": 0.1128, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.9, "calls": 4, "tokens_in": 31866, "tokens_out": 5317, "ctx_chars": 8224, "t_end": 1791523760.5585554, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.1128, "lo95": 0.1124, "mean": 0.1129, "ev_only": 0.1127, "ref_ms": 31.43324, "cand_ms": 278.60507, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2757, "r_wall_s": 93.9, "compile_s": 2.98, "r_error": "", "src_len": 2728, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 1844, "ts": 1791523615.4640915, "chk": "forbidden", "code_len": 2935}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7498, "tout": 1521, "ts": 1791523629.2098022, "chk": "ok", "code_len": 2728}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9131, "tout": 589, "ts": 1791523653.8220012, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9744, "tout": 1363, "ts": 1791523666.61402, "chk": null, "code_len": 2728}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 5493, "started": 1791523596.6681373}
{"ep": "ok-00283", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.476, "speedup": 0.476, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 247.6, "calls": 2, "tokens_in": 10983, "tokens_out": 17728, "ctx_chars": 0, "t_end": 1791523766.7832417, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.476, "lo95": 0.4751, "mean": 0.4883, "ev_only": 0.4741, "ref_ms": 3.38548, "cand_ms": 7.11205, "n_trials": 208, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3861, "r_wall_s": 36.6, "compile_s": 7.76, "r_error": "", "src_len": 9882, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 12494, "ts": 1791523625.4197278, "chk": "ok", "code_len": 9882}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8355, "tout": 5234, "ts": 1791523730.14959, "chk": null, "code_len": 9882}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791523519.229984}
{"ep": "ok-00303", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.023, "speedup": 1.023, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 168.8, "calls": 3, "tokens_in": 24699, "tokens_out": 1883, "ctx_chars": 13736, "t_end": 1791523767.0085385, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.023, "lo95": 1.0228, "mean": 1.0332, "ev_only": 1.0252, "ref_ms": 8.15136, "cand_ms": 7.96798, "n_trials": 179, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0038, "r_wall_s": 89.29, "compile_s": 3.08, "r_error": "", "src_len": 1852, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7508, "tout": 941, "ts": 1791523608.7092862, "chk": "ok", "code_len": 1852}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8561, "tout": 45, "ts": 1791523669.9622777, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8630, "tout": 897, "ts": 1791523677.6209543, "chk": null, "code_len": 1852}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7508, "started": 1791523598.181941}
{"ep": "ok-00291", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.8654, "speedup": 0.8654, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 206.1, "calls": 2, "tokens_in": 14650, "tokens_out": 10521, "ctx_chars": 6513, "t_end": 1791523767.8992279, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8654, "lo95": 0.8566, "mean": 0.9143, "ev_only": 0.8664, "ref_ms": 3.41944, "cand_ms": 3.95122, "n_trials": 92, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0969, "r_wall_s": 69.28, "compile_s": 3.01, "r_error": "", "src_len": 6921, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 7050, "ts": 1791523622.3062873, "chk": "ok", "code_len": 6921}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9319, "tout": 3471, "ts": 1791523698.5953448, "chk": null, "code_len": 6921}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5331, "started": 1791523561.8488731}
{"ep": "ok-00288", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0036, "speedup": 1.0036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 224.8, "calls": 4, "tokens_in": 14978, "tokens_out": 7528, "ctx_chars": 0, "t_end": 1791523775.6458237, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0036, "lo95": 1.0022, "mean": 1.0005, "ev_only": 1.005, "ref_ms": 8.05517, "cand_ms": 8.02616, "n_trials": 146, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 29.67, "compile_s": 1.98, "r_error": "", "src_len": 1007, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 2645, "ts": 1791523594.9839883, "chk": "incorrect", "code_len": 2239}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3324, "tout": 2381, "ts": 1791523654.0587003, "chk": "incorrect", "code_len": 1000}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4449, "tout": 1818, "ts": 1791523698.782281, "chk": "ok", "code_len": 1007}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5522, "tout": 684, "ts": 1791523745.8721068, "chk": null, "code_len": 1007}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1683, "started": 1791523571.141981}
{"ep": "ok-00154", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.8879, "speedup": 0.8879, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 806.0, "calls": 5, "tokens_in": 62852, "tokens_out": 12832, "ctx_chars": 9125, "t_end": 1791523778.489982, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8879, "lo95": 0.885, "mean": 0.8724, "ev_only": 0.8872, "ref_ms": 17.22871, "cand_ms": 19.40296, "n_trials": 43, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0412, "r_wall_s": 89.19, "compile_s": 2.72, "r_error": "", "src_len": 4017, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6570, "tout": 2739, "ts": 1791522994.4852202, "chk": "incorrect", "code_len": 5797}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9442, "tout": 3192, "ts": 1791523084.9759097, "chk": "incorrect", "code_len": 6104}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12767, "tout": 3065, "ts": 1791523392.2283669, "chk": "incorrect", "code_len": 5955}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 15966, "tout": 2009, "ts": 1791523460.7975242, "chk": "ok", "code_len": 4017}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 18107, "tout": 1827, "ts": 1791523553.2390327, "chk": null, "code_len": 4017}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 6570, "started": 1791522972.5076034}
{"ep": "ok-00338", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0963, "speedup": 1.0963, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 41.0, "calls": 1, "tokens_in": 6776, "tokens_out": 1071, "ctx_chars": 11064, "t_end": 1791523782.6374478, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0963, "lo95": 1.0952, "mean": 1.1008, "ev_only": 1.0957, "ref_ms": 22.32724, "cand_ms": 20.36665, "n_trials": 55, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0401, "r_wall_s": 30.91, "compile_s": 1.95, "r_error": "", "src_len": 2150, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 6776, "tout": 1071, "ts": 1791523751.3235853, "chk": null, "code_len": 2150}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 6776, "started": 1791523741.6109877}
{"ep": "ok-00294", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0311, "speedup": 1.0311, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 207.9, "calls": 3, "tokens_in": 25432, "tokens_out": 2785, "ctx_chars": 12848, "t_end": 1791523785.9565368, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0311, "lo95": 1.0293, "mean": 1.0322, "ev_only": 1.0326, "ref_ms": 8.25752, "cand_ms": 8.00836, "n_trials": 119, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0049, "r_wall_s": 137.29, "compile_s": 2.25, "r_error": "", "src_len": 1819, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7153, "tout": 1838, "ts": 1791523595.3858418, "chk": "ok", "code_len": 1819}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9103, "tout": 49, "ts": 1791523641.2396932, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9176, "tout": 898, "ts": 1791523648.6196969, "chk": null, "code_len": 1819}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7153, "started": 1791523578.0339599}
{"ep": "ok-00290", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0239, "speedup": 1.0239, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 231.8, "calls": 3, "tokens_in": 20927, "tokens_out": 1831, "ctx_chars": 10373, "t_end": 1791523790.217966, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0239, "lo95": 1.0226, "mean": 1.0245, "ev_only": 1.0249, "ref_ms": 8.22512, "cand_ms": 8.03319, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0061, "r_wall_s": 52.17, "compile_s": 11.2, "r_error": "", "src_len": 1838, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6268, "tout": 931, "ts": 1791523566.7308488, "chk": "ok", "code_len": 1838}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7311, "tout": 13, "ts": 1791523730.4831011, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7348, "tout": 887, "ts": 1791523737.9689786, "chk": null, "code_len": 1838}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6268, "started": 1791523558.4326282}
{"ep": "ok-00312", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.1013, "speedup": 1.1013, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 155.3, "calls": 1, "tokens_in": 7684, "tokens_out": 1056, "ctx_chars": 12888, "t_end": 1791523791.0163014, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1013, "lo95": 1.1006, "mean": 1.1011, "ev_only": 1.1006, "ref_ms": 22.26277, "cand_ms": 20.21574, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0327, "r_wall_s": 145.16, "compile_s": 2.65, "r_error": "", "src_len": 2140, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7684, "tout": 1056, "ts": 1791523645.6353056, "chk": null, "code_len": 2140}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7684, "started": 1791523635.718092}
{"ep": "ok-00278", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0079, "speedup": 1.0079, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 321.9, "calls": 5, "tokens_in": 402010, "tokens_out": 4470, "ctx_chars": 182830, "t_end": 1791523792.896248, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0079, "lo95": 1.0071, "mean": 1.0075, "ev_only": 1.0057, "ref_ms": 8.04556, "cand_ms": 7.98248, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 82.51, "compile_s": 2.05, "r_error": "", "src_len": 966, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78248, "tout": 916, "ts": 1791523501.9715981, "chk": "incorrect", "code_len": 1548}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 79297, "tout": 909, "ts": 1791523547.3137114, "chk": "incorrect", "code_len": 1589}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 80339, "tout": 1144, "ts": 1791523618.069972, "chk": "incorrect", "code_len": 1221}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 81616, "tout": 762, "ts": 1791523691.8316152, "chk": "ok", "code_len": 966}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 82510, "tout": 739, "ts": 1791523710.3522477, "chk": null, "code_len": 966}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 78248, "started": 1791523491.2343588}
{"ep": "ok-00256", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0336, "speedup": 1.0336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 396.7, "calls": 2, "tokens_in": 159687, "tokens_out": 6970, "ctx_chars": 182830, "t_end": 1791523796.503549, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0336, "lo95": 1.0332, "mean": 1.0349, "ev_only": 1.0336, "ref_ms": 29.75395, "cand_ms": 28.78637, "n_trials": 42, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.02, "r_wall_s": 102.65, "compile_s": 53.21, "r_error": "", "src_len": 5000, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78312, "tout": 3963, "ts": 1791523434.89173, "chk": "ok", "code_len": 5000}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81375, "tout": 3007, "ts": 1791523560.7345457, "chk": null, "code_len": 5000}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78312, "started": 1791523399.796465}
{"ep": "ok-00251", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.1173, "speedup": 0.1173, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 413.2, "calls": 4, "tokens_in": 22562, "tokens_out": 7515, "ctx_chars": 0, "t_end": 1791523799.8877041, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.1173, "lo95": 0.1171, "mean": 0.1175, "ev_only": 0.1172, "ref_ms": 31.46166, "cand_ms": 268.24392, "n_trials": 11, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.2901, "r_wall_s": 135.63, "compile_s": 16.55, "r_error": "", "src_len": 4009, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1949, "tout": 2081, "ts": 1791523405.957625, "chk": "forbidden", "code_len": 4090}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4191, "tout": 1806, "ts": 1791523438.3521914, "chk": "compile_error", "code_len": 3941}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7248, "tout": 1814, "ts": 1791523530.2562528, "chk": "ok", "code_len": 4009}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9174, "tout": 1814, "ts": 1791523664.2173662, "chk": null, "code_len": 4009}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "compile_error", "ok", null], "first_tin": 1949, "started": 1791523386.6461918}
{"ep": "ok-00317", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.2984, "speedup": 0.2984, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 150.7, "calls": 1, "tokens_in": 5329, "tokens_out": 2143, "ctx_chars": 6513, "t_end": 1791523802.436585, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.2984, "lo95": 0.2971, "mean": 0.2957, "ev_only": 0.2988, "ref_ms": 3.31642, "cand_ms": 11.11429, "n_trials": 125, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0734, "r_wall_s": 129.66, "compile_s": 3.38, "r_error": "", "src_len": 4115, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5329, "tout": 2143, "ts": 1791523672.729915, "chk": null, "code_len": 4115}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5329, "started": 1791523651.7320814}
{"ep": "ok-00184", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 15.2493, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 750.9, "calls": 3, "tokens_in": 28589, "tokens_out": 34824, "ctx_chars": 2425, "t_end": 1791523804.248698, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 15.2493, "lo95": 14.5449, "mean": 14.1273, "ev_only": 15.8726, "ref_ms": 4.87951, "cand_ms": 0.31998, "n_trials": 205, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 139.76, "compile_s": 16.04, "r_error": "", "src_len": 10512, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 22956, "ts": 1791523256.1735666, "chk": "no_custom_kernel", "code_len": 10557}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9714, "tout": 6150, "ts": 1791523575.5342243, "chk": "ok", "code_len": 10512}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15601, "tout": 5718, "ts": 1791523664.4478264, "chk": null, "code_len": 10512}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 3274, "started": 1791523053.370327}
{"ep": "ok-00318", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.3287, "speedup": 0.3287, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.3, "calls": 3, "tokens_in": 21329, "tokens_out": 5410, "ctx_chars": 6417, "t_end": 1791523813.9317982, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.3287, "lo95": 0.3253, "mean": 0.3296, "ev_only": 0.3273, "ref_ms": 6.74377, "cand_ms": 20.51525, "n_trials": 64, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0766, "r_wall_s": 36.7, "compile_s": 3.24, "r_error": "", "src_len": 5186, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5212, "tout": 2716, "ts": 1791523677.5596914, "chk": "ok", "code_len": 5186}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8040, "tout": 13, "ts": 1791523756.1939154, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8077, "tout": 2681, "ts": 1791523777.1215892, "chk": null, "code_len": 5186}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5212, "started": 1791523652.679281}
{"ep": "ok-00292", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.6757, "speedup": 0.6757, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 250.6, "calls": 3, "tokens_in": 30834, "tokens_out": 16003, "ctx_chars": 9125, "t_end": 1791523815.821218, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6757, "lo95": 0.6115, "mean": 0.6262, "ev_only": 0.6747, "ref_ms": 31.80943, "cand_ms": 47.07968, "n_trials": 21, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0522, "r_wall_s": 55.68, "compile_s": 2.79, "r_error": "", "src_len": 4012, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6572, "tout": 10425, "ts": 1791523656.378381, "chk": "incorrect", "code_len": 7860}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11010, "tout": 3042, "ts": 1791523720.9536357, "chk": "ok", "code_len": 4012}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13252, "tout": 2536, "ts": 1791523760.028673, "chk": null, "code_len": 4012}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 6572, "started": 1791523565.2656689}
{"ep": "ok-00325", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 36.4107, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 156.5, "calls": 2, "tokens_in": 14285, "tokens_out": 6064, "ctx_chars": 9324, "t_end": 1791523819.4840772, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 36.4107, "lo95": 35.9123, "mean": 36.059, "ev_only": 38.5662, "ref_ms": 22.40537, "cand_ms": 0.61535, "n_trials": 58, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 60.32, "compile_s": 2.43, "r_error": "", "src_len": 2938, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6118, "tout": 4486, "ts": 1791523703.4971921, "chk": "ok", "code_len": 2938}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8167, "tout": 1578, "ts": 1791523758.768648, "chk": null, "code_len": 2938}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6118, "started": 1791523662.9508085}
{"ep": "ok-00316", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.9958, "speedup": 0.9958, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 174.5, "calls": 3, "tokens_in": 17440, "tokens_out": 2964, "ctx_chars": 7333, "t_end": 1791523823.0446715, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9958, "lo95": 0.9926, "mean": 0.9992, "ev_only": 0.9959, "ref_ms": 8.12465, "cand_ms": 8.15916, "n_trials": 143, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0176, "r_wall_s": 61.2, "compile_s": 2.75, "r_error": "", "src_len": 2881, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4705, "tout": 1510, "ts": 1791523661.8293695, "chk": "ok", "code_len": 2881}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6327, "tout": 57, "ts": 1791523750.0688105, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6408, "tout": 1397, "ts": 1791523761.6871817, "chk": null, "code_len": 2881}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4705, "started": 1791523648.5535424}
{"ep": "ok-00313", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.7114, "speedup": 0.7114, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.0, "calls": 2, "tokens_in": 15869, "tokens_out": 6962, "ctx_chars": 9125, "t_end": 1791523828.0194986, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7114, "lo95": 0.6232, "mean": 0.6408, "ev_only": 0.712, "ref_ms": 16.61613, "cand_ms": 23.35835, "n_trials": 69, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0395, "r_wall_s": 88.16, "compile_s": 12.64, "r_error": "", "src_len": 5013, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6572, "tout": 4382, "ts": 1791523677.7375965, "chk": "ok", "code_len": 5013}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9297, "tout": 2580, "ts": 1791523739.8369763, "chk": null, "code_len": 5013}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6572, "started": 1791523640.032948}
{"ep": "ok-00221", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 8.8652, "speedup": 8.8652, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 585.8, "calls": 3, "tokens_in": 254881, "tokens_out": 30526, "ctx_chars": 182830, "t_end": 1791523829.9128892, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 8.8652, "lo95": 8.7674, "mean": 9.1402, "ev_only": 9.0556, "ref_ms": 4.15824, "cand_ms": 0.46905, "n_trials": 204, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 115.96, "compile_s": 63.65, "r_error": "", "src_len": 11096, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78925, "tout": 18419, "ts": 1791523407.801263, "chk": "no_custom_kernel", "code_len": 11126}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 85102, "tout": 6165, "ts": 1791523614.9870603, "chk": "ok", "code_len": 11096}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 90854, "tout": 5942, "ts": 1791523713.9253817, "chk": null, "code_len": 11096}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 78925, "started": 1791523244.1215425}
{"ep": "ok-00242", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.9131, "speedup": 1.9131, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 478.0, "calls": 2, "tokens_in": 18435, "tokens_out": 18163, "ctx_chars": 9125, "t_end": 1791523832.5886385, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.9131, "lo95": 1.8888, "mean": 1.9517, "ev_only": 1.9001, "ref_ms": 5.10061, "cand_ms": 2.66621, "n_trials": 209, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.3893, "r_wall_s": 136.27, "compile_s": 62.31, "r_error": "", "src_len": 11225, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6281, "tout": 12671, "ts": 1791523467.4233446, "chk": "ok", "code_len": 11271}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 12154, "tout": 5492, "ts": 1791523696.2907348, "chk": null, "code_len": 11225}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6281, "started": 1791523354.5780156}
{"ep": "ok-00323", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.406, "speedup": 1.406, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 171.2, "calls": 2, "tokens_in": 159351, "tokens_out": 7199, "ctx_chars": 182830, "t_end": 1791523832.5966694, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.406, "lo95": 1.4054, "mean": 1.407, "ev_only": 1.4098, "ref_ms": 8.14608, "cand_ms": 5.79398, "n_trials": 161, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.8604, "r_wall_s": 26.33, "compile_s": 2.0, "r_error": "", "src_len": 4230, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78292, "tout": 4550, "ts": 1791523702.240645, "chk": "ok", "code_len": 4230}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81059, "tout": 2649, "ts": 1791523806.1825619, "chk": null, "code_len": 4230}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78292, "started": 1791523661.405978}
{"ep": "ok-00335", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0239, "speedup": 1.0239, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 107.8, "calls": 2, "tokens_in": 10907, "tokens_out": 2632, "ctx_chars": 7159, "t_end": 1791523837.059285, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0239, "lo95": 1.0229, "mean": 1.0231, "ev_only": 1.027, "ref_ms": 8.17662, "cand_ms": 7.98561, "n_trials": 104, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0052, "r_wall_s": 30.07, "compile_s": 2.14, "r_error": "", "src_len": 1870, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4795, "tout": 1559, "ts": 1791523742.8265367, "chk": "ok", "code_len": 1870}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6112, "tout": 1073, "ts": 1791523806.8689399, "chk": null, "code_len": 1870}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4795, "started": 1791523729.251905}
{"ep": "ok-00345", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 71.2, "calls": 1, "tokens_in": 3050, "tokens_out": 2853, "ctx_chars": 495, "t_end": 1791523838.0031118, "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": 0.0642, "r_wall_s": 36.31, "compile_s": 9.53, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 5243, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3050, "tout": 2853, "ts": 1791523801.5796046, "chk": null, "code_len": 5243}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3050, "started": 1791523766.7835324}
{"ep": "ok-00287", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0319, "speedup": 1.0319, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 320.5, "calls": 2, "tokens_in": 13478, "tokens_out": 4620, "ctx_chars": 8788, "t_end": 1791523848.376408, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0319, "lo95": 1.0312, "mean": 1.0145, "ev_only": 1.032, "ref_ms": 29.80072, "cand_ms": 28.87933, "n_trials": 39, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0223, "r_wall_s": 105.55, "compile_s": 18.92, "r_error": "", "src_len": 2894, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5761, "tout": 3034, "ts": 1791523562.7590883, "chk": "ok", "code_len": 2894}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7717, "tout": 1586, "ts": 1791523742.0900688, "chk": null, "code_len": 2894}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5761, "started": 1791523527.8852153}
{"ep": "ok-00349", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 73.0, "calls": 1, "tokens_in": 1960, "tokens_out": 2015, "ctx_chars": 495, "t_end": 1791523851.4855413, "error": "RuntimeError: Error building extension 'fused_pool_l2_050': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_l2_050 -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": 55.12, "compile_s": 55.11, "r_error": "RuntimeError: Error building extension 'fused_pool_l2_050': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_l2_050 -DTORCH_API_INCLUDE_EXTENSION_H", "src_len": 3863, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1960, "tout": 2015, "ts": 1791523796.2592597, "chk": null, "code_len": 3863}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1960, "started": 1791523778.4904904}
{"ep": "ok-00295", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0331, "speedup": 1.0331, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 275.2, "calls": 4, "tokens_in": 22329, "tokens_out": 4588, "ctx_chars": 3968, "t_end": 1791523855.1213672, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0331, "lo95": 1.0317, "mean": 1.0312, "ev_only": 1.0352, "ref_ms": 8.24921, "cand_ms": 7.98461, "n_trials": 195, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0052, "r_wall_s": 63.27, "compile_s": 17.28, "r_error": "", "src_len": 3062, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3392, "tout": 1600, "ts": 1791523594.566118, "chk": "compile_error", "code_len": 3188}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5211, "tout": 1501, "ts": 1791523678.1669433, "chk": "ok", "code_len": 3062}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6824, "tout": 54, "ts": 1791523779.9456599, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6902, "tout": 1433, "ts": 1791523791.7391872, "chk": null, "code_len": 3062}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 3392, "started": 1791523579.9694223}
{"ep": "ok-00355", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0293, "speedup": 1.0293, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 64.0, "calls": 2, "tokens_in": 10148, "tokens_out": 2657, "ctx_chars": 6332, "t_end": 1791523860.527009, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0293, "lo95": 1.0263, "mean": 1.0288, "ev_only": 1.0313, "ref_ms": 8.31894, "cand_ms": 8.08253, "n_trials": 100, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 31.07, "compile_s": 2.13, "r_error": "", "src_len": 1585, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4462, "tout": 1796, "ts": 1791523813.5056698, "chk": "ok", "code_len": 1585}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5686, "tout": 861, "ts": 1791523829.410461, "chk": null, "code_len": 1585}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4462, "started": 1791523796.503892}
{"ep": "ok-00359", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0282, "speedup": 1.0282, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 47.5, "calls": 1, "tokens_in": 4853, "tokens_out": 940, "ctx_chars": 7308, "t_end": 1791523861.389132, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0282, "lo95": 1.0268, "mean": 1.0287, "ev_only": 1.0282, "ref_ms": 8.22284, "cand_ms": 7.99713, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0029, "r_wall_s": 38.78, "compile_s": 2.08, "r_error": "", "src_len": 1814, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 4853, "tout": 940, "ts": 1791523822.450206, "chk": null, "code_len": 1814}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 4853, "started": 1791523813.932137}
{"ep": "ok-00351", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0964, "speedup": 1.0964, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 77.0, "calls": 3, "tokens_in": 25073, "tokens_out": 3316, "ctx_chars": 11064, "t_end": 1791523862.970492, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0964, "lo95": 1.0953, "mean": 1.0955, "ev_only": 1.0954, "ref_ms": 22.30197, "cand_ms": 20.34086, "n_trials": 62, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0199, "r_wall_s": 37.1, "compile_s": 1.89, "r_error": "", "src_len": 2151, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6776, "tout": 2231, "ts": 1791523805.69596, "chk": "ok", "code_len": 2151}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9119, "tout": 35, "ts": 1791523816.973948, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9178, "tout": 1050, "ts": 1791523825.6467335, "chk": null, "code_len": 2151}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6776, "started": 1791523785.9568806}
{"ep": "ok-00308", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0257, "speedup": 1.0257, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 247.6, "calls": 2, "tokens_in": 5385, "tokens_out": 2550, "ctx_chars": 768, "t_end": 1791523867.9650671, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0257, "lo95": 1.0246, "mean": 1.0275, "ev_only": 1.0278, "ref_ms": 8.18499, "cand_ms": 7.97995, "n_trials": 173, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 51.63, "compile_s": 2.1, "r_error": "", "src_len": 1858, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2026, "tout": 1560, "ts": 1791523633.0235007, "chk": "ok", "code_len": 1858}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3359, "tout": 990, "ts": 1791523682.1871498, "chk": null, "code_len": 1858}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2026, "started": 1791523620.3973625}
{"ep": "ok-00305", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 37.1329, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 261.2, "calls": 2, "tokens_in": 6416, "tokens_out": 6294, "ctx_chars": 0, "t_end": 1791523872.2120407, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 37.1329, "lo95": 36.647, "mean": 35.4966, "ev_only": 38.0161, "ref_ms": 22.3298, "cand_ms": 0.60135, "n_trials": 44, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.7622, "r_wall_s": 78.43, "compile_s": 15.95, "r_error": "", "src_len": 4147, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1829, "tout": 4198, "ts": 1791523668.1223981, "chk": "ok", "code_len": 4147}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4587, "tout": 2096, "ts": 1791523793.3723943, "chk": null, "code_len": 4147}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1829, "started": 1791523631.3832824}
{"ep": "ok-00326", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 206.9, "calls": 1, "tokens_in": 1876, "tokens_out": 1929, "ctx_chars": 495, "t_end": 1791523875.0550768, "error": "RuntimeError: Error building extension 'relu_gn_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_fused -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": 54.69, "compile_s": 54.67, "r_error": "RuntimeError: Error building extension 'relu_gn_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/", "src_len": 3948, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1876, "tout": 1929, "ts": 1791523685.5406535, "chk": null, "code_len": 3948}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1876, "started": 1791523668.1540704}
{"ep": "ok-00327", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0267, "speedup": 1.0267, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 195.0, "calls": 2, "tokens_in": 11694, "tokens_out": 4347, "ctx_chars": 7221, "t_end": 1791523878.1614954, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0267, "lo95": 1.0261, "mean": 1.0268, "ev_only": 1.027, "ref_ms": 29.64443, "cand_ms": 28.87313, "n_trials": 42, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0214, "r_wall_s": 107.55, "compile_s": 2.39, "r_error": "", "src_len": 2913, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4831, "tout": 2759, "ts": 1791523727.0126994, "chk": "ok", "code_len": 2913}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6863, "tout": 1588, "ts": 1791523769.9195979, "chk": null, "code_len": 2913}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4831, "started": 1791523703.511396}
{"ep": "ok-00311", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.085, "speedup": 0.085, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 247.5, "calls": 3, "tokens_in": 29565, "tokens_out": 6434, "ctx_chars": 10587, "t_end": 1791523881.1586766, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.085, "lo95": 0.0845, "mean": 0.0851, "ev_only": 0.0851, "ref_ms": 32.10368, "cand_ms": 377.53486, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2233, "r_wall_s": 148.99, "compile_s": 9.43, "r_error": "", "src_len": 2402, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 4996, "ts": 1791523678.634936, "chk": "ok", "code_len": 2402}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 11470, "tout": 239, "ts": 1791523722.0123088, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11733, "tout": 1199, "ts": 1791523732.1368008, "chk": null, "code_len": 2402}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791523633.6241944}
{"ep": "ok-00336", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0435, "speedup": 1.0435, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 149.6, "calls": 2, "tokens_in": 4963, "tokens_out": 3187, "ctx_chars": 0, "t_end": 1791523883.3922005, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0435, "lo95": 1.0434, "mean": 1.043, "ev_only": 1.042, "ref_ms": 8.21312, "cand_ms": 7.87037, "n_trials": 137, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0036, "r_wall_s": 111.17, "compile_s": 2.91, "r_error": "", "src_len": 1627, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 2282, "ts": 1791523755.0197194, "chk": "ok", "code_len": 1627}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3161, "tout": 905, "ts": 1791523772.1108034, "chk": null, "code_len": 1627}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791523733.7742448}
{"ep": "ok-00334", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0359, "speedup": 1.0359, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.2, "calls": 2, "tokens_in": 15682, "tokens_out": 2764, "ctx_chars": 12848, "t_end": 1791523886.4070854, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0359, "lo95": 1.0357, "mean": 1.0361, "ev_only": 1.036, "ref_ms": 8.1969, "cand_ms": 7.91277, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 96.23, "compile_s": 2.8, "r_error": "", "src_len": 1618, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7155, "tout": 1868, "ts": 1791523741.4166634, "chk": "ok", "code_len": 1618}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8527, "tout": 896, "ts": 1791523790.0673132, "chk": null, "code_len": 1618}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7155, "started": 1791523724.2430334}
{"ep": "ok-00350", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 113.7, "calls": 1, "tokens_in": 3050, "tokens_out": 4865, "ctx_chars": 495, "t_end": 1791523896.3483508, "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": 0.0344, "r_wall_s": 74.15, "compile_s": 2.04, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 5507, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3050, "tout": 4865, "ts": 1791523822.1496074, "chk": null, "code_len": 5507}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3050, "started": 1791523782.637775}
{"ep": "ok-00324", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 32.4204, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 236.8, "calls": 2, "tokens_in": 18160, "tokens_out": 7181, "ctx_chars": 12888, "t_end": 1791523898.5114102, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 32.4204, "lo95": 32.2371, "mean": 31.264, "ev_only": 33.032, "ref_ms": 22.25614, "cand_ms": 0.68649, "n_trials": 82, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.8127, "r_wall_s": 107.08, "compile_s": 3.66, "r_error": "", "src_len": 3941, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7686, "tout": 5179, "ts": 1791523709.451677, "chk": "ok", "code_len": 4047}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10474, "tout": 2002, "ts": 1791523791.017666, "chk": null, "code_len": 3941}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7686, "started": 1791523661.702024}
{"ep": "ok-00322", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0203, "speedup": 1.0203, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 239.6, "calls": 3, "tokens_in": 22353, "tokens_out": 2745, "ctx_chars": 10528, "t_end": 1791523899.1197162, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0203, "lo95": 1.0196, "mean": 1.0206, "ev_only": 1.0199, "ref_ms": 29.73436, "cand_ms": 29.14387, "n_trials": 20, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0182, "r_wall_s": 164.51, "compile_s": 11.42, "r_error": "", "src_len": 2622, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6419, "tout": 1411, "ts": 1791523678.2558525, "chk": "ok", "code_len": 2622}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7942, "tout": 26, "ts": 1791523723.0743601, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7992, "tout": 1308, "ts": 1791523733.9227185, "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": 6419, "started": 1791523659.4880493}
{"ep": "ok-00340", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0459, "speedup": 1.0459, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.2, "calls": 2, "tokens_in": 13931, "tokens_out": 2835, "ctx_chars": 9546, "t_end": 1791523909.1448505, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0459, "lo95": 1.0438, "mean": 1.0793, "ev_only": 1.0411, "ref_ms": 8.38984, "cand_ms": 8.02202, "n_trials": 156, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 33.16, "compile_s": 3.17, "r_error": "", "src_len": 1729, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5935, "tout": 1949, "ts": 1791523765.7343955, "chk": "ok", "code_len": 1729}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7996, "tout": 886, "ts": 1791523875.9446352, "chk": null, "code_len": 1729}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5935, "started": 1791523747.9726295}
{"ep": "ok-00299", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.3052, "speedup": 0.3052, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 321.9, "calls": 3, "tokens_in": 23366, "tokens_out": 4191, "ctx_chars": 9125, "t_end": 1791523915.8483484, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.3052, "lo95": 0.2997, "mean": 0.3256, "ev_only": 0.3027, "ref_ms": 3.44881, "cand_ms": 11.30031, "n_trials": 124, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0765, "r_wall_s": 174.45, "compile_s": 17.48, "r_error": "", "src_len": 4093, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6279, "tout": 2134, "ts": 1791523614.7748199, "chk": "ok", "code_len": 4137}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8525, "tout": 13, "ts": 1791523725.0764556, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8562, "tout": 2044, "ts": 1791523741.3734882, "chk": null, "code_len": 4093}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6279, "started": 1791523593.9714284}
{"ep": "ok-00371", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "no_custom_kernel", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 60.7, "calls": 1, "tokens_in": 2626, "tokens_out": 4494, "ctx_chars": 0, "t_end": 1791523915.8593256, "error": "none of the candidate's kernels ['_relu6_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-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": 0.0, "r_wall_s": 24.48, "compile_s": 9.22, "r_error": "none of the candidate's kernels ['_relu6_kernel', '_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "src_len": 4872, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2626, "tout": 4494, "ts": 1791523891.3257916, "chk": null, "code_len": 4872}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2626, "started": 1791523855.1216335}
{"ep": "ok-00261", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.1685, "speedup": 1.1685, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 512.9, "calls": 2, "tokens_in": 12754, "tokens_out": 23076, "ctx_chars": 0, "t_end": 1791523918.2009046, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.1685, "lo95": 1.1646, "mean": 1.1351, "ev_only": 1.1724, "ref_ms": 3.35166, "cand_ms": 2.86827, "n_trials": 193, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.4355, "r_wall_s": 109.45, "compile_s": 12.88, "r_error": "", "src_len": 13176, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 16071, "ts": 1791523557.3951504, "chk": "ok", "code_len": 13176}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10126, "tout": 7005, "ts": 1791523808.6906633, "chk": null, "code_len": 13176}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791523405.334593}
{"ep": "ok-00337", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0347, "speedup": 1.0347, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 189.1, "calls": 3, "tokens_in": 7912, "tokens_out": 2046, "ctx_chars": 0, "t_end": 1791523924.9121656, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0347, "lo95": 1.0344, "mean": 1.0346, "ev_only": 1.0334, "ref_ms": 8.21233, "cand_ms": 7.93687, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0061, "r_wall_s": 159.84, "compile_s": 2.2, "r_error": "", "src_len": 1803, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1800, "tout": 1102, "ts": 1791523746.84404, "chk": "ok", "code_len": 1904}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3014, "tout": 60, "ts": 1791523757.4913301, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3098, "tout": 884, "ts": 1791523764.9640622, "chk": null, "code_len": 1803}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1800, "started": 1791523735.8139272}
{"ep": "ok-00300", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0206, "speedup": 1.0206, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 335.2, "calls": 3, "tokens_in": 28891, "tokens_out": 2870, "ctx_chars": 15603, "t_end": 1791523929.4931934, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0206, "lo95": 1.0202, "mean": 1.0205, "ev_only": 1.0209, "ref_ms": 29.69074, "cand_ms": 29.09011, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.034, "r_wall_s": 108.62, "compile_s": 2.08, "r_error": "", "src_len": 2723, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8528, "tout": 1523, "ts": 1791523609.8825295, "chk": "ok", "code_len": 2723}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10163, "tout": 13, "ts": 1791523676.8885908, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10200, "tout": 1334, "ts": 1791523687.9082878, "chk": null, "code_len": 2723}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 8528, "started": 1791523594.3049753}
{"ep": "ok-00320", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.1058, "speedup": 1.1058, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 277.6, "calls": 2, "tokens_in": 158682, "tokens_out": 3397, "ctx_chars": 182830, "t_end": 1791523936.8456616, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1058, "lo95": 1.1056, "mean": 1.1058, "ev_only": 1.1062, "ref_ms": 22.24268, "cand_ms": 20.11391, "n_trials": 68, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0652, "r_wall_s": 140.83, "compile_s": 52.14, "r_error": "", "src_len": 3242, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78394, "tout": 1782, "ts": 1791523676.7842546, "chk": "ok", "code_len": 3291}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 80288, "tout": 1615, "ts": 1791523795.7278025, "chk": null, "code_len": 3242}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78394, "started": 1791523659.2642064}
{"ep": "ok-00281", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0001, "speedup": 1.0001, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 443.8, "calls": 4, "tokens_in": 25304, "tokens_out": 7464, "ctx_chars": 5630, "t_end": 1791523941.5289152, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0001, "lo95": 0.999, "mean": 1.0, "ev_only": 1.0014, "ref_ms": 7.92991, "cand_ms": 7.92874, "n_trials": 167, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 152.39, "compile_s": 2.63, "r_error": "", "src_len": 944, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4087, "tout": 3215, "ts": 1791523525.6139991, "chk": "incorrect", "code_len": 2924}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6047, "tout": 2289, "ts": 1791523559.3605707, "chk": "incorrect", "code_len": 1112}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7126, "tout": 1396, "ts": 1791523770.4858575, "chk": "ok", "code_len": 944}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8044, "tout": 564, "ts": 1791523789.0285473, "chk": null, "code_len": 944}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 4087, "started": 1791523497.7728758}
{"ep": "ok-00372", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 84.1, "calls": 1, "tokens_in": 1681, "tokens_out": 1250, "ctx_chars": 0, "t_end": 1791523944.5998602, "error": "RuntimeError: Error building extension 'gemm_div_sum': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemm_div_sum -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "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": 71.41, "compile_s": 71.41, "r_error": "RuntimeError: Error building extension 'gemm_div_sum': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemm_div_sum -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 2422, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1681, "tout": 1250, "ts": 1791523873.1414106, "chk": null, "code_len": 2422}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1681, "started": 1791523860.5273063}
{"ep": "ok-00331", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0222, "speedup": 1.0222, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 233.8, "calls": 3, "tokens_in": 8520, "tokens_out": 2884, "ctx_chars": 0, "t_end": 1791523945.843732, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0222, "lo95": 1.0218, "mean": 1.0221, "ev_only": 1.0232, "ref_ms": 29.77634, "cand_ms": 29.13105, "n_trials": 20, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0335, "r_wall_s": 84.77, "compile_s": 2.21, "r_error": "", "src_len": 2706, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1743, "tout": 1515, "ts": 1791523727.2347758, "chk": "ok", "code_len": 2706}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3370, "tout": 13, "ts": 1791523849.6776924, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3407, "tout": 1356, "ts": 1791523860.5486798, "chk": null, "code_len": 2706}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1743, "started": 1791523712.0860329}
{"ep": "ok-00247", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 7.5962, "speedup": 7.5962, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 585.5, "calls": 3, "tokens_in": 33991, "tokens_out": 41050, "ctx_chars": 4637, "t_end": 1791523949.0037966, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 7.5962, "lo95": 7.2594, "mean": 6.467, "ev_only": 7.6666, "ref_ms": 6.18838, "cand_ms": 0.81467, "n_trials": 138, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9936, "r_wall_s": 66.9, "compile_s": 22.54, "r_error": "", "src_len": 13829, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4068, "tout": 27170, "ts": 1791523608.6299102, "chk": "ok", "code_len": 14101}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11479, "tout": 7135, "ts": 1791523721.706146, "chk": "ok", "code_len": 13829}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 18444, "tout": 6745, "ts": 1791523882.044776, "chk": null, "code_len": 13829}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 4068, "started": 1791523363.4591126}
{"ep": "ok-00342", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.3258, "speedup": 0.3258, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 193.3, "calls": 2, "tokens_in": 12919, "tokens_out": 4178, "ctx_chars": 6513, "t_end": 1791523950.1026225, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.3258, "lo95": 0.3114, "mean": 0.3495, "ev_only": 0.3249, "ref_ms": 3.8304, "cand_ms": 11.75715, "n_trials": 62, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.073, "r_wall_s": 100.62, "compile_s": 2.03, "r_error": "", "src_len": 4056, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5329, "tout": 2149, "ts": 1791523774.3842893, "chk": "ok", "code_len": 4107}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7590, "tout": 2029, "ts": 1791523849.4338953, "chk": null, "code_len": 4056}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5329, "started": 1791523756.8524766}
{"ep": "ok-00304", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.4726, "speedup": 1.4726, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.2, "calls": 2, "tokens_in": 160040, "tokens_out": 13747, "ctx_chars": 182830, "t_end": 1791523950.591526, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4726, "lo95": 1.4694, "mean": 1.5018, "ev_only": 1.4822, "ref_ms": 8.11382, "cand_ms": 5.5098, "n_trials": 222, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9787, "r_wall_s": 61.33, "compile_s": 7.75, "r_error": "", "src_len": 5666, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78174, "tout": 10022, "ts": 1791523692.1619322, "chk": "ok", "code_len": 5666}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81866, "tout": 3725, "ts": 1791523889.1639495, "chk": null, "code_len": 5666}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78174, "started": 1791523601.3716152}
{"ep": "ok-00330", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9621, "speedup": 0.9621, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 240.0, "calls": 3, "tokens_in": 9451, "tokens_out": 3727, "ctx_chars": 495, "t_end": 1791523950.6910667, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9621, "lo95": 0.9615, "mean": 0.9622, "ev_only": 0.9638, "ref_ms": 8.01309, "cand_ms": 8.32844, "n_trials": 148, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.191, "r_wall_s": 88.99, "compile_s": 49.22, "r_error": "", "src_len": 3715, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1738, "tout": 1951, "ts": 1791523736.42361, "chk": "ok", "code_len": 3917}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3801, "tout": 87, "ts": 1791523847.9930387, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3912, "tout": 1689, "ts": 1791523861.6096218, "chk": null, "code_len": 3715}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1738, "started": 1791523710.675401}
{"ep": "ok-00353", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.7889, "speedup": 0.7889, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 160.4, "calls": 2, "tokens_in": 15262, "tokens_out": 5342, "ctx_chars": 9125, "t_end": 1791523951.3849006, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7889, "lo95": 0.7071, "mean": 0.7521, "ev_only": 0.7905, "ref_ms": 22.19998, "cand_ms": 28.13947, "n_trials": 42, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0385, "r_wall_s": 56.74, "compile_s": 12.48, "r_error": "", "src_len": 3717, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6572, "tout": 3495, "ts": 1791523821.9751525, "chk": "ok", "code_len": 3789}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8690, "tout": 1847, "ts": 1791523894.593418, "chk": null, "code_len": 3717}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6572, "started": 1791523791.0167181}
{"ep": "ok-00279", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.006, "speedup": 1.006, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 479.2, "calls": 5, "tokens_in": 38416, "tokens_out": 4059, "ctx_chars": 9192, "t_end": 1791523953.356751, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.006, "lo95": 1.0054, "mean": 1.007, "ev_only": 1.0056, "ref_ms": 7.93193, "cand_ms": 7.88446, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 111.06, "compile_s": 3.29, "r_error": "", "src_len": 975, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 597, "ts": 1791523482.1831074, "chk": "incorrect", "code_len": 1095}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6361, "tout": 1425, "ts": 1791523507.351148, "chk": "incorrect", "code_len": 1157}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7919, "tout": 752, "ts": 1791523554.636705, "chk": "incorrect", "code_len": 1077}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8805, "tout": 763, "ts": 1791523766.8520644, "chk": "ok", "code_len": 975}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9700, "tout": 522, "ts": 1791523842.253654, "chk": null, "code_len": 975}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 5631, "started": 1791523474.1911774}
{"ep": "ok-00286", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0356, "speedup": 1.0356, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 432.3, "calls": 2, "tokens_in": 159633, "tokens_out": 7052, "ctx_chars": 182830, "t_end": 1791523959.4078948, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0356, "lo95": 1.0349, "mean": 1.0357, "ev_only": 1.036, "ref_ms": 29.76743, "cand_ms": 28.74377, "n_trials": 49, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0203, "r_wall_s": 190.76, "compile_s": 55.64, "r_error": "", "src_len": 4761, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78312, "tout": 4064, "ts": 1791523581.3612578, "chk": "ok", "code_len": 4761}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81321, "tout": 2988, "ts": 1791523768.0711033, "chk": null, "code_len": 4761}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78312, "started": 1791523527.1497116}
{"ep": "ok-00356", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.2351, "speedup": 1.2351, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 168.7, "calls": 2, "tokens_in": 6243, "tokens_out": 6329, "ctx_chars": 495, "t_end": 1791523968.5765982, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2351, "lo95": 1.2347, "mean": 1.2337, "ev_only": 1.2337, "ref_ms": 8.20256, "cand_ms": 6.64095, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 34.19, "compile_s": 2.15, "r_error": "", "src_len": 3847, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1858, "tout": 3814, "ts": 1791523832.8506634, "chk": "ok", "code_len": 3847}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4385, "tout": 2515, "ts": 1791523934.3138914, "chk": null, "code_len": 3847}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1858, "started": 1791523799.888019}
{"ep": "ok-00343", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0285, "speedup": 1.0285, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 212.1, "calls": 2, "tokens_in": 13833, "tokens_out": 2172, "ctx_chars": 10373, "t_end": 1791523969.851029, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0285, "lo95": 1.0279, "mean": 1.0297, "ev_only": 1.0272, "ref_ms": 8.16672, "cand_ms": 7.94031, "n_trials": 156, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 176.75, "compile_s": 4.58, "r_error": "", "src_len": 1771, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6270, "tout": 1181, "ts": 1791523767.298174, "chk": "ok", "code_len": 1771}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7563, "tout": 991, "ts": 1791523792.9486961, "chk": null, "code_len": 1771}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6270, "started": 1791523757.7497785}
{"ep": "ok-00319", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0344, "speedup": 1.0344, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 312.9, "calls": 2, "tokens_in": 13089, "tokens_out": 2008, "ctx_chars": 9546, "t_end": 1791523970.7470293, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0344, "lo95": 1.0334, "mean": 1.0346, "ev_only": 1.035, "ref_ms": 8.22842, "cand_ms": 7.9547, "n_trials": 133, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 186.55, "compile_s": 3.16, "r_error": "", "src_len": 1764, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5935, "tout": 1107, "ts": 1791523668.4644682, "chk": "ok", "code_len": 1814}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7154, "tout": 901, "ts": 1791523784.0907314, "chk": null, "code_len": 1764}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5935, "started": 1791523657.8694592}
{"ep": "ok-00309", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0035, "speedup": 1.0035, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 360.1, "calls": 4, "tokens_in": 35103, "tokens_out": 8061, "ctx_chars": 12555, "t_end": 1791523981.5881307, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0035, "lo95": 1.0033, "mean": 1.0035, "ev_only": 1.0041, "ref_ms": 7.91689, "cand_ms": 7.88926, "n_trials": 144, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 188.74, "compile_s": 2.97, "r_error": "", "src_len": 992, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6873, "tout": 2643, "ts": 1791523646.843007, "chk": "incorrect", "code_len": 1751}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8356, "tout": 3080, "ts": 1791523746.7824621, "chk": "incorrect", "code_len": 1117}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9413, "tout": 1534, "ts": 1791523770.6487083, "chk": "ok", "code_len": 992}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10461, "tout": 804, "ts": 1791523792.7445266, "chk": null, "code_len": 992}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6873, "started": 1791523621.4515674}
{"ep": "ok-00310", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.7887, "speedup": 0.7887, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 373.0, "calls": 2, "tokens_in": 163311, "tokens_out": 14494, "ctx_chars": 182830, "t_end": 1791523995.1437354, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7887, "lo95": 0.6312, "mean": 0.7861, "ev_only": 0.7913, "ref_ms": 3.81827, "cand_ms": 4.84098, "n_trials": 172, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.003, "r_wall_s": 121.65, "compile_s": 69.11, "r_error": "", "src_len": 8666, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79195, "tout": 9783, "ts": 1791523708.2205374, "chk": "ok", "code_len": 8666}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 84116, "tout": 4711, "ts": 1791523873.4388845, "chk": null, "code_len": 8666}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79195, "started": 1791523622.1253016}
{"ep": "ok-00402", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "forbidden", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 30.4, "calls": 1, "tokens_in": 2626, "tokens_out": 3750, "ctx_chars": 0, "t_end": 1791523998.9595869, "error": "static check failed: line 87: assignment to attribute 'new_conv.weight.data' is not allowed (only self.<x>); line 88: assignment to attribute 'new_conv.bias.dat", "f_status": "forbidden", "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": 0.01, "compile_s": null, "r_error": "static check failed: line 87: assignment to attribute 'new_conv.weight.data' is not allowed (only self.<x>); line 88: assignment to attribute 'new_conv.bias.dat", "src_len": 4243, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2626, "tout": 3750, "ts": 1791523998.9290633, "chk": null, "code_len": 4243}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2626, "started": 1791523968.576899}
{"ep": "ok-00393", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9968, "speedup": 0.9968, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 57.2, "calls": 3, "tokens_in": 26169, "tokens_out": 2976, "ctx_chars": 14186, "t_end": 1791524001.7752805, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9968, "lo95": 0.9965, "mean": 0.9966, "ev_only": 0.9953, "ref_ms": 8.03875, "cand_ms": 8.0649, "n_trials": 141, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0173, "r_wall_s": 20.9, "compile_s": 2.65, "r_error": "", "src_len": 2893, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7602, "tout": 1536, "ts": 1791523958.2468019, "chk": "ok", "code_len": 2893}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9250, "tout": 43, "ts": 1791523969.1428878, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9317, "tout": 1397, "ts": 1791523980.8018308, "chk": null, "code_len": 2893}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7602, "started": 1791523944.6001937}
{"ep": "ok-00389", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.7648, "speedup": 0.7648, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 85.0, "calls": 3, "tokens_in": 12001, "tokens_out": 4077, "ctx_chars": 0, "t_end": 1791524009.867197, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7648, "lo95": 0.7555, "mean": 0.754, "ev_only": 0.7641, "ref_ms": 4.00772, "cand_ms": 5.24033, "n_trials": 188, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0745, "r_wall_s": 14.38, "compile_s": 1.84, "r_error": "", "src_len": 3536, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2356, "tout": 2327, "ts": 1791523947.6469758, "chk": "ok", "code_len": 3617}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4795, "tout": 31, "ts": 1791523981.2098684, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4850, "tout": 1719, "ts": 1791523995.440044, "chk": null, "code_len": 3536}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2356, "started": 1791523924.9128318}
{"ep": "ok-00365", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9413, "speedup": 0.9413, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 181.2, "calls": 2, "tokens_in": 7124, "tokens_out": 5881, "ctx_chars": 1383, "t_end": 1791524013.779306, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9413, "lo95": 0.9406, "mean": 0.9416, "ev_only": 0.9408, "ref_ms": 29.76739, "cand_ms": 31.62431, "n_trials": 34, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0176, "r_wall_s": 103.0, "compile_s": 17.2, "r_error": "", "src_len": 3626, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2299, "tout": 3927, "ts": 1791523870.9713728, "chk": "ok", "code_len": 3626}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4825, "tout": 1954, "ts": 1791523910.2318048, "chk": null, "code_len": 3626}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2299, "started": 1791523832.5890584}
{"ep": "ok-00400", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.3, "speedup": 0.3, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 72.0, "calls": 3, "tokens_in": 23505, "tokens_out": 4296, "ctx_chars": 9125, "t_end": 1791524025.400733, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.3, "lo95": 0.2994, "mean": 0.3046, "ev_only": 0.2986, "ref_ms": 3.43616, "cand_ms": 11.45517, "n_trials": 130, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.08, "r_wall_s": 15.53, "compile_s": 1.93, "r_error": "", "src_len": 4186, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6279, "tout": 2196, "ts": 1791523976.1219037, "chk": "ok", "code_len": 4271}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8587, "tout": 28, "ts": 1791523993.3734887, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8639, "tout": 2072, "ts": 1791524009.82899, "chk": null, "code_len": 4186}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6279, "started": 1791523953.357236}
{"ep": "ok-00401", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0339, "speedup": 1.0339, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 69.7, "calls": 2, "tokens_in": 14369, "tokens_out": 3343, "ctx_chars": 9546, "t_end": 1791524029.1433163, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0339, "lo95": 1.0337, "mean": 1.0341, "ev_only": 1.0345, "ref_ms": 8.20574, "cand_ms": 7.93705, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0056, "r_wall_s": 23.14, "compile_s": 1.9, "r_error": "", "src_len": 1811, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5935, "tout": 2387, "ts": 1791523980.8996236, "chk": "ok", "code_len": 1811}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8434, "tout": 956, "ts": 1791524005.9565518, "chk": null, "code_len": 1811}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5935, "started": 1791523959.4082253}
{"ep": "ok-00387", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 45.7512, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 121.3, "calls": 2, "tokens_in": 17650, "tokens_out": 7509, "ctx_chars": 12888, "t_end": 1791524037.139171, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 45.7512, "lo95": 45.4218, "mean": 45.1244, "ev_only": 47.3831, "ref_ms": 22.2685, "cand_ms": 0.48673, "n_trials": 68, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 32.5, "compile_s": 1.82, "r_error": "", "src_len": 3436, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7686, "tout": 5832, "ts": 1791523971.30578, "chk": "ok", "code_len": 3436}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9964, "tout": 1677, "ts": 1791524004.3544984, "chk": null, "code_len": 3436}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7686, "started": 1791523915.8595963}
{"ep": "ok-00411", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 15.1, "calls": 1, "tokens_in": 3925, "tokens_out": 594, "ctx_chars": 5534, "t_end": 1791524040.5072384, "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": 0.1111, "r_wall_s": 9.03, "compile_s": 2.13, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1091, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 3925, "tout": 594, "ts": 1791524031.431024, "chk": null, "code_len": 1091}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 3925, "started": 1791524025.401091}
{"ep": "ok-00344", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.5323, "speedup": 0.5323, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 287.0, "calls": 2, "tokens_in": 13253, "tokens_out": 5424, "ctx_chars": 6861, "t_end": 1791524047.543428, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.5323, "lo95": 0.5058, "mean": 0.7218, "ev_only": 0.535, "ref_ms": 3.73514, "cand_ms": 7.01647, "n_trials": 180, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 126.72, "compile_s": 23.6, "r_error": "", "src_len": 3935, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 3317, "ts": 1791523788.629464, "chk": "ok", "code_len": 3935}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7851, "tout": 2107, "ts": 1791523920.779427, "chk": null, "code_len": 3935}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791523760.558851}
{"ep": "ok-00352", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.6471, "speedup": 0.6471, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 259.7, "calls": 4, "tokens_in": 33729, "tokens_out": 17409, "ctx_chars": 0, "t_end": 1791524049.9490097, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.6471, "lo95": 0.6448, "mean": 0.6534, "ev_only": 0.6478, "ref_ms": 16.23926, "cand_ms": 25.09628, "n_trials": 50, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.052, "r_wall_s": 14.96, "compile_s": 2.62, "r_error": "", "src_len": 3788, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 7914, "ts": 1791523858.9507904, "chk": "incorrect", "code_len": 7206}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6887, "tout": 4793, "ts": 1791523972.5340137, "chk": "incorrect", "code_len": 7446}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 10868, "tout": 2783, "ts": 1791524012.0284507, "chk": "ok", "code_len": 3788}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13055, "tout": 1919, "ts": 1791524034.945211, "chk": null, "code_len": 3788}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2919, "started": 1791523790.2182255}
{"ep": "ok-00399", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.005, "speedup": 1.005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 103.2, "calls": 4, "tokens_in": 21216, "tokens_out": 3201, "ctx_chars": 5534, "t_end": 1791524054.5984247, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.005, "lo95": 1.0044, "mean": 1.0049, "ev_only": 1.0047, "ref_ms": 7.93574, "cand_ms": 7.89633, "n_trials": 232, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 24.85, "compile_s": 1.97, "r_error": "", "src_len": 910, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3925, "tout": 647, "ts": 1791523962.6733575, "chk": "incorrect", "code_len": 945}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4705, "tout": 979, "ts": 1791523995.781105, "chk": "ok", "code_len": 910}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5793, "tout": 867, "ts": 1791524013.3244371, "chk": "incorrect", "code_len": 962}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6793, "tout": 708, "ts": 1791524029.70818, "chk": null, "code_len": 910}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "incorrect", null], "first_tin": 3925, "started": 1791523951.3851871}
{"ep": "ok-00408", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0279, "speedup": 1.0279, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 54.9, "calls": 3, "tokens_in": 16706, "tokens_out": 1870, "ctx_chars": 7308, "t_end": 1791524056.6426632, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0279, "lo95": 1.0274, "mean": 1.0277, "ev_only": 1.0261, "ref_ms": 8.15908, "cand_ms": 7.9376, "n_trials": 180, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 28.74, "compile_s": 3.16, "r_error": "", "src_len": 1816, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4853, "tout": 912, "ts": 1791524009.683195, "chk": "ok", "code_len": 1816}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5877, "tout": 75, "ts": 1791524020.0317004, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5976, "tout": 883, "ts": 1791524027.738791, "chk": null, "code_len": 1816}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4853, "started": 1791524001.7756152}
{"ep": "ok-00378", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.999, "speedup": 0.999, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 182.5, "calls": 2, "tokens_in": 8632, "tokens_out": 4382, "ctx_chars": 3636, "t_end": 1791524060.663194, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.999, "lo95": 0.996, "mean": 0.986, "ev_only": 1.0017, "ref_ms": 8.18297, "cand_ms": 8.19122, "n_trials": 129, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0075, "r_wall_s": 88.68, "compile_s": 3.24, "r_error": "", "src_len": 3172, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3285, "tout": 2752, "ts": 1791523909.506266, "chk": "ok", "code_len": 3172}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5347, "tout": 1630, "ts": 1791523971.8769503, "chk": null, "code_len": 3172}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3285, "started": 1791523878.1618009}
{"ep": "ok-00404", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0258, "speedup": 1.0258, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 90.2, "calls": 3, "tokens_in": 20929, "tokens_out": 1838, "ctx_chars": 10373, "t_end": 1791524060.946081, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0258, "lo95": 1.025, "mean": 1.0258, "ev_only": 1.0263, "ref_ms": 8.15967, "cand_ms": 7.95422, "n_trials": 186, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0065, "r_wall_s": 41.89, "compile_s": 1.86, "r_error": "", "src_len": 1846, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6268, "tout": 932, "ts": 1791523979.1141055, "chk": "ok", "code_len": 1846}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7312, "tout": 13, "ts": 1791524011.44409, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7349, "tout": 893, "ts": 1791524018.9664223, "chk": null, "code_len": 1846}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6268, "started": 1791523970.747375}
{"ep": "ok-00364", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0382, "speedup": 1.0382, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 238.7, "calls": 2, "tokens_in": 5496, "tokens_out": 4848, "ctx_chars": 0, "t_end": 1791524068.6260917, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0382, "lo95": 1.0374, "mean": 1.0395, "ev_only": 1.0372, "ref_ms": 29.79469, "cand_ms": 28.69722, "n_trials": 44, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0196, "r_wall_s": 156.25, "compile_s": 17.98, "r_error": "", "src_len": 2879, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1745, "tout": 3233, "ts": 1791523875.8061652, "chk": "ok", "code_len": 2879}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3751, "tout": 1615, "ts": 1791523911.5583043, "chk": null, "code_len": 2879}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1745, "started": 1791523829.9133434}
{"ep": "ok-00373", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8334, "speedup": 0.8334, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 223.4, "calls": 3, "tokens_in": 254367, "tokens_out": 13422, "ctx_chars": 182830, "t_end": 1791524084.7770653, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8334, "lo95": 0.8328, "mean": 0.8476, "ev_only": 0.8335, "ref_ms": 8.21759, "cand_ms": 9.86047, "n_trials": 128, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9996, "r_wall_s": 28.58, "compile_s": 1.91, "r_error": "", "src_len": 3918, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78367, "tout": 7716, "ts": 1791523935.6770177, "chk": "incorrect", "code_len": 3899}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 86216, "tout": 3456, "ts": 1791524020.7936578, "chk": "ok", "code_len": 3918}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 89784, "tout": 2250, "ts": 1791524056.1514196, "chk": null, "code_len": 3918}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78367, "started": 1791523861.3893788}
{"ep": "ok-00347", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9982, "speedup": 0.9982, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 320.2, "calls": 5, "tokens_in": 43128, "tokens_out": 3811, "ctx_chars": 12555, "t_end": 1791524088.1101832, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9982, "lo95": 0.9975, "mean": 0.9982, "ev_only": 0.9993, "ref_ms": 7.93385, "cand_ms": 7.9479, "n_trials": 171, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 46.28, "compile_s": 1.97, "r_error": "", "src_len": 930, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6871, "tout": 594, "ts": 1791523791.014541, "chk": "incorrect", "code_len": 999}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7598, "tout": 770, "ts": 1791523963.623296, "chk": "incorrect", "code_len": 957}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8501, "tout": 840, "ts": 1791523999.5714083, "chk": "incorrect", "code_len": 1033}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9474, "tout": 1078, "ts": 1791524019.2887795, "chk": "ok", "code_len": 930}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 10684, "tout": 529, "ts": 1791524041.786346, "chk": null, "code_len": 930}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 6871, "started": 1791523767.8997743}
{"ep": "ok-00382", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9949, "speedup": 0.9949, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 193.4, "calls": 3, "tokens_in": 17360, "tokens_out": 2949, "ctx_chars": 7273, "t_end": 1791524089.702594, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9949, "lo95": 0.9944, "mean": 1.013, "ev_only": 0.9958, "ref_ms": 8.03179, "cand_ms": 8.07315, "n_trials": 145, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0173, "r_wall_s": 19.18, "compile_s": 1.94, "r_error": "", "src_len": 2872, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4686, "tout": 1497, "ts": 1791523909.1901026, "chk": "ok", "code_len": 2872}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6295, "tout": 60, "ts": 1791524058.812262, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6379, "tout": 1392, "ts": 1791524070.4439387, "chk": null, "code_len": 2872}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4686, "started": 1791523896.3486722}
{"ep": "ok-00329", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.4613, "speedup": 1.4613, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 385.5, "calls": 3, "tokens_in": 12779, "tokens_out": 8840, "ctx_chars": 0, "t_end": 1791524091.3675673, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.4613, "lo95": 1.4592, "mean": 1.4543, "ev_only": 1.4661, "ref_ms": 8.28489, "cand_ms": 5.66941, "n_trials": 160, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9995, "r_wall_s": 174.75, "compile_s": 19.55, "r_error": "", "src_len": 3587, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 4043, "ts": 1791523741.162022, "chk": "incorrect", "code_len": 3592}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4346, "tout": 2741, "ts": 1791523866.7181334, "chk": "ok", "code_len": 3587}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6631, "tout": 2056, "ts": 1791523916.5686731, "chk": null, "code_len": 3587}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1802, "started": 1791523705.8350244}
{"ep": "ok-00302", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.9936, "speedup": 0.9936, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 501.5, "calls": 4, "tokens_in": 20890, "tokens_out": 6403, "ctx_chars": 0, "t_end": 1791524098.865264, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9936, "lo95": 0.9929, "mean": 0.993, "ev_only": 0.9958, "ref_ms": 8.09884, "cand_ms": 8.15125, "n_trials": 210, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0189, "r_wall_s": 208.94, "compile_s": 22.68, "r_error": "", "src_len": 4543, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1605, "tout": 2261, "ts": 1791523618.1300638, "chk": "compile_error", "code_len": 4549}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4961, "tout": 2053, "ts": 1791523837.6332493, "chk": "ok", "code_len": 4543}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7126, "tout": 48, "ts": 1791523873.4878204, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7198, "tout": 2041, "ts": 1791523889.82103, "chk": null, "code_len": 4543}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1605, "started": 1791523597.3781977}
{"ep": "ok-00358", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.4455, "speedup": 1.4455, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 301.5, "calls": 2, "tokens_in": 6637, "tokens_out": 7011, "ctx_chars": 495, "t_end": 1791524105.7254255, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.4455, "lo95": 1.4438, "mean": 1.4424, "ev_only": 1.4485, "ref_ms": 8.31377, "cand_ms": 5.75151, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 143.33, "compile_s": 1.98, "r_error": "", "src_len": 4096, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1935, "tout": 4548, "ts": 1791523864.429471, "chk": "ok", "code_len": 4096}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4702, "tout": 2463, "ts": 1791523962.3689988, "chk": null, "code_len": 4096}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1935, "started": 1791523824.6449006}
{"ep": "ok-00409", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.8933, "speedup": 0.8933, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 100.7, "calls": 2, "tokens_in": 13199, "tokens_out": 8022, "ctx_chars": 5888, "t_end": 1791524110.5740943, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8933, "lo95": 0.8885, "mean": 0.8978, "ev_only": 0.8909, "ref_ms": 3.37306, "cand_ms": 3.77581, "n_trials": 178, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4875, "r_wall_s": 17.21, "compile_s": 2.76, "r_error": "", "src_len": 5282, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5062, "tout": 5379, "ts": 1791524056.7142112, "chk": "ok", "code_len": 5282}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8137, "tout": 2643, "ts": 1791524093.340237, "chk": null, "code_len": 5282}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5062, "started": 1791524009.867444}
{"ep": "ok-00391", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0322, "speedup": 1.0322, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 175.6, "calls": 2, "tokens_in": 10885, "tokens_out": 2207, "ctx_chars": 7159, "t_end": 1791524112.4037845, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0322, "lo95": 1.0314, "mean": 1.0312, "ev_only": 1.0302, "ref_ms": 8.2318, "cand_ms": 7.9748, "n_trials": 108, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 123.76, "compile_s": 3.08, "r_error": "", "src_len": 1836, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4795, "tout": 1183, "ts": 1791523946.6163328, "chk": "ok", "code_len": 1836}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6090, "tout": 1024, "ts": 1791523988.5379636, "chk": null, "code_len": 1836}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4795, "started": 1791523936.8459992}
{"ep": "ok-00357", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0304, "speedup": 1.0304, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 311.1, "calls": 2, "tokens_in": 7398, "tokens_out": 5357, "ctx_chars": 2175, "t_end": 1791524113.5039473, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0304, "lo95": 1.0301, "mean": 1.0304, "ev_only": 1.0309, "ref_ms": 29.63882, "cand_ms": 28.7633, "n_trials": 43, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0246, "r_wall_s": 216.8, "compile_s": 11.79, "r_error": "", "src_len": 3200, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2546, "tout": 3532, "ts": 1791523833.1109083, "chk": "ok", "code_len": 3200}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4852, "tout": 1825, "ts": 1791523895.699404, "chk": null, "code_len": 3200}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2546, "started": 1791523802.436928}
{"ep": "ok-00417", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0399, "speedup": 1.0399, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 59.8, "calls": 2, "tokens_in": 5148, "tokens_out": 3205, "ctx_chars": 0, "t_end": 1791524114.4023883, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0399, "lo95": 1.0395, "mean": 1.0408, "ev_only": 1.042, "ref_ms": 8.20278, "cand_ms": 7.88824, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0036, "r_wall_s": 23.41, "compile_s": 2.08, "r_error": "", "src_len": 1666, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 2339, "ts": 1791524075.9394965, "chk": "ok", "code_len": 1666}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3346, "tout": 866, "ts": 1791524090.9650905, "chk": null, "code_len": 1666}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524054.5986958}
{"ep": "ok-00398", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0256, "speedup": 1.0256, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.7, "calls": 3, "tokens_in": 25899, "tokens_out": 12124, "ctx_chars": 5888, "t_end": 1791524115.399935, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0256, "lo95": 0.9055, "mean": 1.0186, "ev_only": 1.0251, "ref_ms": 33.32905, "cand_ms": 32.49587, "n_trials": 32, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0329, "r_wall_s": 18.37, "compile_s": 2.48, "r_error": "", "src_len": 3589, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5353, "tout": 7179, "ts": 1791524012.8572285, "chk": "incorrect", "code_len": 6915}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9222, "tout": 3217, "ts": 1791524050.8486755, "chk": "ok", "code_len": 3834}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11324, "tout": 1728, "ts": 1791524097.0036147, "chk": null, "code_len": 3589}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5353, "started": 1791523950.6913033}
{"ep": "ok-00376", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0956, "speedup": 1.0956, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 244.8, "calls": 3, "tokens_in": 24117, "tokens_out": 2044, "ctx_chars": 12121, "t_end": 1791524117.0531087, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0956, "lo95": 1.0901, "mean": 1.0927, "ev_only": 1.0932, "ref_ms": 22.41869, "cand_ms": 20.46194, "n_trials": 76, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0403, "r_wall_s": 202.48, "compile_s": 20.17, "r_error": "", "src_len": 2063, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7260, "tout": 1038, "ts": 1791523881.9130225, "chk": "ok", "code_len": 2063}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8410, "tout": 13, "ts": 1791523906.2052813, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8447, "tout": 993, "ts": 1791523914.3028207, "chk": null, "code_len": 2063}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7260, "started": 1791523872.2123568}
{"ep": "ok-00360", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.4555, "speedup": 0.4555, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 301.3, "calls": 2, "tokens_in": 10384, "tokens_out": 15621, "ctx_chars": 0, "t_end": 1791524117.0763896, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.4555, "lo95": 0.4542, "mean": 0.447, "ev_only": 0.4528, "ref_ms": 3.36528, "cand_ms": 7.38856, "n_trials": 190, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4363, "r_wall_s": 26.34, "compile_s": 2.09, "r_error": "", "src_len": 8338, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 11114, "ts": 1791523914.1774397, "chk": "ok", "code_len": 8338}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7756, "tout": 4507, "ts": 1791524090.711964, "chk": null, "code_len": 8338}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791523815.8214884}
{"ep": "ok-00420", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0365, "speedup": 1.0365, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 58.2, "calls": 2, "tokens_in": 10331, "tokens_out": 2867, "ctx_chars": 6332, "t_end": 1791524119.1149993, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0365, "lo95": 1.036, "mean": 1.0396, "ev_only": 1.0371, "ref_ms": 8.26062, "cand_ms": 7.96959, "n_trials": 176, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0037, "r_wall_s": 25.01, "compile_s": 1.98, "r_error": "", "src_len": 1721, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4462, "tout": 1938, "ts": 1791524078.7901335, "chk": "ok", "code_len": 1721}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5869, "tout": 929, "ts": 1791524094.0849748, "chk": null, "code_len": 1721}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4462, "started": 1791524060.9464142}
{"ep": "ok-00412", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0061, "speedup": 1.0061, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 94.4, "calls": 2, "tokens_in": 15267, "tokens_out": 5515, "ctx_chars": 10823, "t_end": 1791524123.5756352, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0061, "lo95": 1.0056, "mean": 1.006, "ev_only": 1.0066, "ref_ms": 8.03921, "cand_ms": 7.99053, "n_trials": 160, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0096, "r_wall_s": 31.98, "compile_s": 2.15, "r_error": "", "src_len": 3995, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 3548, "ts": 1791524059.6071405, "chk": "ok", "code_len": 3995}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8903, "tout": 1967, "ts": 1791524091.5309885, "chk": null, "code_len": 3995}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6364, "started": 1791524029.1436448}
{"ep": "ok-00414", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9919, "speedup": 0.9919, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 85.9, "calls": 2, "tokens_in": 16927, "tokens_out": 3067, "ctx_chars": 14186, "t_end": 1791524126.4090934, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9919, "lo95": 0.991, "mean": 0.992, "ev_only": 0.9942, "ref_ms": 8.04491, "cand_ms": 8.11031, "n_trials": 147, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0169, "r_wall_s": 39.61, "compile_s": 2.13, "r_error": "", "src_len": 2900, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7602, "tout": 1611, "ts": 1791524055.0726385, "chk": "ok", "code_len": 2971}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9325, "tout": 1456, "ts": 1791524086.7346342, "chk": null, "code_len": 2900}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7602, "started": 1791524040.5075743}
{"ep": "ok-00284", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 8.1858, "speedup": 8.1858, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 615.5, "calls": 3, "tokens_in": 30578, "tokens_out": 20796, "ctx_chars": 8224, "t_end": 1791524134.8978047, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 8.1858, "lo95": 7.1667, "mean": 8.1583, "ev_only": 8.2434, "ref_ms": 43.28857, "cand_ms": 5.28824, "n_trials": 50, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 196.47, "compile_s": 15.93, "r_error": "", "src_len": 7743, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5495, "tout": 12195, "ts": 1791523625.8229153, "chk": "no_custom_kernel", "code_len": 8211}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10427, "tout": 4547, "ts": 1791523757.0298665, "chk": "ok", "code_len": 7743}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14656, "tout": 4054, "ts": 1791523938.3950722, "chk": null, "code_len": 7743}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5495, "started": 1791523519.3525002}
{"ep": "ok-00392", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.9897, "speedup": 0.9897, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 194.6, "calls": 3, "tokens_in": 18152, "tokens_out": 2984, "ctx_chars": 7758, "t_end": 1791524136.10187, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9897, "lo95": 0.9886, "mean": 0.9933, "ev_only": 0.9928, "ref_ms": 8.0793, "cand_ms": 8.1631, "n_trials": 146, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0175, "r_wall_s": 159.29, "compile_s": 2.22, "r_error": "", "src_len": 2936, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4947, "tout": 1500, "ts": 1791523954.3129032, "chk": "ok", "code_len": 2936}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6559, "tout": 63, "ts": 1791523965.0077288, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6646, "tout": 1421, "ts": 1791523976.7346222, "chk": null, "code_len": 2936}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4947, "started": 1791523941.529238}
{"ep": "ok-00375", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 6.1161, "speedup": 6.1161, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 271.8, "calls": 3, "tokens_in": 22816, "tokens_out": 18963, "ctx_chars": 2425, "t_end": 1791524139.7702866, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 6.1161, "lo95": 5.897, "mean": 5.9218, "ev_only": 6.086, "ref_ms": 4.19709, "cand_ms": 0.68624, "n_trials": 214, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8354, "r_wall_s": 39.98, "compile_s": 13.26, "r_error": "", "src_len": 7933, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 10785, "ts": 1791523983.0224168, "chk": "no_custom_kernel", "code_len": 7934}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7725, "tout": 4334, "ts": 1791524042.261236, "chk": "ok", "code_len": 7933}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11817, "tout": 3844, "ts": 1791524099.7667794, "chk": null, "code_len": 7933}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 3274, "started": 1791523888.4391294}
{"ep": "ok-00366", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 4.3879, "speedup": 4.3879, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 323.9, "calls": 2, "tokens_in": 12826, "tokens_out": 23255, "ctx_chars": 2425, "t_end": 1791524156.480077, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.3879, "lo95": 4.3744, "mean": 4.4215, "ev_only": 4.3756, "ref_ms": 3.92328, "cand_ms": 0.89411, "n_trials": 218, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9959, "r_wall_s": 104.92, "compile_s": 12.71, "r_error": "", "src_len": 11441, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 17668, "ts": 1791523992.3634837, "chk": "ok", "code_len": 11441}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9552, "tout": 5587, "ts": 1791524051.449785, "chk": null, "code_len": 11441}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3274, "started": 1791523832.5969317}
{"ep": "ok-00397", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.0631, "speedup": 0.0631, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 208.3, "calls": 3, "tokens_in": 25989, "tokens_out": 6205, "ctx_chars": 8141, "t_end": 1791524158.9255438, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0631, "lo95": 0.0599, "mean": 0.0667, "ev_only": 0.063, "ref_ms": 32.3399, "cand_ms": 512.40459, "n_trials": 13, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2232, "r_wall_s": 22.38, "compile_s": 2.41, "r_error": "", "src_len": 2510, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5389, "tout": 4625, "ts": 1791523993.626414, "chk": "ok", "code_len": 2510}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10126, "tout": 324, "ts": 1791524125.772152, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10474, "tout": 1256, "ts": 1791524136.5025973, "chk": null, "code_len": 2510}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5389, "started": 1791523950.5919228}
{"ep": "ok-00354", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0017, "speedup": 1.0017, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 369.6, "calls": 5, "tokens_in": 408753, "tokens_out": 6859, "ctx_chars": 182830, "t_end": 1791524162.4630756, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0017, "lo95": 1.0005, "mean": 1.0098, "ev_only": 1.001, "ref_ms": 7.98136, "cand_ms": 7.96788, "n_trials": 148, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 32.9, "compile_s": 1.95, "r_error": "", "src_len": 952, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78248, "tout": 2044, "ts": 1791523813.1320298, "chk": "incorrect", "code_len": 1757}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 80425, "tout": 1502, "ts": 1791523840.1012962, "chk": "incorrect", "code_len": 1778}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 82060, "tout": 1184, "ts": 1791523912.735268, "chk": "incorrect", "code_len": 1226}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 83378, "tout": 1108, "ts": 1791523972.1063545, "chk": "incorrect", "code_len": 1236}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 84642, "tout": 1021, "ts": 1791524129.5175047, "chk": null, "code_len": 952}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 78248, "started": 1791523792.8965309}
{"ep": "ok-00341", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.031, "speedup": 1.031, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 413.5, "calls": 2, "tokens_in": 11817, "tokens_out": 4824, "ctx_chars": 7221, "t_end": 1791524167.7835543, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.031, "lo95": 1.0305, "mean": 1.031, "ev_only": 1.0309, "ref_ms": 29.75084, "cand_ms": 28.85616, "n_trials": 52, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0279, "r_wall_s": 247.92, "compile_s": 22.82, "r_error": "", "src_len": 2975, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4831, "tout": 3189, "ts": 1791523783.422674, "chk": "ok", "code_len": 2975}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6986, "tout": 1635, "ts": 1791523919.0000598, "chk": null, "code_len": 2975}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4831, "started": 1791523754.252728}
{"ep": "ok-00435", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0145, "speedup": 1.0145, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 50.9, "calls": 1, "tokens_in": 1723, "tokens_out": 1089, "ctx_chars": 0, "t_end": 1791524169.991255, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0145, "lo95": 1.0136, "mean": 1.0201, "ev_only": 1.021, "ref_ms": 8.1981, "cand_ms": 8.08065, "n_trials": 149, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 40.03, "compile_s": 1.96, "r_error": "", "src_len": 2137, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1723, "tout": 1089, "ts": 1791524129.8664641, "chk": null, "code_len": 2137}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1723, "started": 1791524119.1154568}
{"ep": "ok-00315", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 75.2254, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 523.5, "calls": 2, "tokens_in": 160399, "tokens_out": 9709, "ctx_chars": 182830, "t_end": 1791524171.3927274, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 75.2254, "lo95": 73.7272, "mean": 63.6132, "ev_only": 84.2, "ref_ms": 22.44884, "cand_ms": 0.29842, "n_trials": 65, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 247.68, "compile_s": 74.93, "r_error": "", "src_len": 5811, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78396, "tout": 6521, "ts": 1791523712.885568, "chk": "ok", "code_len": 5811}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82003, "tout": 3188, "ts": 1791523923.2779903, "chk": null, "code_len": 5811}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78396, "started": 1791523647.8843174}
{"ep": "ok-00396", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0081, "speedup": 1.0081, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 230.8, "calls": 3, "tokens_in": 20360, "tokens_out": 6298, "ctx_chars": 9192, "t_end": 1791524180.8762271, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0081, "lo95": 1.0061, "mean": 1.0217, "ev_only": 1.0062, "ref_ms": 7.98883, "cand_ms": 7.92459, "n_trials": 164, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 139.13, "compile_s": 3.07, "r_error": "", "src_len": 982, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5633, "tout": 2064, "ts": 1791523970.232835, "chk": "incorrect", "code_len": 1488}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6861, "tout": 3664, "ts": 1791524023.2595644, "chk": "ok", "code_len": 982}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7866, "tout": 570, "ts": 1791524041.6349704, "chk": null, "code_len": 982}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5633, "started": 1791523950.1029851}
{"ep": "ok-00388", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.73, "speedup": 0.73, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 263.2, "calls": 5, "tokens_in": 58567, "tokens_out": 10191, "ctx_chars": 9125, "t_end": 1791524181.4448774, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.73, "lo95": 0.7123, "mean": 0.793, "ev_only": 0.7322, "ref_ms": 16.80672, "cand_ms": 23.02435, "n_trials": 57, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.061, "r_wall_s": 77.75, "compile_s": 2.02, "r_error": "", "src_len": 4566, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6570, "tout": 2674, "ts": 1791523939.7995446, "chk": "incorrect", "code_len": 5587}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9377, "tout": 3007, "ts": 1791524007.0305173, "chk": "incorrect", "code_len": 5836}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12518, "tout": 2367, "ts": 1791524036.983435, "chk": "ok", "code_len": 4566}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14994, "tout": 67, "ts": 1791524086.1304746, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 15108, "tout": 2076, "ts": 1791524103.6608238, "chk": null, "code_len": 4566}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 6570, "started": 1791523918.2012362}
{"ep": "ok-00333", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0358, "speedup": 1.0358, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 458.5, "calls": 2, "tokens_in": 159851, "tokens_out": 7312, "ctx_chars": 182830, "t_end": 1791524182.4636476, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0358, "lo95": 1.0353, "mean": 1.0359, "ev_only": 1.0356, "ref_ms": 29.7619, "cand_ms": 28.73445, "n_trials": 56, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0202, "r_wall_s": 283.96, "compile_s": 68.21, "r_error": "", "src_len": 5267, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78312, "tout": 4321, "ts": 1791523760.9457893, "chk": "ok", "code_len": 5267}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81539, "tout": 2991, "ts": 1791523897.9363697, "chk": null, "code_len": 5267}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78312, "started": 1791523723.9671898}
{"ep": "ok-00361", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.034, "speedup": 1.034, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 378.4, "calls": 3, "tokens_in": 17651, "tokens_out": 3436, "ctx_chars": 5518, "t_end": 1791524197.8715672, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.034, "lo95": 1.0333, "mean": 1.0332, "ev_only": 1.0336, "ref_ms": 8.28039, "cand_ms": 8.00778, "n_trials": 146, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 293.62, "compile_s": 9.97, "r_error": "", "src_len": 1697, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4076, "tout": 2581, "ts": 1791523841.7269497, "chk": "ok", "code_len": 1697}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6769, "tout": 13, "ts": 1791523888.5698085, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6806, "tout": 842, "ts": 1791523904.1304467, "chk": null, "code_len": 1697}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4076, "started": 1791523819.484393}
{"ep": "ok-00370", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.032, "speedup": 1.032, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.6, "calls": 3, "tokens_in": 15969, "tokens_out": 2655, "ctx_chars": 5518, "t_end": 1791524201.0815759, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.032, "lo95": 1.0314, "mean": 1.0334, "ev_only": 1.0334, "ref_ms": 8.27728, "cand_ms": 8.02042, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0049, "r_wall_s": 308.88, "compile_s": 11.52, "r_error": "", "src_len": 1805, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4076, "tout": 1724, "ts": 1791523867.2215974, "chk": "ok", "code_len": 1805}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5912, "tout": 45, "ts": 1791523884.5952418, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5981, "tout": 886, "ts": 1791523892.1542904, "chk": null, "code_len": 1805}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4076, "started": 1791523851.4858806}
{"ep": "ok-00369", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0991, "speedup": 1.0991, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 361.2, "calls": 3, "tokens_in": 242783, "tokens_out": 4779, "ctx_chars": 182830, "t_end": 1791524209.5751178, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0991, "lo95": 1.0942, "mean": 1.0974, "ev_only": 1.0974, "ref_ms": 22.38756, "cand_ms": 20.36844, "n_trials": 49, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0411, "r_wall_s": 112.53, "compile_s": 53.05, "r_error": "", "src_len": 3255, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78394, "tout": 1684, "ts": 1791523865.6744773, "chk": "compile_error", "code_len": 3305}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81375, "tout": 1527, "ts": 1791523952.313601, "chk": "ok", "code_len": 3255}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 83014, "tout": 1568, "ts": 1791524096.8354647, "chk": null, "code_len": 3255}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", null], "first_tin": 78394, "started": 1791523848.3766527}
{"ep": "ok-00406", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.036, "speedup": 1.036, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 220.3, "calls": 2, "tokens_in": 6433, "tokens_out": 6374, "ctx_chars": 0, "t_end": 1791524215.4786046, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.036, "lo95": 1.0308, "mean": 1.0342, "ev_only": 1.0342, "ref_ms": 29.83574, "cand_ms": 28.79854, "n_trials": 23, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0199, "r_wall_s": 107.27, "compile_s": 11.3, "r_error": "", "src_len": 5019, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1745, "tout": 3904, "ts": 1791524049.883052, "chk": "ok", "code_len": 5019}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4688, "tout": 2470, "ts": 1791524107.263148, "chk": null, "code_len": 5019}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1745, "started": 1791524015.4925115}
{"ep": "ok-00363", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0216, "speedup": 1.0216, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 391.0, "calls": 3, "tokens_in": 20342, "tokens_out": 2881, "ctx_chars": 9128, "t_end": 1791524219.0344734, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0216, "lo95": 1.0212, "mean": 1.0215, "ev_only": 1.0212, "ref_ms": 29.78714, "cand_ms": 29.15816, "n_trials": 45, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0345, "r_wall_s": 324.06, "compile_s": 11.68, "r_error": "", "src_len": 2693, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5681, "tout": 1512, "ts": 1791523850.45394, "chk": "ok", "code_len": 2693}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7305, "tout": 27, "ts": 1791523883.366187, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7356, "tout": 1342, "ts": 1791523894.391668, "chk": null, "code_len": 2693}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5681, "started": 1791523828.0198262}
{"ep": "ok-00394", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.5693, "speedup": 0.5693, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 274.3, "calls": 4, "tokens_in": 35426, "tokens_out": 17337, "ctx_chars": 0, "t_end": 1791524220.1448236, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.5693, "lo95": 0.4865, "mean": 0.7228, "ev_only": 0.5699, "ref_ms": 19.41688, "cand_ms": 34.10375, "n_trials": 18, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0191, "r_wall_s": 69.28, "compile_s": 2.68, "r_error": "", "src_len": 3624, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 7979, "ts": 1791524013.2420757, "chk": "incorrect", "code_len": 7324}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7219, "tout": 4940, "ts": 1791524060.1144361, "chk": "incorrect", "code_len": 7748}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11557, "tout": 2601, "ts": 1791524111.0388746, "chk": "ok", "code_len": 3894}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13731, "tout": 1817, "ts": 1791524150.8145392, "chk": null, "code_len": 3624}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2919, "started": 1791523945.844046}
{"ep": "ok-00403", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.7567, "speedup": 0.7567, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 255.4, "calls": 2, "tokens_in": 164275, "tokens_out": 13949, "ctx_chars": 182830, "t_end": 1791524225.2327187, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7567, "lo95": 0.5282, "mean": 0.7825, "ev_only": 0.7568, "ref_ms": 25.03852, "cand_ms": 33.09011, "n_trials": 40, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0282, "r_wall_s": 90.01, "compile_s": 50.58, "r_error": "", "src_len": 10049, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79486, "tout": 8343, "ts": 1791524041.1662948, "chk": "ok", "code_len": 10049}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 84789, "tout": 5606, "ts": 1791524135.1965516, "chk": null, "code_len": 10049}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79486, "started": 1791523969.8512836}
{"ep": "ok-00426", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.8261, "speedup": 0.8261, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 126.6, "calls": 4, "tokens_in": 24072, "tokens_out": 5311, "ctx_chars": 2425, "t_end": 1791524225.4697437, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8261, "lo95": 0.823, "mean": 0.8852, "ev_only": 0.8258, "ref_ms": 4.12161, "cand_ms": 4.98912, "n_trials": 202, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0216, "r_wall_s": 32.87, "compile_s": 1.82, "r_error": "", "src_len": 3370, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 1954, "ts": 1791524116.8186827, "chk": "runtime_error", "code_len": 3390}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5726, "tout": 1631, "ts": 1791524149.6328428, "chk": "ok", "code_len": 3370}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7469, "tout": 112, "ts": 1791524179.22322, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7605, "tout": 1614, "ts": 1791524192.4901955, "chk": null, "code_len": 3370}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", "no_code", null], "first_tin": 3272, "started": 1791524098.8658285}
{"ep": "ok-00386", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.9579, "speedup": 0.9579, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 314.2, "calls": 4, "tokens_in": 18572, "tokens_out": 4590, "ctx_chars": 0, "t_end": 1791524230.0277472, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9579, "lo95": 0.9557, "mean": 0.9564, "ev_only": 0.9562, "ref_ms": 29.89708, "cand_ms": 31.21021, "n_trials": 37, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0994, "r_wall_s": 169.38, "compile_s": 43.3, "r_error": "", "src_len": 3130, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1743, "tout": 1543, "ts": 1791523929.816655, "chk": "compile_error", "code_len": 3255}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4497, "tout": 1521, "ts": 1791523998.0426424, "chk": "ok", "code_len": 3130}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6130, "tout": 48, "ts": 1791524047.7004719, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6202, "tout": 1478, "ts": 1791524059.936968, "chk": null, "code_len": 3130}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1743, "started": 1791523915.8486567}
{"ep": "ok-00425", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0206, "speedup": 1.0206, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 145.9, "calls": 3, "tokens_in": 25394, "tokens_out": 2925, "ctx_chars": 12352, "t_end": 1791524237.2651067, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0206, "lo95": 1.0199, "mean": 1.0208, "ev_only": 1.0203, "ref_ms": 29.69062, "cand_ms": 29.09212, "n_trials": 44, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0329, "r_wall_s": 88.07, "compile_s": 2.75, "r_error": "", "src_len": 2653, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1576, "ts": 1791524106.6031685, "chk": "ok", "code_len": 2800}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9015, "tout": 13, "ts": 1791524137.7228436, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9052, "tout": 1336, "ts": 1791524148.5121927, "chk": null, "code_len": 2653}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7327, "started": 1791524091.3678699}
{"ep": "ok-00405", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9973, "speedup": 0.9973, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 256.3, "calls": 2, "tokens_in": 159543, "tokens_out": 5360, "ctx_chars": 182830, "t_end": 1791524237.8446648, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9973, "lo95": 0.996, "mean": 0.9967, "ev_only": 0.9965, "ref_ms": 29.87677, "cand_ms": 29.95819, "n_trials": 49, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0645, "r_wall_s": 155.38, "compile_s": 47.99, "r_error": "", "src_len": 5244, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78310, "tout": 2811, "ts": 1791524009.692177, "chk": "ok", "code_len": 5283}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81233, "tout": 2549, "ts": 1791524081.9238205, "chk": null, "code_len": 5244}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78310, "started": 1791523981.5884638}
{"ep": "ok-00285", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9994, "speedup": 0.9994, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 711.0, "calls": 4, "tokens_in": 29763, "tokens_out": 7343, "ctx_chars": 9192, "t_end": 1791524238.0003216, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9994, "lo95": 0.9966, "mean": 0.9976, "ev_only": 1.0014, "ref_ms": 7.98739, "cand_ms": 7.99256, "n_trials": 149, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 333.93, "compile_s": 7.3, "r_error": "", "src_len": 967, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5633, "tout": 2021, "ts": 1791523563.6155314, "chk": "incorrect", "code_len": 1626}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7024, "tout": 3443, "ts": 1791523754.154561, "chk": "incorrect", "code_len": 1040}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8099, "tout": 1333, "ts": 1791523775.54166, "chk": "ok", "code_len": 967}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9007, "tout": 546, "ts": 1791523903.9870856, "chk": null, "code_len": 967}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5633, "started": 1791523526.9749398}
{"ep": "ok-00368", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9942, "speedup": 0.9942, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 406.7, "calls": 3, "tokens_in": 26331, "tokens_out": 3064, "ctx_chars": 14186, "t_end": 1791524244.6624124, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9942, "lo95": 0.993, "mean": 0.9954, "ev_only": 0.9934, "ref_ms": 8.10668, "cand_ms": 8.15387, "n_trials": 141, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0173, "r_wall_s": 223.49, "compile_s": 2.16, "r_error": "", "src_len": 2883, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7602, "tout": 1605, "ts": 1791523852.147939, "chk": "ok", "code_len": 2883}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9319, "tout": 67, "ts": 1791523876.6171339, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9410, "tout": 1392, "ts": 1791523888.0267138, "chk": null, "code_len": 2883}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7602, "started": 1791523838.0034747}
{"ep": "ok-00430", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9349, "speedup": 0.9349, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 131.9, "calls": 2, "tokens_in": 16577, "tokens_out": 4061, "ctx_chars": 12352, "t_end": 1791524245.4396434, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9349, "lo95": 0.9344, "mean": 0.9363, "ev_only": 0.9366, "ref_ms": 29.79885, "cand_ms": 31.87468, "n_trials": 33, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.02, "r_wall_s": 84.95, "compile_s": 2.44, "r_error": "", "src_len": 2804, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7329, "tout": 2550, "ts": 1791524135.7257006, "chk": "ok", "code_len": 2804}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9248, "tout": 1511, "ts": 1791524159.9431179, "chk": null, "code_len": 2804}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7329, "started": 1791524113.5042877}
{"ep": "ok-00395", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 8.0806, "speedup": 8.0806, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 298.2, "calls": 3, "tokens_in": 17754, "tokens_out": 19796, "ctx_chars": 0, "t_end": 1791524247.187738, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 8.0806, "lo95": 8.0256, "mean": 9.2957, "ev_only": 8.159, "ref_ms": 32.44038, "cand_ms": 4.01458, "n_trials": 26, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 85.05, "compile_s": 19.18, "r_error": "", "src_len": 6132, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1951, "tout": 12273, "ts": 1791524061.3921819, "chk": "no_custom_kernel", "code_len": 6117}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6021, "tout": 4030, "ts": 1791524107.644224, "chk": "ok", "code_len": 6132}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9782, "tout": 3493, "ts": 1791524162.0694613, "chk": null, "code_len": 6132}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 1951, "started": 1791523949.0044615}
{"ep": "ok-00383", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9341, "speedup": 0.9341, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.4, "calls": 2, "tokens_in": 19367, "tokens_out": 5528, "ctx_chars": 15603, "t_end": 1791524247.909146, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9341, "lo95": 0.9325, "mean": 0.9315, "ev_only": 0.9349, "ref_ms": 29.6356, "cand_ms": 31.72496, "n_trials": 44, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0212, "r_wall_s": 52.9, "compile_s": 1.95, "r_error": "", "src_len": 3335, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8530, "tout": 3457, "ts": 1791523927.3945417, "chk": "ok", "code_len": 3335}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10837, "tout": 2071, "ts": 1791524194.4033525, "chk": null, "code_len": 3335}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 8530, "started": 1791523898.511783}
{"ep": "ok-00348", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0148, "speedup": 1.0148, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 485.9, "calls": 3, "tokens_in": 25329, "tokens_out": 2887, "ctx_chars": 12352, "t_end": 1791524261.5655403, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0148, "lo95": 1.0143, "mean": 1.0148, "ev_only": 1.0151, "ref_ms": 29.62294, "cand_ms": 29.19078, "n_trials": 53, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.038, "r_wall_s": 340.36, "compile_s": 23.54, "r_error": "", "src_len": 2607, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1514, "ts": 1791523789.5944886, "chk": "ok", "code_len": 2651}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8953, "tout": 72, "ts": 1791523909.5036707, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9049, "tout": 1301, "ts": 1791523920.4265726, "chk": null, "code_len": 2607}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7327, "started": 1791523775.6460876}
{"ep": "ok-00427", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.774, "speedup": 0.774, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 156.7, "calls": 3, "tokens_in": 10234, "tokens_out": 1697, "ctx_chars": 1993, "t_end": 1791524262.3922036, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.774, "lo95": 0.77, "mean": 0.8369, "ev_only": 0.7734, "ref_ms": 31.96572, "cand_ms": 41.29968, "n_trials": 26, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 53.64, "compile_s": 12.2, "r_error": "", "src_len": 1509, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2698, "tout": 922, "ts": 1791524115.5622046, "chk": "ok", "code_len": 1509}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3729, "tout": 54, "ts": 1791524202.3356938, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3807, "tout": 721, "ts": 1791524208.6408522, "chk": null, "code_len": 1509}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2698, "started": 1791524105.725776}
{"ep": "ok-00410", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.5475, "speedup": 1.5475, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 249.6, "calls": 2, "tokens_in": 6136, "tokens_out": 6498, "ctx_chars": 0, "t_end": 1791524263.3542323, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.5475, "lo95": 1.54, "mean": 1.5362, "ev_only": 1.5492, "ref_ms": 8.36321, "cand_ms": 5.40417, "n_trials": 160, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 160.31, "compile_s": 2.04, "r_error": "", "src_len": 3852, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 4334, "ts": 1791524052.6489215, "chk": "ok", "code_len": 3852}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4334, "tout": 2164, "ts": 1791524103.0101142, "chk": null, "code_len": 3852}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524013.7796946}
{"ep": "ok-00431", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0238, "speedup": 1.0238, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 158.3, "calls": 3, "tokens_in": 20884, "tokens_out": 1834, "ctx_chars": 10373, "t_end": 1791524272.6793528, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0238, "lo95": 1.0232, "mean": 1.0431, "ev_only": 1.0251, "ref_ms": 8.15161, "cand_ms": 7.96241, "n_trials": 149, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0065, "r_wall_s": 124.58, "compile_s": 2.43, "r_error": "", "src_len": 1844, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6268, "tout": 889, "ts": 1791524122.376731, "chk": "ok", "code_len": 1844}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7269, "tout": 54, "ts": 1791524140.2642026, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7347, "tout": 891, "ts": 1791524148.000348, "chk": null, "code_len": 1844}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6268, "started": 1791524114.4026637}
{"ep": "ok-00407", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.005, "speedup": 1.005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 274.9, "calls": 4, "tokens_in": 25583, "tokens_out": 8510, "ctx_chars": 5978, "t_end": 1791524273.8490672, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.005, "lo95": 1.0034, "mean": 1.0021, "ev_only": 1.0051, "ref_ms": 7.94478, "cand_ms": 7.9055, "n_trials": 158, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 127.09, "compile_s": 2.99, "r_error": "", "src_len": 932, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4158, "tout": 3430, "ts": 1791524029.8914585, "chk": "incorrect", "code_len": 2825}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6014, "tout": 2429, "ts": 1791524062.7782972, "chk": "incorrect", "code_len": 1059}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7197, "tout": 1793, "ts": 1791524097.6653285, "chk": "ok", "code_len": 932}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8214, "tout": 858, "ts": 1791524146.7158172, "chk": null, "code_len": 932}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 4158, "started": 1791523998.9599314}
{"ep": "ok-00423", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.5647, "speedup": 1.5647, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 191.1, "calls": 2, "tokens_in": 5973, "tokens_out": 5845, "ctx_chars": 0, "t_end": 1791524279.241839, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.5647, "lo95": 1.5639, "mean": 1.5648, "ev_only": 1.5675, "ref_ms": 8.15086, "cand_ms": 5.20928, "n_trials": 167, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 110.57, "compile_s": 16.33, "r_error": "", "src_len": 3681, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 3797, "ts": 1791524121.5134106, "chk": "ok", "code_len": 3705}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4248, "tout": 2048, "ts": 1791524168.5788565, "chk": null, "code_len": 3681}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791524088.1104784}
{"ep": "ok-00440", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0259, "speedup": 1.0259, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 141.5, "calls": 3, "tokens_in": 25316, "tokens_out": 2928, "ctx_chars": 12352, "t_end": 1791524281.2922394, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0259, "lo95": 1.0257, "mean": 1.026, "ev_only": 1.0254, "ref_ms": 29.75633, "cand_ms": 29.00496, "n_trials": 53, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0436, "r_wall_s": 71.24, "compile_s": 2.35, "r_error": "", "src_len": 2801, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1537, "ts": 1791524154.3421087, "chk": "ok", "code_len": 2801}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8976, "tout": 13, "ts": 1791524189.3050902, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9013, "tout": 1378, "ts": 1791524209.2517416, "chk": null, "code_len": 2801}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7327, "started": 1791524139.7705653}
{"ep": "ok-00433", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.6666, "speedup": 0.6666, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.3, "calls": 2, "tokens_in": 9722, "tokens_out": 11827, "ctx_chars": 495, "t_end": 1791524281.3407192, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6666, "lo95": 0.658, "mean": 0.6701, "ev_only": 0.6659, "ref_ms": 3.37196, "cand_ms": 5.05853, "n_trials": 185, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3376, "r_wall_s": 36.43, "compile_s": 2.53, "r_error": "", "src_len": 7031, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2761, "tout": 7714, "ts": 1791524205.7354772, "chk": "ok", "code_len": 7031}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6961, "tout": 4113, "ts": 1791524244.7995617, "chk": null, "code_len": 7031}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2761, "started": 1791524137.3985338}
{"ep": "ok-00447", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0365, "speedup": 1.0365, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 103.2, "calls": 2, "tokens_in": 4973, "tokens_out": 2946, "ctx_chars": 0, "t_end": 1791524284.0575485, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0365, "lo95": 1.036, "mean": 1.0359, "ev_only": 1.0365, "ref_ms": 8.2056, "cand_ms": 7.9169, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 42.89, "compile_s": 2.72, "r_error": "", "src_len": 1606, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 2070, "ts": 1791524219.9350703, "chk": "ok", "code_len": 1606}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3171, "tout": 876, "ts": 1791524241.0569375, "chk": null, "code_len": 1606}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524201.7364652}
{"ep": "ok-00445", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0069, "speedup": 1.0069, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 116.1, "calls": 2, "tokens_in": 17743, "tokens_out": 5944, "ctx_chars": 14186, "t_end": 1791524286.1394534, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0069, "lo95": 1.0053, "mean": 0.9383, "ev_only": 1.0024, "ref_ms": 8.20732, "cand_ms": 8.15117, "n_trials": 160, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0104, "r_wall_s": 58.18, "compile_s": 2.61, "r_error": "", "src_len": 3912, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7604, "tout": 3740, "ts": 1791524203.4130895, "chk": "ok", "code_len": 3912}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10139, "tout": 2204, "ts": 1791524227.7812576, "chk": null, "code_len": 3912}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7604, "started": 1791524169.991612}
{"ep": "ok-00452", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.097, "speedup": 1.097, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.9, "calls": 3, "tokens_in": 24159, "tokens_out": 2080, "ctx_chars": 12103, "t_end": 1791524290.4773078, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.097, "lo95": 1.0966, "mean": 1.0965, "ev_only": 1.0963, "ref_ms": 22.32541, "cand_ms": 20.35122, "n_trials": 73, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0403, "r_wall_s": 42.53, "compile_s": 3.46, "r_error": "", "src_len": 2087, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7259, "tout": 1054, "ts": 1791524219.5087895, "chk": "ok", "code_len": 2087}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8425, "tout": 26, "ts": 1791524238.7669766, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8475, "tout": 1000, "ts": 1791524247.3131354, "chk": null, "code_len": 2087}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7259, "started": 1791524209.5754666}
{"ep": "ok-00346", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 5.1426, "speedup": 5.1426, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 541.8, "calls": 3, "tokens_in": 19428, "tokens_out": 20425, "ctx_chars": 1495, "t_end": 1791524308.806184, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.1426, "lo95": 5.1339, "mean": 5.5516, "ev_only": 5.1521, "ref_ms": 31.83125, "cand_ms": 6.18972, "n_trials": 41, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 142.16, "compile_s": 26.25, "r_error": "", "src_len": 7343, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2464, "tout": 12073, "ts": 1791523880.1434286, "chk": "no_custom_kernel", "code_len": 7241}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6591, "tout": 4472, "ts": 1791523949.3194673, "chk": "ok", "code_len": 7343}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10373, "tout": 3880, "ts": 1791524166.592071, "chk": null, "code_len": 7343}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2464, "started": 1791523767.0089045}
{"ep": "ok-00374", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 6.3588, "speedup": 6.3588, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 452.0, "calls": 3, "tokens_in": 30786, "tokens_out": 38078, "ctx_chars": 2713, "t_end": 1791524314.9950042, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.3588, "lo95": 6.2999, "mean": 6.0171, "ev_only": 6.3756, "ref_ms": 4.1153, "cand_ms": 0.64718, "n_trials": 194, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9959, "r_wall_s": 47.05, "compile_s": 12.75, "r_error": "", "src_len": 13222, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3326, "tout": 24910, "ts": 1791524085.3835437, "chk": "no_custom_kernel", "code_len": 13592}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10457, "tout": 6884, "ts": 1791524149.0288239, "chk": "ok", "code_len": 13222}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 17003, "tout": 6284, "ts": 1791524267.6596873, "chk": null, "code_len": 13222}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 3326, "started": 1791523862.970822}
{"ep": "ok-00384", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 6.8203, "speedup": 6.8203, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 428.8, "calls": 3, "tokens_in": 21513, "tokens_out": 24873, "ctx_chars": 495, "t_end": 1791524327.8934875, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.8203, "lo95": 6.7596, "mean": 7.5907, "ev_only": 6.8933, "ref_ms": 31.64282, "cand_ms": 4.63947, "n_trials": 34, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 168.49, "compile_s": 17.08, "r_error": "", "src_len": 8351, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2084, "tout": 15137, "ts": 1791524031.278716, "chk": "no_custom_kernel", "code_len": 8375}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7298, "tout": 5176, "ts": 1791524099.2650595, "chk": "ok", "code_len": 8351}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12131, "tout": 4560, "ts": 1791524159.359015, "chk": null, "code_len": 8351}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2084, "started": 1791523899.120063}
{"ep": "ok-00432", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0179, "speedup": 1.0179, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.2, "calls": 3, "tokens_in": 25498, "tokens_out": 3003, "ctx_chars": 12352, "t_end": 1791524328.6160777, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0179, "lo95": 1.0176, "mean": 1.0177, "ev_only": 1.0173, "ref_ms": 29.64102, "cand_ms": 29.11931, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0341, "r_wall_s": 157.65, "compile_s": 15.18, "r_error": "", "src_len": 2730, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1628, "ts": 1791524131.802561, "chk": "ok", "code_len": 2730}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9067, "tout": 13, "ts": 1791524158.670083, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9104, "tout": 1362, "ts": 1791524170.4523306, "chk": null, "code_len": 2730}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7327, "started": 1791524115.4003222}
{"ep": "ok-00339", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.8832, "speedup": 0.8832, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 586.8, "calls": 5, "tokens_in": 54611, "tokens_out": 10028, "ctx_chars": 6513, "t_end": 1791524330.1214447, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8832, "lo95": 0.8801, "mean": 0.8829, "ev_only": 0.8832, "ref_ms": 16.22634, "cand_ms": 18.37318, "n_trials": 51, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0504, "r_wall_s": 164.11, "compile_s": 4.37, "r_error": "", "src_len": 3911, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 2775, "ts": 1791523786.487551, "chk": "incorrect", "code_len": 5758}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8528, "tout": 3309, "ts": 1791523977.8457396, "chk": "incorrect", "code_len": 6083}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11971, "tout": 2101, "ts": 1791524137.1366923, "chk": "ok", "code_len": 3911}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14181, "tout": 83, "ts": 1791524151.790702, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 14311, "tout": 1760, "ts": 1791524165.9583728, "chk": null, "code_len": 3911}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5620, "started": 1791523763.9794838}
{"ep": "ok-00415", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9336, "speedup": 0.9336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 289.1, "calls": 4, "tokens_in": 328830, "tokens_out": 9440, "ctx_chars": 182830, "t_end": 1791524336.6788251, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9336, "lo95": 0.9333, "mean": 0.9335, "ev_only": 0.9326, "ref_ms": 8.19219, "cand_ms": 8.77484, "n_trials": 141, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 52.9, "compile_s": 3.51, "r_error": "", "src_len": 3908, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78290, "tout": 2723, "ts": 1791524076.9830673, "chk": "incorrect", "code_len": 4075}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81145, "tout": 2168, "ts": 1791524108.2103934, "chk": "ok", "code_len": 3917}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 83425, "tout": 2433, "ts": 1791524239.053926, "chk": "ok", "code_len": 3908}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 85970, "tout": 2116, "ts": 1791524283.6953006, "chk": null, "code_len": 3908}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", null], "first_tin": 78290, "started": 1791524047.5436988}
{"ep": "ok-00429", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0277, "speedup": 1.0277, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 227.6, "calls": 3, "tokens_in": 17846, "tokens_out": 3549, "ctx_chars": 5518, "t_end": 1791524340.018803, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0277, "lo95": 1.0257, "mean": 1.0311, "ev_only": 1.0322, "ref_ms": 8.29432, "cand_ms": 8.0707, "n_trials": 80, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0028, "r_wall_s": 101.65, "compile_s": 3.77, "r_error": "", "src_len": 1680, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4076, "tout": 2666, "ts": 1791524137.204345, "chk": "ok", "code_len": 1680}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6854, "tout": 38, "ts": 1791524231.004276, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6916, "tout": 845, "ts": 1791524238.348067, "chk": null, "code_len": 1680}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4076, "started": 1791524112.4040956}
{"ep": "ok-00381", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0312, "speedup": 1.0312, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 453.6, "calls": 2, "tokens_in": 16320, "tokens_out": 2377, "ctx_chars": 13736, "t_end": 1791524340.0444915, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0312, "lo95": 1.0293, "mean": 1.0315, "ev_only": 1.0286, "ref_ms": 8.23034, "cand_ms": 7.98112, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0043, "r_wall_s": 74.61, "compile_s": 2.06, "r_error": "", "src_len": 1757, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7510, "tout": 1414, "ts": 1791523906.8974466, "chk": "ok", "code_len": 1757}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8810, "tout": 963, "ts": 1791524265.1858337, "chk": null, "code_len": 1757}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7510, "started": 1791523886.4074175}
{"ep": "ok-00377", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.8281, "speedup": 0.8281, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 466.8, "calls": 2, "tokens_in": 11375, "tokens_out": 20573, "ctx_chars": 0, "t_end": 1791524341.8231206, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8281, "lo95": 0.8273, "mean": 0.8326, "ev_only": 0.8239, "ref_ms": 3.34824, "cand_ms": 4.04312, "n_trials": 172, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9942, "r_wall_s": 67.95, "compile_s": 3.19, "r_error": "", "src_len": 10902, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 14982, "ts": 1791524005.1090589, "chk": "ok", "code_len": 11055}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8747, "tout": 5591, "ts": 1791524273.8430994, "chk": null, "code_len": 10902}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791523875.055359}
{"ep": "ok-00362", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.3085, "speedup": 0.3085, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 524.0, "calls": 3, "tokens_in": 23364, "tokens_out": 4215, "ctx_chars": 9125, "t_end": 1791524347.0745592, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.3085, "lo95": 0.3051, "mean": 0.2991, "ev_only": 0.3078, "ref_ms": 3.74489, "cand_ms": 12.13899, "n_trials": 90, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0753, "r_wall_s": 423.8, "compile_s": 23.91, "r_error": "", "src_len": 4154, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6279, "tout": 2116, "ts": 1791523840.435214, "chk": "ok", "code_len": 4154}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8507, "tout": 47, "ts": 1791523906.9075725, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8578, "tout": 2052, "ts": 1791523923.2211049, "chk": null, "code_len": 4154}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6279, "started": 1791523823.045024}
{"ep": "ok-00437", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0038, "speedup": 1.0038, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 220.7, "calls": 2, "tokens_in": 8870, "tokens_out": 5043, "ctx_chars": 3636, "t_end": 1791524347.1086748, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0038, "lo95": 1.0031, "mean": 1.0389, "ev_only": 1.0042, "ref_ms": 8.09949, "cand_ms": 8.06885, "n_trials": 135, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0078, "r_wall_s": 49.82, "compile_s": 6.89, "r_error": "", "src_len": 3610, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3285, "tout": 3312, "ts": 1791524154.827968, "chk": "ok", "code_len": 3610}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5585, "tout": 1731, "ts": 1791524296.9640415, "chk": null, "code_len": 3610}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3285, "started": 1791524126.4093711}
{"ep": "ok-00458", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0251, "speedup": 1.0251, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.2, "calls": 3, "tokens_in": 16831, "tokens_out": 1966, "ctx_chars": 7308, "t_end": 1791524352.2281296, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0251, "lo95": 1.0245, "mean": 1.0252, "ev_only": 1.0258, "ref_ms": 8.20912, "cand_ms": 8.00775, "n_trials": 127, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 70.42, "compile_s": 2.76, "r_error": "", "src_len": 1918, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4853, "tout": 982, "ts": 1791524238.969004, "chk": "ok", "code_len": 1918}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5947, "tout": 60, "ts": 1791524273.876298, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6031, "tout": 924, "ts": 1791524281.7107408, "chk": null, "code_len": 1918}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4853, "started": 1791524230.0280807}
{"ep": "ok-00438", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.819, "speedup": 0.819, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 223.5, "calls": 2, "tokens_in": 165726, "tokens_out": 10010, "ctx_chars": 182830, "t_end": 1791524358.4001613, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.819, "lo95": 0.8171, "mean": 0.8183, "ev_only": 0.8191, "ref_ms": 16.46003, "cand_ms": 20.09726, "n_trials": 80, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0014, "r_wall_s": 91.28, "compile_s": 61.64, "r_error": "", "src_len": 7292, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79484, "tout": 6649, "ts": 1791524189.3803566, "chk": "ok", "code_len": 7292}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 86242, "tout": 3361, "ts": 1791524267.0990295, "chk": null, "code_len": 7292}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79484, "started": 1791524134.8982337}
{"ep": "ok-00461", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0339, "speedup": 1.0339, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 124.7, "calls": 2, "tokens_in": 10287, "tokens_out": 2868, "ctx_chars": 6332, "t_end": 1791524362.701381, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0339, "lo95": 1.0327, "mean": 1.0677, "ev_only": 1.0354, "ref_ms": 8.35587, "cand_ms": 8.08164, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 33.77, "compile_s": 2.31, "r_error": "", "src_len": 1666, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4462, "tout": 2000, "ts": 1791524255.9517512, "chk": "ok", "code_len": 1666}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5825, "tout": 868, "ts": 1791524328.9090736, "chk": null, "code_len": 1666}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4462, "started": 1791524238.0010068}
{"ep": "ok-00451", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.1159, "speedup": 0.1159, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.7, "calls": 4, "tokens_in": 31644, "tokens_out": 4848, "ctx_chars": 8224, "t_end": 1791524362.8294306, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.1159, "lo95": 0.1109, "mean": 0.1218, "ev_only": 0.1158, "ref_ms": 33.48507, "cand_ms": 288.95597, "n_trials": 13, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2762, "r_wall_s": 94.86, "compile_s": 2.07, "r_error": "", "src_len": 2603, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 2016, "ts": 1791524221.6151788, "chk": "forbidden", "code_len": 2990}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7670, "tout": 1379, "ts": 1791524233.534576, "chk": "ok", "code_len": 2603}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9161, "tout": 135, "ts": 1791524252.9210706, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9320, "tout": 1318, "ts": 1791524267.9423199, "chk": null, "code_len": 2603}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 5493, "started": 1791524201.0818794}
{"ep": "ok-00321", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7416, "speedup": 0.7416, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 706.2, "calls": 5, "tokens_in": 56771, "tokens_out": 11015, "ctx_chars": 6513, "t_end": 1791524365.5584383, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7416, "lo95": 0.644, "mean": 0.6373, "ev_only": 0.7413, "ref_ms": 28.92527, "cand_ms": 39.00381, "n_trials": 43, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0604, "r_wall_s": 44.32, "compile_s": 3.16, "r_error": "", "src_len": 4545, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 3112, "ts": 1791523685.155132, "chk": "incorrect", "code_len": 6315}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8865, "tout": 3392, "ts": 1791523918.7726648, "chk": "incorrect", "code_len": 6607}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12391, "tout": 2377, "ts": 1791524282.0284045, "chk": "ok", "code_len": 4545}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14877, "tout": 94, "ts": 1791524305.0516105, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 15018, "tout": 2040, "ts": 1791524321.215406, "chk": null, "code_len": 4545}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5620, "started": 1791523659.374841}
{"ep": "ok-00385", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 11.3773, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 458.6, "calls": 3, "tokens_in": 20802, "tokens_out": 28069, "ctx_chars": 495, "t_end": 1791524367.7234979, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 11.3773, "lo95": 9.9124, "mean": 11.5723, "ev_only": 11.9134, "ref_ms": 48.50905, "cand_ms": 4.26368, "n_trials": 30, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9858, "r_wall_s": 56.46, "compile_s": 13.73, "r_error": "", "src_len": 8669, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2084, "tout": 18502, "ts": 1791524073.9478364, "chk": "no_custom_kernel", "code_len": 8673}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7036, "tout": 5195, "ts": 1791524129.724202, "chk": "ok", "code_len": 8669}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11682, "tout": 4372, "ts": 1791524311.23109, "chk": null, "code_len": 8669}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2084, "started": 1791523909.1451921}
{"ep": "ok-00428", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0281, "speedup": 1.0281, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.0, "calls": 2, "tokens_in": 159496, "tokens_out": 6882, "ctx_chars": 182830, "t_end": 1791524370.547017, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0281, "lo95": 1.0271, "mean": 1.0289, "ev_only": 1.0285, "ref_ms": 8.20647, "cand_ms": 7.98183, "n_trials": 180, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.005, "r_wall_s": 88.13, "compile_s": 56.82, "r_error": "", "src_len": 4716, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78292, "tout": 4216, "ts": 1791524147.9002304, "chk": "ok", "code_len": 4757}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81204, "tout": 2666, "ts": 1791524282.3176105, "chk": null, "code_len": 4716}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78292, "started": 1791524110.5743525}
{"ep": "ok-00332", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0067, "speedup": 1.0067, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 653.2, "calls": 4, "tokens_in": 19189, "tokens_out": 10603, "ctx_chars": 495, "t_end": 1791524371.476891, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0067, "lo95": 1.0062, "mean": 1.0068, "ev_only": 1.0038, "ref_ms": 7.99317, "cand_ms": 7.94022, "n_trials": 141, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0002, "r_wall_s": 124.32, "compile_s": 19.4, "r_error": "", "src_len": 1612, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1816, "tout": 3550, "ts": 1791523750.139832, "chk": "incorrect", "code_len": 3954}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4256, "tout": 3451, "ts": 1791523980.8282938, "chk": "incorrect", "code_len": 2337}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5853, "tout": 2408, "ts": 1791524163.7459354, "chk": "ok", "code_len": 1612}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7264, "tout": 1194, "ts": 1791524247.103403, "chk": null, "code_len": 1612}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 1816, "started": 1791523718.2437057}
{"ep": "ok-00434", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0026, "speedup": 1.0026, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 264.8, "calls": 2, "tokens_in": 159928, "tokens_out": 6538, "ctx_chars": 182830, "t_end": 1791524381.8542447, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0026, "lo95": 1.0023, "mean": 1.0303, "ev_only": 1.003, "ref_ms": 8.06675, "cand_ms": 8.04581, "n_trials": 139, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0122, "r_wall_s": 115.25, "compile_s": 62.38, "r_error": "", "src_len": 5677, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78172, "tout": 3474, "ts": 1791524149.9659433, "chk": "ok", "code_len": 6528}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81756, "tout": 3064, "ts": 1791524266.5268958, "chk": null, "code_len": 5677}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78172, "started": 1791524117.076641}
{"ep": "ok-00457", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0378, "speedup": 1.0378, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 164.4, "calls": 2, "tokens_in": 5014, "tokens_out": 3084, "ctx_chars": 0, "t_end": 1791524389.8791833, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0378, "lo95": 1.037, "mean": 1.0861, "ev_only": 1.0378, "ref_ms": 8.22577, "cand_ms": 7.92618, "n_trials": 165, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 29.88, "compile_s": 3.72, "r_error": "", "src_len": 1777, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 2081, "ts": 1791524244.4316328, "chk": "ok", "code_len": 1777}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3212, "tout": 1003, "ts": 1791524359.9631433, "chk": null, "code_len": 1777}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524225.470235}
{"ep": "ok-00439", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.1062, "speedup": 0.1062, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 257.5, "calls": 4, "tokens_in": 31284, "tokens_out": 4775, "ctx_chars": 8224, "t_end": 1791524393.5563345, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.1062, "lo95": 0.1053, "mean": 0.1048, "ev_only": 0.1061, "ref_ms": 31.60114, "cand_ms": 297.42922, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.291, "r_wall_s": 56.62, "compile_s": 2.69, "r_error": "", "src_len": 2559, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 1860, "ts": 1791524155.5098698, "chk": "forbidden", "code_len": 2904}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7514, "tout": 1357, "ts": 1791524167.262989, "chk": "ok", "code_len": 2603}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8983, "tout": 287, "ts": 1791524325.788828, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9294, "tout": 1271, "ts": 1791524336.9133105, "chk": null, "code_len": 2559}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 5493, "started": 1791524136.1021912}
{"ep": "ok-00367", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0259, "speedup": 1.0259, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 563.7, "calls": 2, "tokens_in": 10660, "tokens_out": 2080, "ctx_chars": 6811, "t_end": 1791524400.7737763, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0259, "lo95": 1.0252, "mean": 1.0595, "ev_only": 1.0276, "ref_ms": 8.1967, "cand_ms": 7.99005, "n_trials": 154, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 494.53, "compile_s": 9.52, "r_error": "", "src_len": 1756, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4724, "tout": 1100, "ts": 1791523849.8187704, "chk": "ok", "code_len": 1756}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5936, "tout": 980, "ts": 1791523906.1498656, "chk": null, "code_len": 1756}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4724, "started": 1791523837.0595725}
{"ep": "ok-00422", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.5972, "speedup": 0.5972, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 316.5, "calls": 2, "tokens_in": 10224, "tokens_out": 14204, "ctx_chars": 0, "t_end": 1791524401.2740018, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.5972, "lo95": 0.5386, "mean": 0.525, "ev_only": 0.5959, "ref_ms": 3.5629, "cand_ms": 5.96636, "n_trials": 166, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.4554, "r_wall_s": 105.07, "compile_s": 4.26, "r_error": "", "src_len": 8075, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 9764, "ts": 1791524166.244398, "chk": "ok", "code_len": 8075}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7596, "tout": 4440, "ts": 1791524296.1336253, "chk": null, "code_len": 8075}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791524084.7775471}
{"ep": "ok-00380", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.005, "speedup": 1.005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 520.4, "calls": 5, "tokens_in": 22510, "tokens_out": 3232, "ctx_chars": 3492, "t_end": 1791524403.7452302, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.005, "lo95": 1.0047, "mean": 1.0446, "ev_only": 1.0056, "ref_ms": 7.96818, "cand_ms": 7.92823, "n_trials": 138, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0029, "r_wall_s": 14.04, "compile_s": 1.93, "r_error": "", "src_len": 992, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3009, "tout": 510, "ts": 1791523889.163286, "chk": "incorrect", "code_len": 901}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3652, "tout": 664, "ts": 1791523927.8522434, "chk": "incorrect", "code_len": 918}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4449, "tout": 620, "ts": 1791524216.4870417, "chk": "incorrect", "code_len": 936}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 5202, "tout": 840, "ts": 1791524234.3895876, "chk": "incorrect", "code_len": 978}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 6198, "tout": 598, "ts": 1791524254.2418582, "chk": null, "code_len": 992}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 3009, "started": 1791523883.3924866}
{"ep": "ok-00459", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0261, "speedup": 1.0261, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.4, "calls": 3, "tokens_in": 24707, "tokens_out": 1893, "ctx_chars": 13736, "t_end": 1791524416.6950984, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0261, "lo95": 1.0237, "mean": 1.0433, "ev_only": 1.0276, "ref_ms": 8.26576, "cand_ms": 8.05541, "n_trials": 124, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 44.14, "compile_s": 2.14, "r_error": "", "src_len": 1866, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7508, "tout": 939, "ts": 1791524245.9462416, "chk": "ok", "code_len": 1866}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8559, "tout": 57, "ts": 1791524364.7867916, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8640, "tout": 897, "ts": 1791524372.3441577, "chk": null, "code_len": 1866}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7508, "started": 1791524237.2654617}
{"ep": "ok-00490", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0976, "speedup": 1.0976, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 57.5, "calls": 1, "tokens_in": 7684, "tokens_out": 1073, "ctx_chars": 12888, "t_end": 1791524420.189072, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0976, "lo95": 1.0968, "mean": 1.126, "ev_only": 1.0972, "ref_ms": 22.29999, "cand_ms": 20.31772, "n_trials": 71, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0327, "r_wall_s": 46.3, "compile_s": 3.09, "r_error": "", "src_len": 2116, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7684, "tout": 1073, "ts": 1791524373.5462284, "chk": null, "code_len": 2116}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7684, "started": 1791524362.7016494}
{"ep": "ok-00449", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.1136, "speedup": 0.1136, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 242.8, "calls": 3, "tokens_in": 26537, "tokens_out": 6649, "ctx_chars": 8141, "t_end": 1791524425.2617047, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.1136, "lo95": 0.112, "mean": 0.1104, "ev_only": 0.1134, "ref_ms": 32.22402, "cand_ms": 283.63989, "n_trials": 15, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2759, "r_wall_s": 39.63, "compile_s": 2.81, "r_error": "", "src_len": 3211, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5389, "tout": 5025, "ts": 1791524225.2184353, "chk": "ok", "code_len": 3211}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10526, "tout": 72, "ts": 1791524240.1460478, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10622, "tout": 1552, "ts": 1791524252.8306751, "chk": null, "code_len": 3211}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5389, "started": 1791524182.4641936}
{"ep": "ok-00328", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0207, "speedup": 1.0207, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 726.5, "calls": 2, "tokens_in": 5586, "tokens_out": 2829, "ctx_chars": 0, "t_end": 1791524427.5943773, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0207, "lo95": 1.0167, "mean": 1.023, "ev_only": 1.0303, "ref_ms": 8.28338, "cand_ms": 8.11503, "n_trials": 90, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0037, "r_wall_s": 520.46, "compile_s": 14.34, "r_error": "", "src_len": 1835, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1800, "tout": 1874, "ts": 1791523719.7657473, "chk": "ok", "code_len": 1835}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3786, "tout": 955, "ts": 1791523907.0857887, "chk": null, "code_len": 1835}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1800, "started": 1791523701.1248753}
{"ep": "ok-00379", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9837, "speedup": 0.9837, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 548.1, "calls": 2, "tokens_in": 158908, "tokens_out": 4365, "ctx_chars": 182830, "t_end": 1791524429.2979608, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9837, "lo95": 0.9834, "mean": 0.9839, "ev_only": 0.9841, "ref_ms": 29.69266, "cand_ms": 30.18462, "n_trials": 49, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.073, "r_wall_s": 136.96, "compile_s": 55.19, "r_error": "", "src_len": 4227, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78310, "tout": 2176, "ts": 1791523902.80978, "chk": "ok", "code_len": 4314}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 80598, "tout": 2189, "ts": 1791524291.809851, "chk": null, "code_len": 4227}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78310, "started": 1791523881.158956}
{"ep": "ok-00390", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.7077, "speedup": 0.7077, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 503.3, "calls": 3, "tokens_in": 17670, "tokens_out": 14973, "ctx_chars": 0, "t_end": 1791524432.7887444, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7077, "lo95": 0.7017, "mean": 0.6576, "ev_only": 0.7054, "ref_ms": 3.64319, "cand_ms": 5.14796, "n_trials": 182, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3253, "r_wall_s": 34.16, "compile_s": 2.6, "r_error": "", "src_len": 5995, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 6765, "ts": 1791524011.307469, "chk": "ok", "code_len": 5109}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5707, "tout": 5042, "ts": 1791524245.1064572, "chk": "ok", "code_len": 5995}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9335, "tout": 3166, "ts": 1791524398.596675, "chk": null, "code_len": 5995}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 2628, "started": 1791523949.7986486}
{"ep": "ok-00477", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.8239, "speedup": 0.8239, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 126.5, "calls": 2, "tokens_in": 10338, "tokens_out": 5038, "ctx_chars": 2425, "t_end": 1791524435.2951822, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8239, "lo95": 0.8164, "mean": 0.8197, "ev_only": 0.8243, "ref_ms": 4.14924, "cand_ms": 5.03624, "n_trials": 170, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.025, "r_wall_s": 39.25, "compile_s": 1.9, "r_error": "", "src_len": 2870, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 3682, "ts": 1791524363.171894, "chk": "ok", "code_len": 2870}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7066, "tout": 1356, "ts": 1791524396.0242043, "chk": null, "code_len": 2870}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3272, "started": 1791524329.1578708}
{"ep": "ok-00442", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0019, "speedup": 1.0019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 279.6, "calls": 5, "tokens_in": 37995, "tokens_out": 7454, "ctx_chars": 6127, "t_end": 1791524438.5223284, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0019, "lo95": 0.9999, "mean": 1.0091, "ev_only": 1.0019, "ref_ms": 8.01909, "cand_ms": 8.00399, "n_trials": 155, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 40.31, "compile_s": 2.18, "r_error": "", "src_len": 942, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4216, "tout": 1471, "ts": 1791524172.7130146, "chk": "incorrect", "code_len": 1193}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5820, "tout": 1853, "ts": 1791524250.7652621, "chk": "incorrect", "code_len": 1086}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7807, "tout": 1188, "ts": 1791524316.6277905, "chk": "incorrect", "code_len": 1122}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 9127, "tout": 1741, "ts": 1791524346.5405014, "chk": "incorrect", "code_len": 1014}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11025, "tout": 1201, "ts": 1791524398.1841187, "chk": null, "code_len": 942}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 4216, "started": 1791524158.9258704}
{"ep": "ok-00474", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.7933, "speedup": 0.7933, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 167.0, "calls": 2, "tokens_in": 6380, "tokens_out": 1636, "ctx_chars": 1993, "t_end": 1791524451.0633616, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7933, "lo95": 0.7912, "mean": 0.81, "ev_only": 0.7931, "ref_ms": 31.91432, "cand_ms": 40.23031, "n_trials": 18, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 75.68, "compile_s": 21.23, "r_error": "", "src_len": 1508, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2698, "tout": 875, "ts": 1791524293.052644, "chk": "ok", "code_len": 1508}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3682, "tout": 761, "ts": 1791524375.281346, "chk": null, "code_len": 1508}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2698, "started": 1791524284.0578952}
{"ep": "ok-00443", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9759, "speedup": 0.9759, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 294.3, "calls": 4, "tokens_in": 334377, "tokens_out": 13074, "ctx_chars": 182830, "t_end": 1791524456.804497, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9759, "lo95": 0.9746, "mean": 0.979, "ev_only": 0.9762, "ref_ms": 8.06032, "cand_ms": 8.25964, "n_trials": 150, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0359, "r_wall_s": 104.49, "compile_s": 2.18, "r_error": "", "src_len": 3992, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78172, "tout": 4050, "ts": 1791524201.814698, "chk": "incorrect", "code_len": 6244}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 82307, "tout": 2618, "ts": 1791524239.587685, "chk": "ok", "code_len": 4145}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 85037, "tout": 3689, "ts": 1791524309.1451983, "chk": "incorrect", "code_len": 5664}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 88861, "tout": 2717, "ts": 1791524352.2408798, "chk": null, "code_len": 3992}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "incorrect", null], "first_tin": 78172, "started": 1791524162.463386}
{"ep": "ok-00482", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0116, "speedup": 1.0116, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.0, "calls": 3, "tokens_in": 11646, "tokens_out": 6573, "ctx_chars": 768, "t_end": 1791524458.705415, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0116, "lo95": 1.0087, "mean": 1.0079, "ev_only": 1.0097, "ref_ms": 8.12702, "cand_ms": 8.03414, "n_trials": 126, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0066, "r_wall_s": 52.45, "compile_s": 2.14, "r_error": "", "src_len": 3249, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1908, "tout": 3266, "ts": 1791524365.7279565, "chk": "forbidden", "code_len": 3222}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3981, "tout": 1664, "ts": 1791524377.2804995, "chk": "ok", "code_len": 3249}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5757, "tout": 1643, "ts": 1791524406.1421843, "chk": null, "code_len": 3249}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", null], "first_tin": 1908, "started": 1791524336.6791391}
{"ep": "ok-00485", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9915, "speedup": 0.9915, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 131.8, "calls": 2, "tokens_in": 14179, "tokens_out": 2697, "ctx_chars": 10823, "t_end": 1791524473.6162226, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9915, "lo95": 0.9909, "mean": 0.9906, "ev_only": 0.9908, "ref_ms": 8.05328, "cand_ms": 8.12234, "n_trials": 140, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0165, "r_wall_s": 60.67, "compile_s": 1.94, "r_error": "", "src_len": 2812, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1343, "ts": 1791524353.060863, "chk": "ok", "code_len": 2785}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7817, "tout": 1354, "ts": 1791524412.876404, "chk": null, "code_len": 2812}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6362, "started": 1791524341.8234668}
{"ep": "ok-00467", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0349, "speedup": 1.0349, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.1, "calls": 2, "tokens_in": 6375, "tokens_out": 6252, "ctx_chars": 0, "t_end": 1791524477.4725556, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0349, "lo95": 1.0338, "mean": 1.0346, "ev_only": 1.0346, "ref_ms": 29.81993, "cand_ms": 28.81551, "n_trials": 40, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0193, "r_wall_s": 100.56, "compile_s": 21.3, "r_error": "", "src_len": 4759, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1745, "tout": 3879, "ts": 1791524294.6067011, "chk": "ok", "code_len": 4759}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4630, "tout": 2373, "ts": 1791524376.2354758, "chk": null, "code_len": 4759}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1745, "started": 1791524262.3924515}
{"ep": "ok-00498", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 99.5, "calls": 1, "tokens_in": 2759, "tokens_out": 2883, "ctx_chars": 495, "t_end": 1791524493.0645351, "error": "RuntimeError: Error building extension 'fold_bn_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fold_bn_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "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": 73.38, "compile_s": 73.23, "r_error": "RuntimeError: Error building extension 'fold_bn_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fold_bn_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "src_len": 5265, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2759, "tout": 2883, "ts": 1791524419.6180239, "chk": null, "code_len": 5265}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2759, "started": 1791524393.556602}
{"ep": "ok-00466", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.1104, "speedup": 0.1104, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 239.1, "calls": 3, "tokens_in": 22900, "tokens_out": 4541, "ctx_chars": 8141, "t_end": 1791524500.6837835, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.1104, "lo95": 0.092, "mean": 0.1151, "ev_only": 0.1104, "ref_ms": 32.05943, "cand_ms": 290.4697, "n_trials": 11, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2741, "r_wall_s": 93.32, "compile_s": 2.46, "r_error": "", "src_len": 2455, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5389, "tout": 3190, "ts": 1791524291.1142564, "chk": "ok", "code_len": 2455}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8691, "tout": 105, "ts": 1791524397.113955, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8820, "tout": 1246, "ts": 1791524407.3397489, "chk": null, "code_len": 2455}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5389, "started": 1791524261.5659506}
{"ep": "ok-00413", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.7969, "speedup": 0.7969, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 468.5, "calls": 4, "tokens_in": 338605, "tokens_out": 13623, "ctx_chars": 182830, "t_end": 1791524505.6208339, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7969, "lo95": 0.7869, "mean": 0.8302, "ev_only": 0.7965, "ref_ms": 16.49427, "cand_ms": 20.69868, "n_trials": 19, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.052, "r_wall_s": 119.02, "compile_s": 61.93, "r_error": "", "src_len": 7585, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79484, "tout": 3420, "ts": 1791524068.4951313, "chk": "forbidden", "code_len": 6802}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 83006, "tout": 3070, "ts": 1791524103.7367125, "chk": "no_custom_kernel", "code_len": 6805}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 86208, "tout": 3590, "ts": 1791524249.58706, "chk": "ok", "code_len": 7585}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 89907, "tout": 3543, "ts": 1791524386.5576828, "chk": null, "code_len": 7585}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "no_custom_kernel", "ok", null], "first_tin": 79484, "started": 1791524037.1394358}
{"ep": "ok-00472", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.1006, "speedup": 1.1006, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 225.0, "calls": 3, "tokens_in": 29118, "tokens_out": 2209, "ctx_chars": 16078, "t_end": 1791524506.2581995, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1006, "lo95": 1.1002, "mean": 1.1005, "ev_only": 1.1006, "ref_ms": 22.25525, "cand_ms": 20.22076, "n_trials": 65, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0347, "r_wall_s": 172.6, "compile_s": 2.78, "r_error": "", "src_len": 2209, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8863, "tout": 1134, "ts": 1791524292.415123, "chk": "ok", "code_len": 2282}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10109, "tout": 13, "ts": 1791524324.6758487, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10146, "tout": 1062, "ts": 1791524333.4321656, "chk": null, "code_len": 2209}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 8863, "started": 1791524281.2929192}
{"ep": "ok-00506", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 85.5, "calls": 1, "tokens_in": 1876, "tokens_out": 1811, "ctx_chars": 495, "t_end": 1791524514.821651, "error": "RuntimeError: Error building extension 'relu_gn_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_ext -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": 68.56, "compile_s": 68.55, "r_error": "RuntimeError: Error building extension 'relu_gn_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "src_len": 3754, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1876, "tout": 1811, "ts": 1791524446.2235243, "chk": null, "code_len": 3754}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1876, "started": 1791524429.2985814}
{"ep": "ok-00510", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0348, "speedup": 1.0348, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 68.7, "calls": 2, "tokens_in": 4899, "tokens_out": 2991, "ctx_chars": 0, "t_end": 1791524519.759083, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0348, "lo95": 1.0343, "mean": 1.035, "ev_only": 1.0369, "ref_ms": 8.21765, "cand_ms": 7.9415, "n_trials": 166, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.003, "r_wall_s": 25.62, "compile_s": 1.85, "r_error": "", "src_len": 1552, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 2127, "ts": 1791524470.7196534, "chk": "ok", "code_len": 1609}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3097, "tout": 864, "ts": 1791524494.0357032, "chk": null, "code_len": 1552}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524451.0636144}
{"ep": "ok-00454", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0135, "speedup": 1.0135, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 301.9, "calls": 2, "tokens_in": 5378, "tokens_out": 4979, "ctx_chars": 0, "t_end": 1791524520.96228, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0135, "lo95": 1.0095, "mean": 1.0143, "ev_only": 1.0149, "ref_ms": 8.16543, "cand_ms": 8.05681, "n_trials": 171, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0072, "r_wall_s": 69.69, "compile_s": 2.4, "r_error": "", "src_len": 3130, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1607, "tout": 3422, "ts": 1791524248.1740832, "chk": "ok", "code_len": 3130}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3771, "tout": 1557, "ts": 1791524315.6239197, "chk": null, "code_len": 3130}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1607, "started": 1791524219.0347426}
{"ep": "ok-00456", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 33.2881, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 297.5, "calls": 2, "tokens_in": 7450, "tokens_out": 5506, "ctx_chars": 2256, "t_end": 1791524522.7273517, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 33.2881, "lo95": 33.0809, "mean": 31.9988, "ev_only": 33.3608, "ref_ms": 22.31422, "cand_ms": 0.67034, "n_trials": 73, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 190.74, "compile_s": 2.78, "r_error": "", "src_len": 2938, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2666, "tout": 4057, "ts": 1791524261.5032208, "chk": "ok", "code_len": 2938}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4784, "tout": 1449, "ts": 1791524331.68582, "chk": null, "code_len": 2938}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2666, "started": 1791524225.233025}
{"ep": "ok-00491", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9845, "speedup": 0.9845, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.5, "calls": 3, "tokens_in": 22307, "tokens_out": 2903, "ctx_chars": 10823, "t_end": 1791524524.2816236, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9845, "lo95": 0.9821, "mean": 0.9896, "ev_only": 0.9873, "ref_ms": 8.10813, "cand_ms": 8.23547, "n_trials": 147, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0172, "r_wall_s": 118.78, "compile_s": 2.27, "r_error": "", "src_len": 2884, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1462, "ts": 1791524375.0768628, "chk": "ok", "code_len": 2884}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7936, "tout": 49, "ts": 1791524393.8604395, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8009, "tout": 1392, "ts": 1791524405.3681493, "chk": null, "code_len": 2884}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791524362.8297086}
{"ep": "ok-00484", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.2967, "speedup": 0.2967, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.6, "calls": 3, "tokens_in": 20451, "tokens_out": 4133, "ctx_chars": 6513, "t_end": 1791524528.6196249, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.2967, "lo95": 0.2934, "mean": 0.3076, "ev_only": 0.295, "ref_ms": 3.60402, "cand_ms": 12.14708, "n_trials": 68, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0757, "r_wall_s": 43.35, "compile_s": 4.28, "r_error": "", "src_len": 4030, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5329, "tout": 2089, "ts": 1791524357.6316867, "chk": "ok", "code_len": 4089}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7530, "tout": 38, "ts": 1791524469.0541553, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7592, "tout": 2006, "ts": 1791524485.2259457, "chk": null, "code_len": 4030}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5329, "started": 1791524340.0447464}
{"ep": "ok-00486", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0099, "speedup": 1.0099, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 188.6, "calls": 3, "tokens_in": 21824, "tokens_out": 2303, "ctx_chars": 10373, "t_end": 1791524535.655811, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0099, "lo95": 1.0081, "mean": 1.0141, "ev_only": 1.0173, "ref_ms": 8.22057, "cand_ms": 8.13965, "n_trials": 59, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 57.71, "compile_s": 4.35, "r_error": "", "src_len": 1848, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6268, "tout": 1357, "ts": 1791524358.6992555, "chk": "ok", "code_len": 2628}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7737, "tout": 58, "ts": 1791524470.4073265, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7819, "tout": 888, "ts": 1791524477.854201, "chk": null, "code_len": 1848}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6268, "started": 1791524347.0748587}
{"ep": "ok-00421", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 6.1079, "speedup": 6.1079, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 468.7, "calls": 3, "tokens_in": 29718, "tokens_out": 30339, "ctx_chars": 2425, "t_end": 1791524537.3205104, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 6.1079, "lo95": 6.0758, "mean": 5.8161, "ev_only": 6.191, "ref_ms": 4.11163, "cand_ms": 0.67317, "n_trials": 219, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 93.39, "compile_s": 16.79, "r_error": "", "src_len": 11165, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 17647, "ts": 1791524231.0930252, "chk": "no_custom_kernel", "code_len": 11313}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10084, "tout": 6760, "ts": 1791524334.0577843, "chk": "ok", "code_len": 11201}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16360, "tout": 5932, "ts": 1791524443.9042804, "chk": null, "code_len": 11165}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 3274, "started": 1791524068.6263657}
{"ep": "ok-00424", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 7.1413, "speedup": 7.1413, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 449.1, "calls": 3, "tokens_in": 27935, "tokens_out": 21240, "ctx_chars": 7644, "t_end": 1791524538.8164456, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.1413, "lo95": 7.0643, "mean": 8.3252, "ev_only": 7.1804, "ref_ms": 32.30129, "cand_ms": 4.5232, "n_trials": 41, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9811, "r_wall_s": 110.9, "compile_s": 20.06, "r_error": "", "src_len": 7063, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5260, "tout": 13077, "ts": 1791524206.1951232, "chk": "no_custom_kernel", "code_len": 7068}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9414, "tout": 4266, "ts": 1791524252.7593436, "chk": "ok", "code_len": 7063}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13261, "tout": 3897, "ts": 1791524427.8647153, "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": 5260, "started": 1791524089.7029037}
{"ep": "ok-00418", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 5.5373, "speedup": 5.5373, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 487.1, "calls": 2, "tokens_in": 10617, "tokens_out": 20400, "ctx_chars": 0, "t_end": 1791524543.7198427, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 5.5373, "lo95": 5.5195, "mean": 5.2449, "ev_only": 5.5337, "ref_ms": 4.0403, "cand_ms": 0.72965, "n_trials": 229, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 230.48, "compile_s": 53.65, "r_error": "", "src_len": 10495, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 15076, "ts": 1791524208.186378, "chk": "ok", "code_len": 10495}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8259, "tout": 5324, "ts": 1791524313.2178898, "chk": null, "code_len": 10495}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2358, "started": 1791524076.9600492}
{"ep": "ok-00479", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0141, "speedup": 1.0141, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 216.4, "calls": 2, "tokens_in": 5784, "tokens_out": 5955, "ctx_chars": 0, "t_end": 1791524544.3266752, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0141, "lo95": 1.0136, "mean": 1.0147, "ev_only": 1.0152, "ref_ms": 8.06041, "cand_ms": 7.94798, "n_trials": 152, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0059, "r_wall_s": 110.46, "compile_s": 2.52, "r_error": "", "src_len": 4025, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1607, "tout": 3964, "ts": 1791524362.1423452, "chk": "ok", "code_len": 4167}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4177, "tout": 1991, "ts": 1791524433.7848558, "chk": null, "code_len": 4025}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1607, "started": 1791524327.8938324}
{"ep": "ok-00480", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0268, "speedup": 1.0268, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.2, "calls": 2, "tokens_in": 11664, "tokens_out": 4238, "ctx_chars": 7221, "t_end": 1791524545.8087192, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0268, "lo95": 1.0257, "mean": 1.0063, "ev_only": 1.0276, "ref_ms": 29.67787, "cand_ms": 28.90399, "n_trials": 43, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0261, "r_wall_s": 128.08, "compile_s": 13.69, "r_error": "", "src_len": 2769, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4831, "tout": 2729, "ts": 1791524352.142402, "chk": "ok", "code_len": 2769}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6833, "tout": 1509, "ts": 1791524417.0788722, "chk": null, "code_len": 2769}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4831, "started": 1791524328.6164289}
{"ep": "ok-00476", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.344, "speedup": 1.344, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 259.6, "calls": 2, "tokens_in": 160235, "tokens_out": 11846, "ctx_chars": 182830, "t_end": 1791524550.1190171, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.344, "lo95": 1.3432, "mean": 1.3431, "ev_only": 1.344, "ref_ms": 8.02717, "cand_ms": 5.97266, "n_trials": 144, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.865, "r_wall_s": 37.82, "compile_s": 2.71, "r_error": "", "src_len": 6243, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78174, "tout": 7622, "ts": 1791524357.796896, "chk": "ok", "code_len": 6243}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82061, "tout": 4224, "ts": 1791524512.1038973, "chk": null, "code_len": 6243}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78174, "started": 1791524290.477613}
{"ep": "ok-00489", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9335, "speedup": 0.9335, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 200.3, "calls": 2, "tokens_in": 16891, "tokens_out": 4865, "ctx_chars": 12352, "t_end": 1791524558.6579142, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9335, "lo95": 0.9328, "mean": 0.9321, "ev_only": 0.9337, "ref_ms": 29.59828, "cand_ms": 31.70825, "n_trials": 47, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0275, "r_wall_s": 110.39, "compile_s": 3.3, "r_error": "", "src_len": 3166, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7329, "tout": 3161, "ts": 1791524388.2064555, "chk": "ok", "code_len": 3166}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9562, "tout": 1704, "ts": 1791524447.4361906, "chk": null, "code_len": 3166}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7329, "started": 1791524358.400538}
{"ep": "ok-00513", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0304, "speedup": 1.0304, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 85.2, "calls": 1, "tokens_in": 1933, "tokens_out": 3243, "ctx_chars": 495, "t_end": 1791524558.828515, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0304, "lo95": 1.029, "mean": 1.0343, "ev_only": 1.0326, "ref_ms": 8.36393, "cand_ms": 8.11702, "n_trials": 74, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0023, "r_wall_s": 55.26, "compile_s": 1.96, "r_error": "", "src_len": 1597, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1933, "tout": 3243, "ts": 1791524503.4595854, "chk": null, "code_len": 1597}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1933, "started": 1791524473.6165037}
{"ep": "ok-00460", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9127, "speedup": 0.9127, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 322.7, "calls": 3, "tokens_in": 18089, "tokens_out": 5980, "ctx_chars": 2169, "t_end": 1791524560.530347, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9127, "lo95": 0.9109, "mean": 0.8977, "ev_only": 0.9196, "ref_ms": 4.04544, "cand_ms": 4.43249, "n_trials": 204, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0271, "r_wall_s": 198.31, "compile_s": 51.81, "r_error": "", "src_len": 3526, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3083, "tout": 4275, "ts": 1791524276.8742635, "chk": "ok", "code_len": 3526}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7470, "tout": 42, "ts": 1791524348.003357, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7536, "tout": 1663, "ts": 1791524362.1749835, "chk": null, "code_len": 3526}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3083, "started": 1791524237.8449843}
{"ep": "ok-00478", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "forbidden", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 245.6, "calls": 4, "tokens_in": 34565, "tokens_out": 4260, "ctx_chars": 12555, "t_end": 1791524560.6184626, "error": "static check failed: no class ModelNew defined", "f_status": "forbidden", "f_error": "", "submit_turn": 3, "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": 0.0, "compile_s": null, "r_error": "static check failed: no class ModelNew defined", "src_len": 437, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6871, "tout": 660, "ts": 1791524321.8065906, "chk": "incorrect", "code_len": 1109}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7664, "tout": 1723, "ts": 1791524352.3198526, "chk": "incorrect", "code_len": 990}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 9520, "tout": 881, "ts": 1791524390.2150702, "chk": "ok", "code_len": 942}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10510, "tout": 996, "ts": 1791524560.5744784, "chk": null, "code_len": 437}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 6871, "started": 1791524314.9955063}
{"ep": "ok-00464", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7776, "speedup": 0.7776, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 314.9, "calls": 4, "tokens_in": 35524, "tokens_out": 6531, "ctx_chars": 7010, "t_end": 1791524562.1080506, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.7776, "lo95": 0.7697, "mean": 0.7911, "ev_only": 0.778, "ref_ms": 17.1701, "cand_ms": 22.08202, "n_trials": 39, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0537, "r_wall_s": 220.64, "compile_s": 2.71, "r_error": "", "src_len": 4130, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5751, "tout": 2520, "ts": 1791524269.028112, "chk": "incorrect", "code_len": 5220}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8404, "tout": 2128, "ts": 1791524313.4636602, "chk": "ok", "code_len": 4130}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10641, "tout": 63, "ts": 1791524326.6097329, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 10728, "tout": 1820, "ts": 1791524341.4426064, "chk": null, "code_len": 4130}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 5751, "started": 1791524247.1880867}
{"ep": "ok-00465", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.9937, "speedup": 0.9937, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 314.3, "calls": 5, "tokens_in": 25406, "tokens_out": 4462, "ctx_chars": 3492, "t_end": 1791524562.2338355, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9937, "lo95": 0.9922, "mean": 0.9785, "ev_only": 0.9961, "ref_ms": 8.01015, "cand_ms": 8.06101, "n_trials": 140, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 46.11, "compile_s": 2.17, "r_error": "", "src_len": 927, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3009, "tout": 847, "ts": 1791524257.738848, "chk": "incorrect", "code_len": 1072}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3989, "tout": 743, "ts": 1791524299.3221838, "chk": "incorrect", "code_len": 1117}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4865, "tout": 1285, "ts": 1791524384.4400353, "chk": "incorrect", "code_len": 1014}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 6284, "tout": 818, "ts": 1791524410.9252374, "chk": "incorrect", "code_len": 891}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7259, "tout": 769, "ts": 1791524516.0104072, "chk": null, "code_len": 927}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 3009, "started": 1791524247.9095027}
{"ep": "ok-00481", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7558, "speedup": 0.7558, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 252.4, "calls": 3, "tokens_in": 15555, "tokens_out": 4433, "ctx_chars": 2425, "t_end": 1791524582.4837403, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7558, "lo95": 0.7543, "mean": 0.742, "ev_only": 0.7554, "ref_ms": 4.034, "cand_ms": 5.33737, "n_trials": 184, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0678, "r_wall_s": 14.92, "compile_s": 1.95, "r_error": "", "src_len": 3511, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 2727, "ts": 1791524357.3402073, "chk": "ok", "code_len": 3563}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6111, "tout": 37, "ts": 1791524551.912066, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6172, "tout": 1669, "ts": 1791524567.515091, "chk": null, "code_len": 3511}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3272, "started": 1791524330.1217701}
{"ep": "ok-00509", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.2992, "speedup": 0.2992, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.3, "calls": 3, "tokens_in": 20446, "tokens_out": 4161, "ctx_chars": 6513, "t_end": 1791524582.8298197, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.2992, "lo95": 0.2974, "mean": 0.3172, "ev_only": 0.2992, "ref_ms": 3.44062, "cand_ms": 11.49752, "n_trials": 145, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0786, "r_wall_s": 100.56, "compile_s": 6.5, "r_error": "", "src_len": 4156, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5329, "tout": 2099, "ts": 1791524455.6957965, "chk": "ok", "code_len": 4156}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7540, "tout": 13, "ts": 1791524465.5391881, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7577, "tout": 2049, "ts": 1791524482.2175205, "chk": null, "code_len": 4156}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5329, "started": 1791524438.5226395}
{"ep": "ok-00444", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.533, "speedup": 1.533, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 420.2, "calls": 2, "tokens_in": 160333, "tokens_out": 13690, "ctx_chars": 182830, "t_end": 1791524587.9988015, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.533, "lo95": 1.5245, "mean": 1.5187, "ev_only": 1.5304, "ref_ms": 8.07536, "cand_ms": 5.2676, "n_trials": 174, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9769, "r_wall_s": 170.57, "compile_s": 2.6, "r_error": "", "src_len": 6349, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78174, "tout": 9761, "ts": 1791524256.67979, "chk": "ok", "code_len": 6349}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82159, "tout": 3929, "ts": 1791524417.351809, "chk": null, "code_len": 6349}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78174, "started": 1791524167.7838473}
{"ep": "ok-00507", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0111, "speedup": 1.0111, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.2, "calls": 3, "tokens_in": 20282, "tokens_out": 2863, "ctx_chars": 9128, "t_end": 1791524593.9732797, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0111, "lo95": 1.0098, "mean": 1.0118, "ev_only": 1.0118, "ref_ms": 29.80706, "cand_ms": 29.47987, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0436, "r_wall_s": 88.37, "compile_s": 1.9, "r_error": "", "src_len": 2720, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5681, "tout": 1489, "ts": 1791524466.6439443, "chk": "ok", "code_len": 2720}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7282, "tout": 13, "ts": 1791524493.4670625, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7319, "tout": 1361, "ts": 1791524504.6500268, "chk": null, "code_len": 2720}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5681, "started": 1791524453.2042465}
{"ep": "ok-00492", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.8735, "speedup": 0.8735, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 241.4, "calls": 5, "tokens_in": 56556, "tokens_out": 10601, "ctx_chars": 6513, "t_end": 1791524606.976268, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8735, "lo95": 0.8668, "mean": 0.9292, "ev_only": 0.8736, "ref_ms": 16.61545, "cand_ms": 19.02272, "n_trials": 28, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0355, "r_wall_s": 81.45, "compile_s": 2.36, "r_error": "", "src_len": 4068, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 3156, "ts": 1791524391.3995323, "chk": "incorrect", "code_len": 6338}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8909, "tout": 3370, "ts": 1791524427.8513603, "chk": "incorrect", "code_len": 6530}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12413, "tout": 2229, "ts": 1791524500.8421726, "chk": "ok", "code_len": 4068}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14751, "tout": 65, "ts": 1791524510.9576738, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 14863, "tout": 1781, "ts": 1791524525.4109044, "chk": null, "code_len": 4068}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5620, "started": 1791524365.5588055}
{"ep": "ok-00520", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0263, "speedup": 1.0263, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 100.8, "calls": 3, "tokens_in": 12690, "tokens_out": 1909, "ctx_chars": 4565, "t_end": 1791524620.5425317, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0263, "lo95": 1.0256, "mean": 1.0325, "ev_only": 1.0247, "ref_ms": 8.15472, "cand_ms": 7.94554, "n_trials": 147, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0062, "r_wall_s": 20.28, "compile_s": 2.69, "r_error": "", "src_len": 1882, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3499, "tout": 966, "ts": 1791524528.9969535, "chk": "ok", "code_len": 1882}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4577, "tout": 13, "ts": 1791524592.503069, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4614, "tout": 930, "ts": 1791524600.1652834, "chk": null, "code_len": 1882}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3499, "started": 1791524519.7593634}
{"ep": "ok-00516", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 44.5395, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 123.5, "calls": 2, "tokens_in": 7408, "tokens_out": 6748, "ctx_chars": 2016, "t_end": 1791524624.1623, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 44.5395, "lo95": 44.1703, "mean": 43.6029, "ev_only": 45.8267, "ref_ms": 22.28099, "cand_ms": 0.50025, "n_trials": 67, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 28.21, "compile_s": 2.74, "r_error": "", "src_len": 3183, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2574, "tout": 5138, "ts": 1791524547.8916712, "chk": "ok", "code_len": 3240}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4834, "tout": 1610, "ts": 1791524595.7696366, "chk": null, "code_len": 3183}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2574, "started": 1791524500.6840794}
{"ep": "ok-00525", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9978, "speedup": 0.9978, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 89.0, "calls": 3, "tokens_in": 22404, "tokens_out": 2949, "ctx_chars": 10823, "t_end": 1791524624.6373408, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9978, "lo95": 0.997, "mean": 0.9965, "ev_only": 0.9972, "ref_ms": 8.05501, "cand_ms": 8.07293, "n_trials": 141, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0175, "r_wall_s": 32.7, "compile_s": 2.4, "r_error": "", "src_len": 2884, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1513, "ts": 1791524549.0074508, "chk": "ok", "code_len": 2884}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7987, "tout": 44, "ts": 1791524580.438737, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8055, "tout": 1392, "ts": 1791524591.8372047, "chk": null, "code_len": 2884}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791524535.6561213}
{"ep": "ok-00495", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9357, "speedup": 0.9357, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 256.8, "calls": 2, "tokens_in": 19083, "tokens_out": 4905, "ctx_chars": 15603, "t_end": 1791524628.321658, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9357, "lo95": 0.935, "mean": 0.9352, "ev_only": 0.9356, "ref_ms": 29.64753, "cand_ms": 31.68389, "n_trials": 33, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0193, "r_wall_s": 100.99, "compile_s": 2.1, "r_error": "", "src_len": 3067, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8530, "tout": 3130, "ts": 1791524398.9658434, "chk": "ok", "code_len": 3067}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10553, "tout": 1775, "ts": 1791524526.7350957, "chk": null, "code_len": 3067}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 8530, "started": 1791524371.4774048}
{"ep": "ok-00535", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0238, "speedup": 1.0238, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 69.0, "calls": 3, "tokens_in": 20118, "tokens_out": 1898, "ctx_chars": 9950, "t_end": 1791524629.5955088, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0238, "lo95": 1.0221, "mean": 1.023, "ev_only": 1.0235, "ref_ms": 8.23323, "cand_ms": 8.04202, "n_trials": 187, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0065, "r_wall_s": 43.01, "compile_s": 1.98, "r_error": "", "src_len": 1848, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5980, "tout": 927, "ts": 1791524569.0245476, "chk": "ok", "code_len": 1848}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7019, "tout": 76, "ts": 1791524579.1419685, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7119, "tout": 895, "ts": 1791524586.493093, "chk": null, "code_len": 1848}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5980, "started": 1791524560.6187744}
{"ep": "ok-00531", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0966, "speedup": 1.0966, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.4, "calls": 2, "tokens_in": 18975, "tokens_out": 2150, "ctx_chars": 16078, "t_end": 1791524630.5538676, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0966, "lo95": 1.0955, "mean": 1.0962, "ev_only": 1.0958, "ref_ms": 22.35329, "cand_ms": 20.38325, "n_trials": 65, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0402, "r_wall_s": 42.2, "compile_s": 2.09, "r_error": "", "src_len": 2111, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8863, "tout": 1137, "ts": 1791524570.0545692, "chk": "ok", "code_len": 2111}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10112, "tout": 1013, "ts": 1791524588.1520152, "chk": null, "code_len": 2111}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 8863, "started": 1791524550.1193662}
{"ep": "ok-00511", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.2607, "speedup": 1.2607, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 176.6, "calls": 2, "tokens_in": 159371, "tokens_out": 7796, "ctx_chars": 182830, "t_end": 1791524633.4409292, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.2607, "lo95": 1.2602, "mean": 1.2599, "ev_only": 1.26, "ref_ms": 8.14819, "cand_ms": 6.46344, "n_trials": 153, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 96.2, "compile_s": 3.2, "r_error": "", "src_len": 4312, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78292, "tout": 5108, "ts": 1791524502.3203616, "chk": "ok", "code_len": 4312}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81079, "tout": 2688, "ts": 1791524537.0868685, "chk": null, "code_len": 4312}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78292, "started": 1791524456.8048027}
{"ep": "ok-00497", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8712, "speedup": 0.8712, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 244.3, "calls": 2, "tokens_in": 160144, "tokens_out": 4280, "ctx_chars": 182830, "t_end": 1791524634.1588001, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8712, "lo95": 0.8689, "mean": 0.8557, "ev_only": 0.8714, "ref_ms": 4.00919, "cand_ms": 4.60212, "n_trials": 198, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0338, "r_wall_s": 77.66, "compile_s": 61.3, "r_error": "", "src_len": 2954, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78923, "tout": 2186, "ts": 1791524414.5734954, "chk": "ok", "code_len": 2954}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81221, "tout": 2094, "ts": 1791524556.393679, "chk": null, "code_len": 2954}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78923, "started": 1791524389.8794508}
{"ep": "ok-00494", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.7566, "speedup": 0.7566, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 266.5, "calls": 3, "tokens_in": 14881, "tokens_out": 4503, "ctx_chars": 1884, "t_end": 1791524636.99964, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7566, "lo95": 0.7552, "mean": 0.7503, "ev_only": 0.7578, "ref_ms": 3.93252, "cand_ms": 5.19742, "n_trials": 188, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0715, "r_wall_s": 84.36, "compile_s": 2.94, "r_error": "", "src_len": 3640, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3057, "tout": 2697, "ts": 1791524417.4418814, "chk": "ok", "code_len": 3640}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5866, "tout": 68, "ts": 1791524538.0097358, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5958, "tout": 1738, "ts": 1791524552.5286791, "chk": null, "code_len": 3640}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3057, "started": 1791524390.8964193}
{"ep": "ok-00469", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 5.977, "speedup": 5.977, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 380.5, "calls": 3, "tokens_in": 31379, "tokens_out": 24371, "ctx_chars": 8224, "t_end": 1791524653.1973803, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.977, "lo95": 5.9541, "mean": 5.9026, "ev_only": 5.9928, "ref_ms": 31.44499, "cand_ms": 5.26102, "n_trials": 51, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9793, "r_wall_s": 50.27, "compile_s": 14.23, "r_error": "", "src_len": 8497, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5495, "tout": 15149, "ts": 1791524405.91162, "chk": "no_custom_kernel", "code_len": 8500}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10638, "tout": 4926, "ts": 1791524558.6892078, "chk": "ok", "code_len": 8497}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15246, "tout": 4296, "ts": 1791524602.8862226, "chk": null, "code_len": 8497}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5495, "started": 1791524272.6797016}
{"ep": "ok-00419", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 3.9167, "speedup": 3.9167, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 592.7, "calls": 3, "tokens_in": 249413, "tokens_out": 26183, "ctx_chars": 182830, "t_end": 1791524653.3533015, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 3.9167, "lo95": 3.9061, "mean": 3.9163, "ev_only": 3.9165, "ref_ms": 31.43966, "cand_ms": 8.02717, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9871, "r_wall_s": 96.09, "compile_s": 63.55, "r_error": "", "src_len": 8477, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78518, "tout": 16542, "ts": 1791524212.8189414, "chk": "no_custom_kernel", "code_len": 8479}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 83238, "tout": 5057, "ts": 1791524315.379791, "chk": "ok", "code_len": 8477}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 87657, "tout": 4584, "ts": 1791524557.1485088, "chk": null, "code_len": 8477}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 78518, "started": 1791524060.6635303}
{"ep": "ok-00446", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.7977, "speedup": 0.7977, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 484.9, "calls": 4, "tokens_in": 336641, "tokens_out": 12686, "ctx_chars": 182830, "t_end": 1791524656.2674568, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7977, "lo95": 0.6021, "mean": 0.7665, "ev_only": 0.7948, "ref_ms": 4.12273, "cand_ms": 5.16795, "n_trials": 203, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.1122, "r_wall_s": 81.07, "compile_s": 44.1, "r_error": "", "src_len": 6005, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79193, "tout": 3429, "ts": 1791524203.70715, "chk": "forbidden", "code_len": 6028}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 82720, "tout": 2840, "ts": 1791524228.2411034, "chk": "no_custom_kernel", "code_len": 5770}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 85691, "tout": 3237, "ts": 1791524403.1221564, "chk": "ok", "code_len": 6005}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 89037, "tout": 3180, "ts": 1791524575.1482694, "chk": null, "code_len": 6005}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "no_custom_kernel", "ok", null], "first_tin": 79193, "started": 1791524171.3930225}
{"ep": "ok-00488", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9955, "speedup": 0.9955, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 305.3, "calls": 3, "tokens_in": 17251, "tokens_out": 2876, "ctx_chars": 7273, "t_end": 1791524657.5110867, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9955, "lo95": 0.9951, "mean": 0.9956, "ev_only": 0.9959, "ref_ms": 8.03399, "cand_ms": 8.07004, "n_trials": 86, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0159, "r_wall_s": 119.47, "compile_s": 3.2, "r_error": "", "src_len": 2881, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4686, "tout": 1466, "ts": 1791524364.698862, "chk": "ok", "code_len": 2881}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6264, "tout": 13, "ts": 1791524526.4624126, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6301, "tout": 1397, "ts": 1791524537.8817143, "chk": null, "code_len": 2881}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4686, "started": 1791524352.2285929}
{"ep": "ok-00534", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7368, "speedup": 0.7368, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 98.5, "calls": 2, "tokens_in": 6497, "tokens_out": 1697, "ctx_chars": 2270, "t_end": 1791524659.0251033, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7368, "lo95": 0.5887, "mean": 0.7803, "ev_only": 0.7376, "ref_ms": 31.67264, "cand_ms": 42.98786, "n_trials": 31, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 61.07, "compile_s": 15.59, "r_error": "", "src_len": 1500, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2738, "tout": 912, "ts": 1791524573.4868143, "chk": "ok", "code_len": 1500}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3759, "tout": 785, "ts": 1791524597.9107127, "chk": null, "code_len": 1500}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2738, "started": 1791524560.530679}
{"ep": "ok-00523", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.1074, "speedup": 1.1074, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.3, "calls": 1, "tokens_in": 78394, "tokens_out": 2068, "ctx_chars": 182830, "t_end": 1791524668.6110775, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1074, "lo95": 1.1059, "mean": 1.1055, "ev_only": 1.107, "ref_ms": 22.29511, "cand_ms": 20.13372, "n_trials": 67, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0415, "r_wall_s": 123.29, "compile_s": 59.85, "r_error": "", "src_len": 3563, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 78394, "tout": 2068, "ts": 1791524545.0347095, "chk": null, "code_len": 3563}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 78394, "started": 1791524524.281891}
{"ep": "ok-00530", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9434, "speedup": 0.9434, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 125.1, "calls": 2, "tokens_in": 7023, "tokens_out": 5610, "ctx_chars": 1383, "t_end": 1791524670.87582, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9434, "lo95": 0.9428, "mean": 0.9437, "ev_only": 0.9434, "ref_ms": 29.76817, "cand_ms": 31.55568, "n_trials": 50, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0224, "r_wall_s": 64.1, "compile_s": 2.3, "r_error": "", "src_len": 3390, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2299, "tout": 3771, "ts": 1791524579.267371, "chk": "ok", "code_len": 3390}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4724, "tout": 1839, "ts": 1791524606.230127, "chk": null, "code_len": 3390}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2299, "started": 1791524545.8090448}
{"ep": "ok-00524", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0381, "speedup": 1.0381, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 157.9, "calls": 1, "tokens_in": 1933, "tokens_out": 2985, "ctx_chars": 495, "t_end": 1791524686.5066216, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0381, "lo95": 1.0369, "mean": 1.0376, "ev_only": 1.0369, "ref_ms": 8.24048, "cand_ms": 7.93842, "n_trials": 179, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0029, "r_wall_s": 129.81, "compile_s": 23.3, "r_error": "", "src_len": 2747, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1933, "tout": 2985, "ts": 1791524556.5933812, "chk": null, "code_len": 2747}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1933, "started": 1791524528.6199348}
{"ep": "ok-00499", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7836, "speedup": 0.7836, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 288.1, "calls": 2, "tokens_in": 6489, "tokens_out": 1673, "ctx_chars": 2270, "t_end": 1791524688.8374815, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7836, "lo95": 0.7763, "mean": 0.7826, "ev_only": 0.7834, "ref_ms": 31.49199, "cand_ms": 40.19081, "n_trials": 31, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 154.78, "compile_s": 14.3, "r_error": "", "src_len": 1498, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2738, "tout": 904, "ts": 1791524409.9837353, "chk": "ok", "code_len": 1498}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3751, "tout": 769, "ts": 1791524533.9463027, "chk": null, "code_len": 1498}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2738, "started": 1791524400.7740934}
{"ep": "ok-00453", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.007, "speedup": 0.007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 473.5, "calls": 2, "tokens_in": 160665, "tokens_out": 6062, "ctx_chars": 182830, "t_end": 1791524688.9516084, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.007, "lo95": 0.007, "mean": 0.007, "ev_only": 0.007, "ref_ms": 31.54784, "cand_ms": 4485.83555, "n_trials": 11, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 222.34, "compile_s": 62.16, "r_error": "", "src_len": 4419, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78516, "tout": 3522, "ts": 1791524252.2559764, "chk": "ok", "code_len": 5200}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82149, "tout": 2540, "ts": 1791524466.5691295, "chk": null, "code_len": 4419}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78516, "started": 1791524215.478952}
{"ep": "ok-00528", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.4977, "speedup": 1.4977, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 145.7, "calls": 2, "tokens_in": 5888, "tokens_out": 5846, "ctx_chars": 0, "t_end": 1791524689.3731425, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.4977, "lo95": 1.4972, "mean": 1.5332, "ev_only": 1.4954, "ref_ms": 8.20855, "cand_ms": 5.4807, "n_trials": 197, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 81.63, "compile_s": 2.44, "r_error": "", "src_len": 3439, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 3966, "ts": 1791524578.2992358, "chk": "ok", "code_len": 3439}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4086, "tout": 1880, "ts": 1791524607.6974585, "chk": null, "code_len": 3439}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524543.7201476}
{"ep": "ok-00468", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.7841, "speedup": 0.7841, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 427.8, "calls": 4, "tokens_in": 28239, "tokens_out": 7629, "ctx_chars": 0, "t_end": 1791524691.1532226, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7841, "lo95": 0.7811, "mean": 0.7885, "ev_only": 0.7868, "ref_ms": 3.29715, "cand_ms": 4.20526, "n_trials": 172, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0057, "r_wall_s": 211.1, "compile_s": 4.58, "r_error": "", "src_len": 2669, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2626, "tout": 4635, "ts": 1791524301.4706626, "chk": "no_custom_kernel", "code_len": 4969}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7383, "tout": 1557, "ts": 1791524369.8307793, "chk": "ok", "code_len": 2669}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9052, "tout": 102, "ts": 1791524468.9000993, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9178, "tout": 1335, "ts": 1791524479.988714, "chk": null, "code_len": 2669}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", "no_code", null], "first_tin": 2626, "started": 1791524263.354526}
{"ep": "ok-00532", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0082, "speedup": 1.0082, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 139.7, "calls": 2, "tokens_in": 15037, "tokens_out": 5230, "ctx_chars": 10823, "t_end": 1791524698.3810291, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0082, "lo95": 1.0071, "mean": 0.9674, "ev_only": 1.0084, "ref_ms": 8.16736, "cand_ms": 8.10066, "n_trials": 164, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0083, "r_wall_s": 51.64, "compile_s": 2.0, "r_error": "", "src_len": 3501, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 3452, "ts": 1791524608.5212283, "chk": "ok", "code_len": 3501}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8673, "tout": 1778, "ts": 1791524646.556678, "chk": null, "code_len": 3501}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6364, "started": 1791524579.1453235}
{"ep": "ok-00462", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 5.503, "speedup": 5.503, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 460.3, "calls": 3, "tokens_in": 28298, "tokens_out": 33534, "ctx_chars": 495, "t_end": 1791524704.916464, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 5.503, "lo95": 4.6727, "mean": 5.0744, "ev_only": 5.4751, "ref_ms": 4.03857, "cand_ms": 0.73389, "n_trials": 164, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.993, "r_wall_s": 83.9, "compile_s": 16.26, "r_error": "", "src_len": 11190, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2491, "tout": 20374, "ts": 1791524445.1176298, "chk": "no_custom_kernel", "code_len": 11535}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9600, "tout": 6802, "ts": 1791524563.1716983, "chk": "ok", "code_len": 11190}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16207, "tout": 6358, "ts": 1791524620.9936697, "chk": null, "code_len": 11190}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2491, "started": 1791524264.969082}
{"ep": "ok-00487", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9293, "speedup": 0.9293, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 358.2, "calls": 3, "tokens_in": 240382, "tokens_out": 6253, "ctx_chars": 182830, "t_end": 1791524705.2745445, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9293, "lo95": 0.9276, "mean": 0.9289, "ev_only": 0.9295, "ref_ms": 8.16845, "cand_ms": 8.78955, "n_trials": 113, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 76.63, "compile_s": 2.64, "r_error": "", "src_len": 4016, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78290, "tout": 1269, "ts": 1791524360.4680474, "chk": "ok", "code_len": 1937}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 79671, "tout": 2638, "ts": 1791524585.7647269, "chk": "ok", "code_len": 4086}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 82421, "tout": 2346, "ts": 1791524628.5726466, "chk": null, "code_len": 4016}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 78290, "started": 1791524347.10894}
{"ep": "ok-00526", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.223, "speedup": 0.223, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 168.0, "calls": 1, "tokens_in": 5329, "tokens_out": 2139, "ctx_chars": 6513, "t_end": 1791524705.3108027, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.223, "lo95": 0.21, "mean": 0.2739, "ev_only": 0.2221, "ref_ms": 3.63242, "cand_ms": 16.28847, "n_trials": 76, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0763, "r_wall_s": 150.08, "compile_s": 2.54, "r_error": "", "src_len": 4221, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5329, "tout": 2139, "ts": 1791524555.1210122, "chk": null, "code_len": 4221}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5329, "started": 1791524537.3208163}
{"ep": "ok-00519", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0245, "speedup": 1.0245, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 190.8, "calls": 2, "tokens_in": 5056, "tokens_out": 2933, "ctx_chars": 495, "t_end": 1791524705.6052327, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0245, "lo95": 1.0227, "mean": 0.9956, "ev_only": 1.0253, "ref_ms": 8.31011, "cand_ms": 8.11123, "n_trials": 188, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 53.51, "compile_s": 2.23, "r_error": "", "src_len": 1789, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1858, "tout": 1880, "ts": 1791524531.5842896, "chk": "ok", "code_len": 1789}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3198, "tout": 1053, "ts": 1791524651.944336, "chk": null, "code_len": 1789}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1858, "started": 1791524514.822154}
{"ep": "ok-00441", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0003, "speedup": 1.0003, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 550.7, "calls": 5, "tokens_in": 37097, "tokens_out": 3633, "ctx_chars": 9192, "t_end": 1791524707.1543138, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0003, "lo95": 1.0001, "mean": 1.002, "ev_only": 0.9994, "ref_ms": 7.92267, "cand_ms": 7.91998, "n_trials": 86, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 154.31, "compile_s": 2.5, "r_error": "", "src_len": 890, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 675, "ts": 1791524163.632621, "chk": "incorrect", "code_len": 1139}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6439, "tout": 826, "ts": 1791524265.448074, "chk": "incorrect", "code_len": 1178}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7398, "tout": 848, "ts": 1791524362.2585738, "chk": "incorrect", "code_len": 1042}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8380, "tout": 712, "ts": 1791524416.072791, "chk": "incorrect", "code_len": 1031}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9249, "tout": 572, "ts": 1791524552.7330117, "chk": null, "code_len": 890}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 5631, "started": 1791524156.4803374}
{"ep": "ok-00455", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 4.568, "speedup": 4.568, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 494.3, "calls": 3, "tokens_in": 21076, "tokens_out": 22081, "ctx_chars": 1495, "t_end": 1791524714.422239, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.568, "lo95": 4.5408, "mean": 4.7664, "ev_only": 4.6153, "ref_ms": 32.38004, "cand_ms": 7.08843, "n_trials": 37, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9947, "r_wall_s": 222.01, "compile_s": 22.46, "r_error": "", "src_len": 8240, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2464, "tout": 12475, "ts": 1791524332.579198, "chk": "no_custom_kernel", "code_len": 8357}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7175, "tout": 5224, "ts": 1791524416.42426, "chk": "ok", "code_len": 8240}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11437, "tout": 4382, "ts": 1791524492.3658767, "chk": null, "code_len": 8240}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2464, "started": 1791524220.1453452}
{"ep": "ok-00416", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 10.92, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 666.4, "calls": 3, "tokens_in": 28368, "tokens_out": 35551, "ctx_chars": 495, "t_end": 1791524716.3707218, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 10.92, "lo95": 8.736, "mean": 9.0189, "ev_only": 11.0856, "ref_ms": 6.07005, "cand_ms": 0.55587, "n_trials": 176, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 0.9924, "r_wall_s": 229.17, "compile_s": 22.75, "r_error": "", "src_len": 12900, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2491, "tout": 22310, "ts": 1791524242.2392783, "chk": "no_custom_kernel", "code_len": 13063}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9623, "tout": 6765, "ts": 1791524390.9490201, "chk": "ok", "code_len": 12900}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16254, "tout": 6476, "ts": 1791524487.1401546, "chk": null, "code_len": 12900}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2491, "started": 1791524049.9492693}
{"ep": "ok-00436", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 4.2874, "speedup": 4.2874, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 594.7, "calls": 3, "tokens_in": 30896, "tokens_out": 27845, "ctx_chars": 7992, "t_end": 1791524718.2301593, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.2874, "lo95": 4.2762, "mean": 4.5413, "ev_only": 4.2966, "ref_ms": 32.15977, "cand_ms": 7.50095, "n_trials": 41, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9998, "r_wall_s": 244.58, "compile_s": 21.18, "r_error": "", "src_len": 8814, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 18101, "ts": 1791524289.2677946, "chk": "no_custom_kernel", "code_len": 8809}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10446, "tout": 5388, "ts": 1791524416.0015368, "chk": "ok", "code_len": 8814}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15119, "tout": 4356, "ts": 1791524473.6097953, "chk": null, "code_len": 8814}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5331, "started": 1791524123.5760546}
{"ep": "ok-00533", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 47.4483, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.4, "calls": 2, "tokens_in": 7455, "tokens_out": 6084, "ctx_chars": 2256, "t_end": 1791524720.2119708, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 47.4483, "lo95": 46.7697, "mean": 43.8957, "ev_only": 47.4135, "ref_ms": 22.27717, "cand_ms": 0.4695, "n_trials": 75, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 92.95, "compile_s": 2.82, "r_error": "", "src_len": 2868, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2666, "tout": 4581, "ts": 1791524599.6953025, "chk": "ok", "code_len": 2868}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4789, "tout": 1503, "ts": 1791524627.0603137, "chk": null, "code_len": 2868}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2666, "started": 1791524558.8288207}
{"ep": "ok-00501", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 58.0813, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 316.6, "calls": 2, "tokens_in": 18281, "tokens_out": 8440, "ctx_chars": 12888, "t_end": 1791524720.3151567, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 58.0813, "lo95": 57.3442, "mean": 56.2565, "ev_only": 58.0383, "ref_ms": 22.35155, "cand_ms": 0.38483, "n_trials": 68, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 230.08, "compile_s": 3.54, "r_error": "", "src_len": 4180, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7686, "tout": 6307, "ts": 1791524460.7881434, "chk": "ok", "code_len": 4233}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10595, "tout": 2133, "ts": 1791524490.016456, "chk": null, "code_len": 4180}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7686, "started": 1791524403.7455475}
{"ep": "ok-00538", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0237, "speedup": 1.0237, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 140.7, "calls": 3, "tokens_in": 18178, "tokens_out": 2956, "ctx_chars": 7245, "t_end": 1791524723.1439304, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0237, "lo95": 1.023, "mean": 1.0237, "ev_only": 1.0237, "ref_ms": 29.81947, "cand_ms": 29.1292, "n_trials": 37, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0417, "r_wall_s": 70.66, "compile_s": 2.98, "r_error": "", "src_len": 2830, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4949, "tout": 1535, "ts": 1791524596.6319213, "chk": "ok", "code_len": 3019}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6596, "tout": 13, "ts": 1791524640.4260256, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6633, "tout": 1408, "ts": 1791524651.8440986, "chk": null, "code_len": 2830}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4949, "started": 1791524582.4840968}
{"ep": "ok-00500", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.7608, "speedup": 0.7608, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 327.2, "calls": 2, "tokens_in": 10620, "tokens_out": 4175, "ctx_chars": 4637, "t_end": 1791524728.4913535, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7608, "lo95": 0.7557, "mean": 0.7782, "ev_only": 0.7559, "ref_ms": 4.03548, "cand_ms": 5.30424, "n_trials": 184, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0693, "r_wall_s": 186.4, "compile_s": 1.99, "r_error": "", "src_len": 3680, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4066, "tout": 2376, "ts": 1791524424.3511162, "chk": "ok", "code_len": 3794}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6554, "tout": 1799, "ts": 1791524541.9841144, "chk": null, "code_len": 3680}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4066, "started": 1791524401.274287}
{"ep": "ok-00471", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 6.2187, "speedup": 6.2187, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 455.9, "calls": 3, "tokens_in": 27269, "tokens_out": 17429, "ctx_chars": 7644, "t_end": 1791524735.0971751, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.2187, "lo95": 6.1979, "mean": 6.2033, "ev_only": 6.2052, "ref_ms": 31.9996, "cand_ms": 5.14568, "n_trials": 40, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 248.73, "compile_s": 21.51, "r_error": "", "src_len": 6715, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5260, "tout": 10361, "ts": 1791524372.3551104, "chk": "no_custom_kernel", "code_len": 6739}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9251, "tout": 3765, "ts": 1791524447.825526, "chk": "ok", "code_len": 6715}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12758, "tout": 3303, "ts": 1791524486.3191495, "chk": null, "code_len": 6715}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5260, "started": 1791524279.2421603}
{"ep": "ok-00544", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0267, "speedup": 1.0267, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 113.8, "calls": 1, "tokens_in": 1723, "tokens_out": 989, "ctx_chars": 0, "t_end": 1791524737.984394, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0267, "lo95": 1.0261, "mean": 1.0738, "ev_only": 1.0267, "ref_ms": 8.13597, "cand_ms": 7.92461, "n_trials": 102, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 103.81, "compile_s": 3.02, "r_error": "", "src_len": 1906, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1723, "tout": 989, "ts": 1791524634.0633357, "chk": null, "code_len": 1906}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1723, "started": 1791524624.162561}
{"ep": "ok-00493", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.995, "speedup": 0.995, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 373.1, "calls": 3, "tokens_in": 18430, "tokens_out": 3120, "ctx_chars": 7758, "t_end": 1791524740.8540711, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.995, "lo95": 0.9945, "mean": 0.9951, "ev_only": 0.9956, "ref_ms": 8.09395, "cand_ms": 8.1348, "n_trials": 171, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0089, "r_wall_s": 260.65, "compile_s": 6.07, "r_error": "", "src_len": 2935, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4947, "tout": 1642, "ts": 1791524382.2375445, "chk": "ok", "code_len": 2935}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6701, "tout": 57, "ts": 1791524468.726032, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6782, "tout": 1421, "ts": 1791524480.109374, "chk": null, "code_len": 2935}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4947, "started": 1791524367.7237906}
{"ep": "ok-00537", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9258, "speedup": 0.9258, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 180.1, "calls": 2, "tokens_in": 7062, "tokens_out": 11015, "ctx_chars": 495, "t_end": 1791524742.289717, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9258, "lo95": 0.9255, "mean": 0.9258, "ev_only": 0.9247, "ref_ms": 8.04023, "cand_ms": 8.68492, "n_trials": 170, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9993, "r_wall_s": 60.4, "compile_s": 2.03, "r_error": "", "src_len": 5564, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1740, "tout": 6985, "ts": 1791524622.264116, "chk": "ok", "code_len": 5564}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5322, "tout": 4030, "ts": 1791524681.815214, "chk": null, "code_len": 5564}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1740, "started": 1791524562.2340994}
{"ep": "ok-00504", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.159, "speedup": 0.159, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 318.7, "calls": 4, "tokens_in": 18019, "tokens_out": 5470, "ctx_chars": 0, "t_end": 1791524743.9817383, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.159, "lo95": 0.1583, "mean": 0.1593, "ev_only": 0.1589, "ref_ms": 31.19362, "cand_ms": 196.17622, "n_trials": 15, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.3875, "r_wall_s": 186.64, "compile_s": 34.01, "r_error": "", "src_len": 3655, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1949, "tout": 1995, "ts": 1791524443.4419289, "chk": "forbidden", "code_len": 3796}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4105, "tout": 1686, "ts": 1791524457.880793, "chk": "ok", "code_len": 3655}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5903, "tout": 135, "ts": 1791524543.3395822, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6062, "tout": 1654, "ts": 1791524557.2159002, "chk": null, "code_len": 3655}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 1949, "started": 1791524425.2620683}
{"ep": "ok-00448", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.8163, "speedup": 0.8163, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 565.4, "calls": 3, "tokens_in": 24759, "tokens_out": 18186, "ctx_chars": 0, "t_end": 1791524746.8819177, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8163, "lo95": 0.8142, "mean": 0.8159, "ev_only": 0.8164, "ref_ms": 16.01857, "cand_ms": 19.62327, "n_trials": 66, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.024, "r_wall_s": 196.68, "compile_s": 20.01, "r_error": "", "src_len": 4977, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 12307, "ts": 1791524284.7696137, "chk": "incorrect", "code_len": 12940}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9608, "tout": 3467, "ts": 1791524375.260304, "chk": "ok", "code_len": 4977}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12232, "tout": 2412, "ts": 1791524550.0917532, "chk": null, "code_len": 4977}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2919, "started": 1791524181.4451673}
{"ep": "ok-00522", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0229, "speedup": 1.0229, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 229.1, "calls": 2, "tokens_in": 10700, "tokens_out": 2061, "ctx_chars": 6811, "t_end": 1791524751.80061, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0229, "lo95": 1.021, "mean": 1.0203, "ev_only": 1.0249, "ref_ms": 8.17587, "cand_ms": 7.9925, "n_trials": 162, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 74.51, "compile_s": 2.5, "r_error": "", "src_len": 1771, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4724, "tout": 1140, "ts": 1791524531.5551746, "chk": "ok", "code_len": 1771}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5976, "tout": 921, "ts": 1791524677.1458833, "chk": null, "code_len": 1771}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4724, "started": 1791524522.7276106}
{"ep": "ok-00558", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 81.3, "calls": 1, "tokens_in": 1960, "tokens_out": 1814, "ctx_chars": 495, "t_end": 1791524752.1422856, "error": "RuntimeError: Error building extension 'fused_pool_l2_050': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_l2_050 -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": 64.44, "compile_s": 64.43, "r_error": "RuntimeError: Error building extension 'fused_pool_l2_050': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_l2_050 -DTORCH_API_INCLUDE_EXTENSION_H", "src_len": 3550, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1960, "tout": 1814, "ts": 1791524687.679823, "chk": null, "code_len": 3550}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1960, "started": 1791524670.8760865}
{"ep": "ok-00515", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0958, "speedup": 1.0958, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.0, "calls": 3, "tokens_in": 24253, "tokens_out": 2133, "ctx_chars": 12121, "t_end": 1791524753.0750875, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0958, "lo95": 1.0943, "mean": 1.0956, "ev_only": 1.0946, "ref_ms": 22.34236, "cand_ms": 20.3898, "n_trials": 31, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0187, "r_wall_s": 72.09, "compile_s": 2.06, "r_error": "", "src_len": 2082, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7260, "tout": 1106, "ts": 1791524523.6544688, "chk": "ok", "code_len": 2082}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8478, "tout": 13, "ts": 1791524672.3653157, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8515, "tout": 1014, "ts": 1791524680.77914, "chk": null, "code_len": 2082}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7260, "started": 1791524513.410523}
{"ep": "ok-00503", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.1725, "speedup": 0.1725, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 336.5, "calls": 3, "tokens_in": 30199, "tokens_out": 10156, "ctx_chars": 8141, "t_end": 1791524756.725109, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.1725, "lo95": 0.1599, "mean": 0.2098, "ev_only": 0.1722, "ref_ms": 59.35729, "cand_ms": 344.04464, "n_trials": 13, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9974, "r_wall_s": 42.44, "compile_s": 2.98, "r_error": "", "src_len": 2932, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5389, "tout": 5117, "ts": 1791524468.6266572, "chk": "ok", "code_len": 2919}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10618, "tout": 3462, "ts": 1791524536.1446698, "chk": "ok", "code_len": 2932}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14192, "tout": 1577, "ts": 1791524714.257465, "chk": null, "code_len": 2932}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 5389, "started": 1791524420.1894224}
{"ep": "ok-00470", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 19.1635, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 494.4, "calls": 2, "tokens_in": 14894, "tokens_out": 6013, "ctx_chars": 10255, "t_end": 1791524768.2518961, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 19.1635, "lo95": 18.3594, "mean": 16.3087, "ev_only": 19.6075, "ref_ms": 22.44653, "cand_ms": 1.17131, "n_trials": 58, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.8563, "r_wall_s": 66.9, "compile_s": 1.86, "r_error": "", "src_len": 2627, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6434, "tout": 4585, "ts": 1791524316.1059604, "chk": "ok", "code_len": 2627}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8460, "tout": 1428, "ts": 1791524566.0946777, "chk": null, "code_len": 2627}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6434, "started": 1791524273.8493655}
{"ep": "ok-00450", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 5.0806, "speedup": 5.0806, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 580.7, "calls": 3, "tokens_in": 33343, "tokens_out": 36856, "ctx_chars": 4637, "t_end": 1791524778.6034367, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 5.0806, "lo95": 5.0567, "mean": 5.0566, "ev_only": 5.1398, "ref_ms": 4.04751, "cand_ms": 0.79666, "n_trials": 230, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 89.0, "compile_s": 26.58, "r_error": "", "src_len": 12178, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4068, "tout": 23484, "ts": 1791524408.009644, "chk": "no_custom_kernel", "code_len": 12641}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11356, "tout": 7003, "ts": 1791524509.60125, "chk": "ok", "code_len": 12178}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 17919, "tout": 6369, "ts": 1791524689.5724983, "chk": null, "code_len": 12178}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 4068, "started": 1791524197.8719244}
{"ep": "ok-00508", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.6763, "speedup": 1.6763, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 345.4, "calls": 3, "tokens_in": 243837, "tokens_out": 13050, "ctx_chars": 182830, "t_end": 1791524780.7339492, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.6763, "lo95": 1.6752, "mean": 1.6699, "ev_only": 1.6823, "ref_ms": 8.28155, "cand_ms": 4.94045, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9991, "r_wall_s": 21.1, "compile_s": 2.0, "r_error": "", "src_len": 4460, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78369, "tout": 4964, "ts": 1791524481.6068995, "chk": "incorrect", "code_len": 4243}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81270, "tout": 4430, "ts": 1791524632.6418912, "chk": "ok", "code_len": 4460}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 84198, "tout": 3656, "ts": 1791524759.5869322, "chk": null, "code_len": 4460}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78369, "started": 1791524435.2954426}
{"ep": "ok-00473", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.9094, "speedup": 0.9094, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 502.4, "calls": 4, "tokens_in": 36085, "tokens_out": 17110, "ctx_chars": 0, "t_end": 1791524783.7002513, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9094, "lo95": 0.9058, "mean": 0.9189, "ev_only": 0.9096, "ref_ms": 17.01484, "cand_ms": 18.70914, "n_trials": 74, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0343, "r_wall_s": 30.42, "compile_s": 1.97, "r_error": "", "src_len": 3819, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 7832, "ts": 1791524346.182148, "chk": "incorrect", "code_len": 8387}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7702, "tout": 4832, "ts": 1791524449.390368, "chk": "incorrect", "code_len": 7519}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11699, "tout": 2602, "ts": 1791524532.1110382, "chk": "ok", "code_len": 3819}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13765, "tout": 1844, "ts": 1791524753.2395182, "chk": null, "code_len": 3819}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2919, "started": 1791524281.341238}
{"ep": "ok-00550", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0245, "speedup": 1.0245, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 151.4, "calls": 3, "tokens_in": 12672, "tokens_out": 1888, "ctx_chars": 4565, "t_end": 1791524785.5860682, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0245, "lo95": 1.0242, "mean": 1.0297, "ev_only": 1.0252, "ref_ms": 8.15852, "cand_ms": 7.96335, "n_trials": 190, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.007, "r_wall_s": 125.27, "compile_s": 2.78, "r_error": "", "src_len": 1888, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3499, "tout": 957, "ts": 1791524642.9005766, "chk": "ok", "code_len": 1888}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4568, "tout": 13, "ts": 1791524652.7260866, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4605, "tout": 918, "ts": 1791524660.2531006, "chk": null, "code_len": 1888}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3499, "started": 1791524634.1591737}
{"ep": "ok-00483", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 450.7, "calls": 5, "tokens_in": 24248, "tokens_out": 3957, "ctx_chars": 3492, "t_end": 1791524790.7229695, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 4, "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": 0.0035, "r_wall_s": 100.53, "compile_s": 7.86, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1023, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3009, "tout": 686, "ts": 1791524347.256872, "chk": "incorrect", "code_len": 1137}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3828, "tout": 912, "ts": 1791524409.7039945, "chk": "incorrect", "code_len": 1210}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4873, "tout": 871, "ts": 1791524558.4203377, "chk": "incorrect", "code_len": 1031}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 5877, "tout": 628, "ts": 1791524627.1746984, "chk": "incorrect", "code_len": 1070}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 6661, "tout": 860, "ts": 1791524690.163371, "chk": null, "code_len": 1023}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 3009, "started": 1791524340.0191338}
{"ep": "ok-00565", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 87.1, "calls": 1, "tokens_in": 1723, "tokens_out": 1791, "ctx_chars": 0, "t_end": 1791524792.0542548, "error": "RuntimeError: Error building extension 'gn_ht': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -is", "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": 70.74, "compile_s": 70.71, "r_error": "RuntimeError: Error building extension 'gn_ht': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -is", "src_len": 3681, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1723, "tout": 1791, "ts": 1791524721.2926369, "chk": null, "code_len": 3681}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1723, "started": 1791524704.9167347}
{"ep": "ok-00554", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.8973, "speedup": 0.8973, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 144.3, "calls": 3, "tokens_in": 17521, "tokens_out": 4878, "ctx_chars": 2922, "t_end": 1791524800.5645897, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8973, "lo95": 0.8385, "mean": 1.007, "ev_only": 0.8943, "ref_ms": 4.42112, "cand_ms": 4.92736, "n_trials": 178, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.7027, "r_wall_s": 67.58, "compile_s": 21.12, "r_error": "", "src_len": 2613, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3403, "tout": 3515, "ts": 1791524689.0149436, "chk": "ok", "code_len": 2613}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7030, "tout": 34, "ts": 1791524721.8210397, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7088, "tout": 1329, "ts": 1791524732.9557095, "chk": null, "code_len": 2613}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3403, "started": 1791524656.2677789}
{"ep": "ok-00505", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0062, "speedup": 1.0062, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 375.9, "calls": 5, "tokens_in": 22997, "tokens_out": 8555, "ctx_chars": 1080, "t_end": 1791524803.4702034, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0062, "lo95": 1.006, "mean": 1.006, "ev_only": 1.0046, "ref_ms": 7.93105, "cand_ms": 7.8823, "n_trials": 143, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0001, "r_wall_s": 143.04, "compile_s": 2.97, "r_error": "", "src_len": 999, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 2023, "ts": 1791524445.8012102, "chk": "incorrect", "code_len": 1691}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3463, "tout": 2489, "ts": 1791524585.1603963, "chk": "incorrect", "code_len": 1727}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4773, "tout": 1843, "ts": 1791524611.4585288, "chk": "incorrect", "code_len": 1123}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 5826, "tout": 1364, "ts": 1791524643.114636, "chk": "ok", "code_len": 999}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 6817, "tout": 836, "ts": 1791524660.4088917, "chk": null, "code_len": 999}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 2118, "started": 1791524427.5949538}
{"ep": "ok-00541", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.6736, "speedup": 0.6736, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.3, "calls": 2, "tokens_in": 16214, "tokens_out": 12965, "ctx_chars": 9125, "t_end": 1791524807.3169086, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6736, "lo95": 0.6718, "mean": 0.687, "ev_only": 0.6726, "ref_ms": 3.45571, "cand_ms": 5.13056, "n_trials": 193, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.2996, "r_wall_s": 16.2, "compile_s": 2.24, "r_error": "", "src_len": 6207, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6281, "tout": 9362, "ts": 1791524676.537235, "chk": "ok", "code_len": 6207}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9933, "tout": 3603, "ts": 1791524791.0055854, "chk": null, "code_len": 6207}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6281, "started": 1791524593.9735916}
{"ep": "ok-00567", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7835, "speedup": 0.7835, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 104.2, "calls": 2, "tokens_in": 13454, "tokens_out": 4495, "ctx_chars": 6513, "t_end": 1791524809.5368757, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7835, "lo95": 0.7779, "mean": 0.7925, "ev_only": 0.7831, "ref_ms": 17.19938, "cand_ms": 21.95258, "n_trials": 57, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0406, "r_wall_s": 19.7, "compile_s": 2.04, "r_error": "", "src_len": 3749, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5622, "tout": 2740, "ts": 1791524727.6936367, "chk": "ok", "code_len": 3749}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7832, "tout": 1755, "ts": 1791524789.7330337, "chk": null, "code_len": 3749}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5622, "started": 1791524705.3111358}
{"ep": "ok-00556", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0372, "speedup": 1.0372, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 152.4, "calls": 2, "tokens_in": 15694, "tokens_out": 2874, "ctx_chars": 12848, "t_end": 1791524811.4097881, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0372, "lo95": 1.0365, "mean": 1.0382, "ev_only": 1.0368, "ref_ms": 8.26138, "cand_ms": 7.96506, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 42.2, "compile_s": 1.91, "r_error": "", "src_len": 1747, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7155, "tout": 1959, "ts": 1791524675.8058257, "chk": "ok", "code_len": 1747}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8539, "tout": 915, "ts": 1791524769.166687, "chk": null, "code_len": 1747}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7155, "started": 1791524659.0254343}
{"ep": "ok-00575", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.4647, "speedup": 1.4647, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 89.2, "calls": 2, "tokens_in": 6001, "tokens_out": 6071, "ctx_chars": 0, "t_end": 1791524812.3492599, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4647, "lo95": 1.464, "mean": 1.4647, "ev_only": 1.4666, "ref_ms": 8.21256, "cand_ms": 5.60697, "n_trials": 151, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 28.56, "compile_s": 1.88, "r_error": "", "src_len": 3410, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 4174, "ts": 1791524759.9063451, "chk": "ok", "code_len": 3410}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4199, "tout": 1897, "ts": 1791524783.6786382, "chk": null, "code_len": 3410}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524723.1442103}
{"ep": "ok-00475", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9273, "speedup": 0.9273, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 527.5, "calls": 5, "tokens_in": 56007, "tokens_out": 25830, "ctx_chars": 495, "t_end": 1791524813.64908, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9273, "lo95": 0.9067, "mean": 0.8891, "ev_only": 0.9273, "ref_ms": 17.25083, "cand_ms": 18.6029, "n_trials": 54, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0376, "r_wall_s": 39.63, "compile_s": 2.09, "r_error": "", "src_len": 3936, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3052, "tout": 9254, "ts": 1791524365.2880194, "chk": "incorrect", "code_len": 7889}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7437, "tout": 5740, "ts": 1791524463.2498584, "chk": "incorrect", "code_len": 8133}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11891, "tout": 5728, "ts": 1791524522.8764622, "chk": "incorrect", "code_len": 6775}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 15699, "tout": 2818, "ts": 1791524674.8416455, "chk": "ok", "code_len": 3936}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 17928, "tout": 2290, "ts": 1791524773.9772534, "chk": null, "code_len": 3936}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 3052, "started": 1791524286.1398273}
{"ep": "ok-00529", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.1002, "speedup": 1.1002, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 271.5, "calls": 2, "tokens_in": 158872, "tokens_out": 3493, "ctx_chars": 182830, "t_end": 1791524815.8368404, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.1002, "lo95": 1.0994, "mean": 1.0997, "ev_only": 1.0995, "ref_ms": 22.25322, "cand_ms": 20.22619, "n_trials": 44, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.041, "r_wall_s": 171.81, "compile_s": 51.12, "r_error": "", "src_len": 3036, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78394, "tout": 1972, "ts": 1791524564.8020906, "chk": "ok", "code_len": 3129}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 80478, "tout": 1521, "ts": 1791524643.7163754, "chk": null, "code_len": 3036}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78394, "started": 1791524544.3269424}
{"ep": "ok-00563", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.9945, "speedup": 0.9945, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 126.1, "calls": 3, "tokens_in": 22475, "tokens_out": 2985, "ctx_chars": 10823, "t_end": 1791524817.2259915, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9945, "lo95": 0.9941, "mean": 0.9946, "ev_only": 0.9952, "ref_ms": 8.02614, "cand_ms": 8.07079, "n_trials": 123, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0178, "r_wall_s": 27.79, "compile_s": 1.92, "r_error": "", "src_len": 2875, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1548, "ts": 1791524704.7735016, "chk": "ok", "code_len": 2875}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8022, "tout": 45, "ts": 1791524777.887933, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8091, "tout": 1392, "ts": 1791524789.2788563, "chk": null, "code_len": 2875}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791524691.153471}
{"ep": "ok-00549", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.9758, "speedup": 0.9758, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 184.3, "calls": 2, "tokens_in": 8881, "tokens_out": 4144, "ctx_chars": 2425, "t_end": 1791524817.6949956, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9758, "lo95": 0.9716, "mean": 0.9812, "ev_only": 0.9719, "ref_ms": 4.144, "cand_ms": 4.24689, "n_trials": 207, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0046, "r_wall_s": 91.93, "compile_s": 33.96, "r_error": "", "src_len": 4115, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 2225, "ts": 1791524653.8094885, "chk": "ok", "code_len": 4252}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5609, "tout": 1919, "ts": 1791524725.7416818, "chk": null, "code_len": 4115}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3272, "started": 1791524633.4411929}
{"ep": "ok-00545", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0185, "speedup": 1.0185, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 194.1, "calls": 3, "tokens_in": 25277, "tokens_out": 2921, "ctx_chars": 12352, "t_end": 1791524818.7413528, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0185, "lo95": 1.0182, "mean": 1.0182, "ev_only": 1.018, "ref_ms": 29.66808, "cand_ms": 29.13059, "n_trials": 51, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0389, "r_wall_s": 78.7, "compile_s": 23.98, "r_error": "", "src_len": 2744, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7327, "tout": 1496, "ts": 1791524638.1651685, "chk": "ok", "code_len": 2744}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8935, "tout": 56, "ts": 1791524728.1667523, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9015, "tout": 1369, "ts": 1791524739.518458, "chk": null, "code_len": 2744}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7327, "started": 1791524624.6378624}
{"ep": "ok-00518", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0005, "speedup": 1.0005, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 313.8, "calls": 2, "tokens_in": 160864, "tokens_out": 5303, "ctx_chars": 182830, "t_end": 1791524820.0192108, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0005, "lo95": 0.9946, "mean": 1.071, "ev_only": 0.9969, "ref_ms": 4.04418, "cand_ms": 4.04201, "n_trials": 203, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0814, "r_wall_s": 104.3, "compile_s": 67.71, "r_error": "", "src_len": 4531, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78923, "tout": 2906, "ts": 1791524535.6003115, "chk": "ok", "code_len": 4661}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81941, "tout": 2397, "ts": 1791524715.6860082, "chk": null, "code_len": 4531}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78923, "started": 1791524506.258536}
{"ep": "ok-00557", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.097, "speedup": 1.097, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 151.7, "calls": 1, "tokens_in": 7259, "tokens_out": 1053, "ctx_chars": 12103, "t_end": 1791524820.300332, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.097, "lo95": 1.0935, "mean": 1.0951, "ev_only": 1.0961, "ref_ms": 22.32721, "cand_ms": 20.35274, "n_trials": 42, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0186, "r_wall_s": 141.6, "compile_s": 2.07, "r_error": "", "src_len": 2100, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7259, "tout": 1053, "ts": 1791524678.4923668, "chk": null, "code_len": 2100}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7259, "started": 1791524668.6115339}
{"ep": "ok-00540", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 31.273, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 240.0, "calls": 3, "tokens_in": 32814, "tokens_out": 7795, "ctx_chars": 16078, "t_end": 1791524827.9574156, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 31.273, "lo95": 30.987, "mean": 30.3185, "ev_only": 31.3887, "ref_ms": 22.34328, "cand_ms": 0.71446, "n_trials": 60, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.8309, "r_wall_s": 47.97, "compile_s": 2.05, "r_error": "", "src_len": 2752, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8865, "tout": 4002, "ts": 1791524623.5639849, "chk": "runtime_error", "code_len": 2719}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11084, "tout": 2231, "ts": 1791524703.655861, "chk": "ok", "code_len": 2752}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12865, "tout": 1562, "ts": 1791524779.709272, "chk": null, "code_len": 2752}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 8865, "started": 1791524587.9991667}
{"ep": "ok-00543", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0168, "speedup": 1.0168, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.1, "calls": 3, "tokens_in": 22603, "tokens_out": 2920, "ctx_chars": 10528, "t_end": 1791524837.6702845, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0168, "lo95": 1.016, "mean": 1.0182, "ev_only": 1.017, "ref_ms": 29.7308, "cand_ms": 29.24015, "n_trials": 38, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0393, "r_wall_s": 63.54, "compile_s": 2.47, "r_error": "", "src_len": 2835, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6419, "tout": 1536, "ts": 1791524655.3824422, "chk": "ok", "code_len": 2983}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8067, "tout": 26, "ts": 1791524762.5284853, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8117, "tout": 1358, "ts": 1791524773.399273, "chk": null, "code_len": 2835}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6419, "started": 1791524640.886211}
{"ep": "ok-00580", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.9944, "speedup": 0.9944, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 95.9, "calls": 1, "tokens_in": 1605, "tokens_out": 2281, "ctx_chars": 0, "t_end": 1791524838.1954012, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.9944, "lo95": 0.9933, "mean": 1.0418, "ev_only": 0.9949, "ref_ms": 8.04522, "cand_ms": 8.09065, "n_trials": 157, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0172, "r_wall_s": 76.28, "compile_s": 48.34, "r_error": "", "src_len": 5343, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1605, "tout": 2281, "ts": 1791524761.845688, "chk": null, "code_len": 5343}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1605, "started": 1791524742.2899983}
{"ep": "ok-00552", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.1749, "speedup": 0.1749, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 190.6, "calls": 4, "tokens_in": 27976, "tokens_out": 7516, "ctx_chars": 495, "t_end": 1791524843.7799726, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.1749, "lo95": 0.1743, "mean": 0.1749, "ev_only": 0.1749, "ref_ms": 31.73632, "cand_ms": 181.43165, "n_trials": 12, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.3491, "r_wall_s": 43.93, "compile_s": 11.24, "r_error": "", "src_len": 3725, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2082, "tout": 4053, "ts": 1791524689.2859743, "chk": "compile_error", "code_len": 3817}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7383, "tout": 1714, "ts": 1791524767.713147, "chk": "ok", "code_len": 3725}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9209, "tout": 69, "ts": 1791524785.7050927, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9302, "tout": 1680, "ts": 1791524799.7419305, "chk": null, "code_len": 3725}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 2082, "started": 1791524653.1976888}
{"ep": "ok-00521", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 7.1064, "speedup": 7.1064, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 328.2, "calls": 3, "tokens_in": 24691, "tokens_out": 28853, "ctx_chars": 1495, "t_end": 1791524849.1688032, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.1064, "lo95": 7.077, "mean": 7.663, "ev_only": 7.1909, "ref_ms": 32.05251, "cand_ms": 4.51037, "n_trials": 44, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 47.41, "compile_s": 11.49, "r_error": "", "src_len": 10270, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2464, "tout": 17566, "ts": 1791524675.0726922, "chk": "no_custom_kernel", "code_len": 10322}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8417, "tout": 5751, "ts": 1791524747.493237, "chk": "ok", "code_len": 10270}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13810, "tout": 5536, "ts": 1791524801.6473708, "chk": null, "code_len": 10270}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2464, "started": 1791524520.9626184}
{"ep": "ok-00562", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0136, "speedup": 1.0136, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 168.2, "calls": 3, "tokens_in": 24591, "tokens_out": 7705, "ctx_chars": 12555, "t_end": 1791524857.5589743, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0136, "lo95": 1.0107, "mean": 1.0107, "ev_only": 1.0048, "ref_ms": 8.10655, "cand_ms": 7.99811, "n_trials": 158, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 57.93, "compile_s": 2.09, "r_error": "", "src_len": 1021, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6873, "tout": 2424, "ts": 1791524712.4659262, "chk": "incorrect", "code_len": 1710}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8328, "tout": 4348, "ts": 1791524777.0195446, "chk": "ok", "code_len": 1021}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9390, "tout": 933, "ts": 1791524799.587286, "chk": null, "code_len": 1021}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 6873, "started": 1791524689.373469}
{"ep": "ok-00560", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.0369, "speedup": 0.0369, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 168.8, "calls": 2, "tokens_in": 161526, "tokens_out": 6499, "ctx_chars": 182830, "t_end": 1791524857.6867352, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0369, "lo95": 0.0367, "mean": 0.0369, "ev_only": 0.0368, "ref_ms": 8.33988, "cand_ms": 225.89593, "n_trials": 12, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 63.01, "compile_s": 2.8, "r_error": "", "src_len": 3337, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78367, "tout": 4680, "ts": 1791524734.1348715, "chk": "ok", "code_len": 3337}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 83159, "tout": 1819, "ts": 1791524794.6312153, "chk": null, "code_len": 3337}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78367, "started": 1791524688.8377187}
{"ep": "ok-00574", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0347, "speedup": 1.0347, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 139.9, "calls": 3, "tokens_in": 22058, "tokens_out": 2848, "ctx_chars": 9546, "t_end": 1791524860.2407424, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0347, "lo95": 1.0343, "mean": 1.0346, "ev_only": 1.0335, "ref_ms": 8.21349, "cand_ms": 7.93781, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0049, "r_wall_s": 43.66, "compile_s": 5.59, "r_error": "", "src_len": 1683, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5935, "tout": 1996, "ts": 1791524739.084943, "chk": "ok", "code_len": 1683}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8043, "tout": 13, "ts": 1791524809.819666, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8080, "tout": 839, "ts": 1791524816.5565975, "chk": null, "code_len": 1683}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5935, "started": 1791524720.3154047}
{"ep": "ok-00587", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.8045, "speedup": 0.8045, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 96.1, "calls": 2, "tokens_in": 13553, "tokens_out": 5435, "ctx_chars": 6861, "t_end": 1791524864.3453343, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8045, "lo95": 0.7622, "mean": 0.7979, "ev_only": 0.8045, "ref_ms": 34.93253, "cand_ms": 43.42155, "n_trials": 36, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0326, "r_wall_s": 28.76, "compile_s": 2.61, "r_error": "", "src_len": 3752, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5693, "tout": 3621, "ts": 1791524799.2904778, "chk": "ok", "code_len": 3816}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7860, "tout": 1814, "ts": 1791524835.5594609, "chk": null, "code_len": 3752}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5693, "started": 1791524768.252587}
{"ep": "ok-00599", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0274, "speedup": 1.0274, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 53.7, "calls": 1, "tokens_in": 1856, "tokens_out": 1044, "ctx_chars": 495, "t_end": 1791524866.0231543, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0274, "lo95": 1.027, "mean": 1.0282, "ev_only": 1.0272, "ref_ms": 8.14518, "cand_ms": 7.92768, "n_trials": 175, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0053, "r_wall_s": 43.65, "compile_s": 5.32, "r_error": "", "src_len": 1914, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1856, "tout": 1044, "ts": 1791524822.2842402, "chk": null, "code_len": 1914}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1856, "started": 1791524812.349538}
{"ep": "ok-00592", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0377, "speedup": 1.0377, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 80.9, "calls": 2, "tokens_in": 5133, "tokens_out": 3174, "ctx_chars": 0, "t_end": 1791524871.6241605, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0377, "lo95": 1.0357, "mean": 1.0563, "ev_only": 1.0404, "ref_ms": 8.385, "cand_ms": 8.08025, "n_trials": 127, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0032, "r_wall_s": 40.92, "compile_s": 2.09, "r_error": "", "src_len": 1706, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1802, "tout": 2248, "ts": 1791524810.4869497, "chk": "ok", "code_len": 1706}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3331, "tout": 926, "ts": 1791524830.6762292, "chk": null, "code_len": 1706}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1802, "started": 1791524790.723233}
{"ep": "ok-00463", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 7.2562, "speedup": 7.2562, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 628.5, "calls": 3, "tokens_in": 29811, "tokens_out": 29922, "ctx_chars": 2425, "t_end": 1791524873.9630466, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.2562, "lo95": 7.173, "mean": 8.1959, "ev_only": 7.1986, "ref_ms": 4.10478, "cand_ms": 0.5657, "n_trials": 197, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 93.96, "compile_s": 56.5, "r_error": "", "src_len": 11246, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 17193, "ts": 1791524390.7466335, "chk": "no_custom_kernel", "code_len": 11496}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10122, "tout": 6646, "ts": 1791524622.5215974, "chk": "ok", "code_len": 11246}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16415, "tout": 6083, "ts": 1791524779.953575, "chk": null, "code_len": 11246}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 3274, "started": 1791524245.439978}
{"ep": "ok-00593", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0255, "speedup": 1.0255, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 82.2, "calls": 2, "tokens_in": 4831, "tokens_out": 2591, "ctx_chars": 0, "t_end": 1791524874.233952, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0255, "lo95": 1.0239, "mean": 1.0739, "ev_only": 1.0262, "ref_ms": 8.31153, "cand_ms": 8.1051, "n_trials": 120, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 45.67, "compile_s": 1.98, "r_error": "", "src_len": 1604, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 1707, "ts": 1791524806.895913, "chk": "ok", "code_len": 1604}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3106, "tout": 884, "ts": 1791524828.4523246, "chk": null, "code_len": 1604}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791524792.054532}
{"ep": "ok-00542", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0352, "speedup": 1.0352, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 267.8, "calls": 2, "tokens_in": 6720, "tokens_out": 6701, "ctx_chars": 495, "t_end": 1791524874.79994, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0352, "lo95": 1.0347, "mean": 1.0336, "ev_only": 1.0354, "ref_ms": 29.63903, "cand_ms": 28.63022, "n_trials": 50, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0198, "r_wall_s": 186.6, "compile_s": 22.81, "r_error": "", "src_len": 5214, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1878, "tout": 4188, "ts": 1791524641.762543, "chk": "ok", "code_len": 5214}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4842, "tout": 2513, "ts": 1791524686.8885832, "chk": null, "code_len": 5214}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1878, "started": 1791524606.9765368}
{"ep": "ok-00539", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0007, "speedup": 1.0007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 292.4, "calls": 5, "tokens_in": 31118, "tokens_out": 4510, "ctx_chars": 5534, "t_end": 1791524875.2054627, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0007, "lo95": 0.9976, "mean": 1.0205, "ev_only": 1.001, "ref_ms": 8.08057, "cand_ms": 8.07485, "n_trials": 153, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 44.43, "compile_s": 2.12, "r_error": "", "src_len": 908, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3925, "tout": 616, "ts": 1791524589.3964686, "chk": "incorrect", "code_len": 1085}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4674, "tout": 1804, "ts": 1791524617.4826117, "chk": "incorrect", "code_len": 1027}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6612, "tout": 639, "ts": 1791524640.2846434, "chk": "incorrect", "code_len": 942}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 7385, "tout": 1005, "ts": 1791524796.5589, "chk": "ok", "code_len": 908}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 8522, "tout": 446, "ts": 1791524830.7457366, "chk": null, "code_len": 908}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 3925, "started": 1791524582.8301148}
{"ep": "ok-00566", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0028, "speedup": 1.0028, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 196.1, "calls": 3, "tokens_in": 10481, "tokens_out": 7465, "ctx_chars": 1080, "t_end": 1791524901.3961434, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0028, "lo95": 1.0009, "mean": 1.0066, "ev_only": 1.0041, "ref_ms": 8.04296, "cand_ms": 8.02036, "n_trials": 136, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 58.3, "compile_s": 5.03, "r_error": "", "src_len": 979, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 1872, "ts": 1791524722.2414231, "chk": "incorrect", "code_len": 1681}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3514, "tout": 3454, "ts": 1791524803.241063, "chk": "incorrect", "code_len": 1722}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4849, "tout": 2139, "ts": 1791524843.0708416, "chk": null, "code_len": 979}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", null], "first_tin": 2118, "started": 1791524705.274854}
{"ep": "ok-00588", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0095, "speedup": 1.0095, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 122.9, "calls": 2, "tokens_in": 17742, "tokens_out": 5740, "ctx_chars": 14186, "t_end": 1791524901.4624453, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0095, "lo95": 1.0087, "mean": 1.0359, "ev_only": 1.0081, "ref_ms": 8.0851, "cand_ms": 8.00886, "n_trials": 179, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.01, "r_wall_s": 56.79, "compile_s": 7.66, "r_error": "", "src_len": 4029, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7604, "tout": 3770, "ts": 1791524811.0373406, "chk": "ok", "code_len": 4029}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10138, "tout": 1970, "ts": 1791524844.5286844, "chk": null, "code_len": 4029}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7604, "started": 1791524778.6038718}
{"ep": "ok-00619", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.307, "speedup": 0.307, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 42.3, "calls": 1, "tokens_in": 5329, "tokens_out": 2097, "ctx_chars": 6513, "t_end": 1791524916.5781577, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.307, "lo95": 0.3062, "mean": 0.3066, "ev_only": 0.3058, "ref_ms": 3.43354, "cand_ms": 11.18338, "n_trials": 95, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.077, "r_wall_s": 24.53, "compile_s": 1.93, "r_error": "", "src_len": 4073, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 5329, "tout": 2097, "ts": 1791524891.9380174, "chk": null, "code_len": 4073}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 5329, "started": 1791524874.2342038}
{"ep": "ok-00546", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0046, "speedup": 1.0046, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 294.6, "calls": 4, "tokens_in": 25463, "tokens_out": 8549, "ctx_chars": 5978, "t_end": 1791524922.8850489, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0046, "lo95": 1.0044, "mean": 1.0224, "ev_only": 1.0049, "ref_ms": 7.92086, "cand_ms": 7.88444, "n_trials": 205, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 69.45, "compile_s": 34.83, "r_error": "", "src_len": 1031, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4158, "tout": 2922, "ts": 1791524654.3465326, "chk": "incorrect", "code_len": 2388}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6033, "tout": 3249, "ts": 1791524788.46422, "chk": "incorrect", "code_len": 1112}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7147, "tout": 1448, "ts": 1791524816.1380577, "chk": "ok", "code_len": 1031}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8125, "tout": 930, "ts": 1791524853.406169, "chk": null, "code_len": 1031}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 4158, "started": 1791524628.3220203}
{"ep": "ok-00600", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.8916, "speedup": 0.8916, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 110.9, "calls": 1, "tokens_in": 2489, "tokens_out": 3296, "ctx_chars": 495, "t_end": 1791524924.519373, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8916, "lo95": 0.8902, "mean": 0.8951, "ev_only": 0.8941, "ref_ms": 4.03494, "cand_ms": 4.52536, "n_trials": 147, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0813, "r_wall_s": 78.58, "compile_s": 26.86, "r_error": "", "src_len": 4783, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2489, "tout": 3296, "ts": 1791524845.912509, "chk": null, "code_len": 4783}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2489, "started": 1791524813.6493464}
{"ep": "ok-00571", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.1377, "speedup": 0.1377, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 210.8, "calls": 5, "tokens_in": 33656, "tokens_out": 9598, "ctx_chars": 495, "t_end": 1791524927.2081716, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.1377, "lo95": 0.1369, "mean": 0.138, "ev_only": 0.1376, "ref_ms": 31.81236, "cand_ms": 230.95625, "n_trials": 10, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9621, "r_wall_s": 90.75, "compile_s": 3.44, "r_error": "", "src_len": 2730, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2082, "tout": 3082, "ts": 1791524745.3238244, "chk": "forbidden", "code_len": 2288}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5325, "tout": 1188, "ts": 1791524755.6759725, "chk": "runtime_error", "code_len": 2247}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6932, "tout": 1200, "ts": 1791524771.7910125, "chk": "ok", "code_len": 2281}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8244, "tout": 2694, "ts": 1791524808.9936159, "chk": "ok", "code_len": 2770}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 11073, "tout": 1434, "ts": 1791524836.4353094, "chk": null, "code_len": 2730}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "runtime_error", "ok", "ok", null], "first_tin": 2082, "started": 1791524716.3712518}
{"ep": "ok-00597", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0131, "speedup": 1.0131, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 118.4, "calls": 2, "tokens_in": 17743, "tokens_out": 5560, "ctx_chars": 14186, "t_end": 1791524927.900433, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0131, "lo95": 1.0125, "mean": 1.0131, "ev_only": 1.0123, "ref_ms": 8.10974, "cand_ms": 8.00502, "n_trials": 152, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0075, "r_wall_s": 21.94, "compile_s": 3.23, "r_error": "", "src_len": 3637, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7604, "tout": 3591, "ts": 1791524839.4576828, "chk": "ok", "code_len": 3637}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10139, "tout": 1969, "ts": 1791524905.8665838, "chk": null, "code_len": 3637}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7604, "started": 1791524809.5374053}
{"ep": "ok-00548", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0551, "speedup": 1.0551, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 297.6, "calls": 5, "tokens_in": 62466, "tokens_out": 12340, "ctx_chars": 9125, "t_end": 1791524928.1102464, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0551, "lo95": 0.9729, "mean": 0.9683, "ev_only": 1.0555, "ref_ms": 25.2402, "cand_ms": 23.92177, "n_trials": 36, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0346, "r_wall_s": 29.95, "compile_s": 2.2, "r_error": "", "src_len": 3897, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6570, "tout": 2744, "ts": 1791524653.3325438, "chk": "forbidden", "code_len": 5850}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9616, "tout": 2714, "ts": 1791524675.1743398, "chk": "incorrect", "code_len": 5876}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12463, "tout": 3301, "ts": 1791524798.886025, "chk": "incorrect", "code_len": 6112}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 15898, "tout": 1889, "ts": 1791524872.6919084, "chk": "ok", "code_len": 3897}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 17919, "tout": 1692, "ts": 1791524898.1163304, "chk": null, "code_len": 3897}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "incorrect", "incorrect", "ok", null], "first_tin": 6570, "started": 1791524630.554192}
{"ep": "ok-00512", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8143, "speedup": 0.8143, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 471.0, "calls": 4, "tokens_in": 350237, "tokens_out": 20111, "ctx_chars": 182830, "t_end": 1791524929.6878743, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8143, "lo95": 0.8126, "mean": 0.8266, "ev_only": 0.8183, "ref_ms": 8.07168, "cand_ms": 9.91273, "n_trials": 128, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9996, "r_wall_s": 53.54, "compile_s": 1.82, "r_error": "", "src_len": 6936, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78172, "tout": 8451, "ts": 1791524532.90341, "chk": "incorrect", "code_len": 7036}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 86756, "tout": 3744, "ts": 1791524750.790599, "chk": "ok", "code_len": 7045}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 90612, "tout": 3973, "ts": 1791524806.283241, "chk": "ok", "code_len": 6936}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 94697, "tout": 3943, "ts": 1791524875.9598432, "chk": null, "code_len": 6936}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "ok", null], "first_tin": 78172, "started": 1791524458.7056773}
{"ep": "ok-00573", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0995, "speedup": 1.0995, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 211.3, "calls": 3, "tokens_in": 25401, "tokens_out": 2063, "ctx_chars": 12888, "t_end": 1791524931.494584, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0995, "lo95": 1.0988, "mean": 1.099, "ev_only": 1.0983, "ref_ms": 22.31492, "cand_ms": 20.2959, "n_trials": 63, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0327, "r_wall_s": 39.25, "compile_s": 1.91, "r_error": "", "src_len": 2110, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7684, "tout": 1044, "ts": 1791524730.1393137, "chk": "ok", "code_len": 2110}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8840, "tout": 13, "ts": 1791524883.4829412, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8877, "tout": 1006, "ts": 1791524891.9629445, "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": 7684, "started": 1791524720.2122266}
{"ep": "ok-00605", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.008, "speedup": 1.008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 115.3, "calls": 2, "tokens_in": 12093, "tokens_out": 5234, "ctx_chars": 7261, "t_end": 1791524935.3113437, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.008, "lo95": 1.0073, "mean": 1.0079, "ev_only": 1.007, "ref_ms": 8.10094, "cand_ms": 8.03671, "n_trials": 147, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0088, "r_wall_s": 30.76, "compile_s": 3.35, "r_error": "", "src_len": 3660, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4818, "tout": 3343, "ts": 1791524849.035981, "chk": "ok", "code_len": 3660}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7275, "tout": 1891, "ts": 1791524904.453839, "chk": null, "code_len": 3660}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4818, "started": 1791524820.0194964}
{"ep": "ok-00577", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.101, "speedup": 1.101, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 203.7, "calls": 1, "tokens_in": 8863, "tokens_out": 1099, "ctx_chars": 16078, "t_end": 1791524938.751002, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.101, "lo95": 1.0923, "mean": 1.0948, "ev_only": 1.0985, "ref_ms": 22.4477, "cand_ms": 20.38806, "n_trials": 58, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0402, "r_wall_s": 193.35, "compile_s": 26.33, "r_error": "", "src_len": 2159, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 8863, "tout": 1099, "ts": 1791524745.1975195, "chk": null, "code_len": 2159}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 8863, "started": 1791524735.097488}
{"ep": "ok-00555", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9567, "speedup": 0.9567, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 285.0, "calls": 3, "tokens_in": 22779, "tokens_out": 8756, "ctx_chars": 2169, "t_end": 1791524942.5391495, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9567, "lo95": 0.9554, "mean": 0.944, "ev_only": 0.9572, "ref_ms": 4.10727, "cand_ms": 4.29299, "n_trials": 208, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0851, "r_wall_s": 98.82, "compile_s": 71.14, "r_error": "", "src_len": 4353, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3083, "tout": 6622, "ts": 1791524713.0987883, "chk": "ok", "code_len": 4353}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9817, "tout": 38, "ts": 1791524826.2337055, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9879, "tout": 2096, "ts": 1791524843.6931539, "chk": null, "code_len": 4353}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3083, "started": 1791524657.5113566}
{"ep": "ok-00536", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 3.667, "speedup": 3.667, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 382.1, "calls": 2, "tokens_in": 14031, "tokens_out": 25447, "ctx_chars": 2425, "t_end": 1791524944.1789477, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 3.667, "lo95": 3.6586, "mean": 3.6091, "ev_only": 3.7014, "ref_ms": 4.02927, "cand_ms": 1.09878, "n_trials": 197, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 93.92, "compile_s": 42.15, "r_error": "", "src_len": 13575, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3274, "tout": 18586, "ts": 1791524722.1348844, "chk": "ok", "code_len": 13575}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10757, "tout": 6861, "ts": 1791524850.2229617, "chk": null, "code_len": 13575}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3274, "started": 1791524562.1083407}
{"ep": "ok-00570", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 4.8126, "speedup": 4.8126, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.5, "calls": 2, "tokens_in": 10408, "tokens_out": 19790, "ctx_chars": 0, "t_end": 1791524951.9294963, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 4.8126, "lo95": 4.5752, "mean": 4.8828, "ev_only": 4.9109, "ref_ms": 5.81512, "cand_ms": 1.20831, "n_trials": 211, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0154, "r_wall_s": 36.58, "compile_s": 14.12, "r_error": "", "src_len": 9670, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 14612, "ts": 1791524840.2917118, "chk": "ok", "code_len": 9670}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8050, "tout": 5178, "ts": 1791524915.3058243, "chk": null, "code_len": 9670}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2358, "started": 1791524714.422494}
{"ep": "ok-00608", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0151, "speedup": 1.0151, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 114.3, "calls": 2, "tokens_in": 11689, "tokens_out": 4503, "ctx_chars": 7261, "t_end": 1791524951.9481337, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0151, "lo95": 1.0146, "mean": 1.014, "ev_only": 1.0131, "ref_ms": 8.10728, "cand_ms": 7.98662, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0066, "r_wall_s": 21.58, "compile_s": 2.25, "r_error": "", "src_len": 2975, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4818, "tout": 2986, "ts": 1791524863.5864253, "chk": "ok", "code_len": 2975}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6871, "tout": 1517, "ts": 1791524929.7853444, "chk": null, "code_len": 2975}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4818, "started": 1791524837.6705513}
{"ep": "ok-00559", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.7757, "speedup": 0.7757, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 274.7, "calls": 2, "tokens_in": 163386, "tokens_out": 14930, "ctx_chars": 182830, "t_end": 1791524961.1669924, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.7757, "lo95": 0.7709, "mean": 0.776, "ev_only": 0.7759, "ref_ms": 3.43147, "cand_ms": 4.42352, "n_trials": 155, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.103, "r_wall_s": 62.52, "compile_s": 53.38, "r_error": "", "src_len": 8918, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79195, "tout": 10079, "ts": 1791524795.362202, "chk": "ok", "code_len": 8918}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 84191, "tout": 4851, "ts": 1791524898.608167, "chk": null, "code_len": 8918}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79195, "started": 1791524707.008328}
{"ep": "ok-00598", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0327, "speedup": 1.0327, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 152.4, "calls": 2, "tokens_in": 13199, "tokens_out": 2536, "ctx_chars": 9546, "t_end": 1791524963.8361616, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0327, "lo95": 1.0313, "mean": 1.0407, "ev_only": 1.0355, "ref_ms": 8.28543, "cand_ms": 8.02287, "n_trials": 177, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0037, "r_wall_s": 26.05, "compile_s": 1.89, "r_error": "", "src_len": 1585, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5937, "tout": 1652, "ts": 1791524826.35719, "chk": "ok", "code_len": 1585}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7262, "tout": 884, "ts": 1791524937.7478287, "chk": null, "code_len": 1585}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5937, "started": 1791524811.4100916}
{"ep": "ok-00582", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.8229, "speedup": 0.8229, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.7, "calls": 3, "tokens_in": 10555, "tokens_out": 1937, "ctx_chars": 2270, "t_end": 1791524964.6071875, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8229, "lo95": 0.8204, "mean": 0.8479, "ev_only": 0.8227, "ref_ms": 32.79528, "cand_ms": 39.85547, "n_trials": 26, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0001, "r_wall_s": 154.43, "compile_s": 17.39, "r_error": "", "src_len": 1514, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2738, "tout": 884, "ts": 1791524777.1342597, "chk": "ok", "code_len": 1514}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3731, "tout": 331, "ts": 1791524803.5372405, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4086, "tout": 722, "ts": 1791524810.1511233, "chk": null, "code_len": 1514}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 2738, "started": 1791524767.2383456}
{"ep": "ok-00581", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.4902, "speedup": 1.4902, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 220.8, "calls": 3, "tokens_in": 14062, "tokens_out": 11533, "ctx_chars": 495, "t_end": 1791524964.7860847, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4902, "lo95": 1.4896, "mean": 1.4895, "ev_only": 1.4897, "ref_ms": 8.21105, "cand_ms": 5.51019, "n_trials": 178, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 41.81, "compile_s": 2.33, "r_error": "", "src_len": 3929, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1935, "tout": 6310, "ts": 1791524801.6236575, "chk": "incorrect", "code_len": 4013}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4853, "tout": 2774, "ts": 1791524887.7512264, "chk": "ok", "code_len": 3929}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7274, "tout": 2449, "ts": 1791524922.8699489, "chk": null, "code_len": 3929}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1935, "started": 1791524743.982026}
{"ep": "ok-00629", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0991, "speedup": 1.0991, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 43.9, "calls": 1, "tokens_in": 1960, "tokens_out": 1288, "ctx_chars": 495, "t_end": 1791524971.971064, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0991, "lo95": 1.0978, "mean": 1.0981, "ev_only": 1.0989, "ref_ms": 22.31316, "cand_ms": 20.30194, "n_trials": 64, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0381, "r_wall_s": 31.3, "compile_s": 1.93, "r_error": "", "src_len": 2374, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1960, "tout": 1288, "ts": 1791524940.326529, "chk": null, "code_len": 2374}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1960, "started": 1791524928.1105325}
{"ep": "ok-00610", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 105.936, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 133.0, "calls": 2, "tokens_in": 8223, "tokens_out": 7281, "ctx_chars": 2256, "t_end": 1791524976.7978086, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 105.936, "lo95": 105.2707, "mean": 102.6058, "ev_only": 106.2468, "ref_ms": 22.25244, "cand_ms": 0.21006, "n_trials": 60, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 52.83, "compile_s": 17.64, "r_error": "", "src_len": 4628, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2666, "tout": 5025, "ts": 1791524886.900008, "chk": "ok", "code_len": 4628}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5557, "tout": 2256, "ts": 1791524923.6310508, "chk": null, "code_len": 4628}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2666, "started": 1791524843.7802413}
{"ep": "ok-00578", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.5105, "speedup": 0.5105, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 240.6, "calls": 2, "tokens_in": 9331, "tokens_out": 10166, "ctx_chars": 0, "t_end": 1791524978.6055415, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.5105, "lo95": 0.486, "mean": 0.6013, "ev_only": 0.5078, "ref_ms": 3.5956, "cand_ms": 7.04317, "n_trials": 149, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3424, "r_wall_s": 117.37, "compile_s": 39.75, "r_error": "", "src_len": 6482, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 6698, "ts": 1791524795.8062806, "chk": "ok", "code_len": 6482}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6703, "tout": 3468, "ts": 1791524861.2082381, "chk": null, "code_len": 6482}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791524737.984662}
{"ep": "ok-00591", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 75.9658, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 194.9, "calls": 2, "tokens_in": 6797, "tokens_out": 7411, "ctx_chars": 0, "t_end": 1791524980.4486532, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 75.9658, "lo95": 73.6609, "mean": 72.3016, "ev_only": 75.8785, "ref_ms": 22.30599, "cand_ms": 0.29363, "n_trials": 72, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 51.98, "compile_s": 16.06, "r_error": "", "src_len": 4828, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1829, "tout": 4928, "ts": 1791524827.9441175, "chk": "ok", "code_len": 4828}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4968, "tout": 2483, "ts": 1791524928.1351557, "chk": null, "code_len": 4828}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1829, "started": 1791524785.5863469}
{"ep": "ok-00572", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0044, "speedup": 1.0044, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 271.1, "calls": 3, "tokens_in": 9234, "tokens_out": 7118, "ctx_chars": 0, "t_end": 1791524989.280889, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0044, "lo95": 1.0023, "mean": 1.0341, "ev_only": 1.0055, "ref_ms": 8.02508, "cand_ms": 7.98957, "n_trials": 161, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 29.04, "compile_s": 2.6, "r_error": "", "src_len": 932, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 2346, "ts": 1791524739.5762286, "chk": "incorrect", "code_len": 2037}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3244, "tout": 3716, "ts": 1791524864.899872, "chk": "ok", "code_len": 932}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4307, "tout": 1056, "ts": 1791524960.195188, "chk": null, "code_len": 932}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1683, "started": 1791524718.2307417}
{"ep": "ok-00564", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.0443, "speedup": 0.0443, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 292.8, "calls": 2, "tokens_in": 167281, "tokens_out": 12899, "ctx_chars": 182830, "t_end": 1791524991.1678853, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.0443, "lo95": 0.0439, "mean": 0.0444, "ev_only": 0.0443, "ref_ms": 31.75341, "cand_ms": 716.08059, "n_trials": 10, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9989, "r_wall_s": 82.23, "compile_s": 51.81, "r_error": "", "src_len": 4761, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78516, "tout": 10137, "ts": 1791524795.314295, "chk": "ok", "code_len": 4761}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 88765, "tout": 2762, "ts": 1791524908.8287535, "chk": null, "code_len": 4761}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78516, "started": 1791524698.3813174}
{"ep": "ok-00585", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0011, "speedup": 1.0011, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 239.1, "calls": 5, "tokens_in": 25062, "tokens_out": 8902, "ctx_chars": 1080, "t_end": 1791524992.1631641, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0011, "lo95": 0.9979, "mean": 1.0035, "ev_only": 1.0027, "ref_ms": 8.01348, "cand_ms": 8.00459, "n_trials": 147, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 40.24, "compile_s": 2.06, "r_error": "", "src_len": 968, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 2215, "ts": 1791524771.857742, "chk": "incorrect", "code_len": 2059}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3751, "tout": 2483, "ts": 1791524813.4626155, "chk": "incorrect", "code_len": 2118}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5364, "tout": 1866, "ts": 1791524871.8386846, "chk": "incorrect", "code_len": 1086}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 6419, "tout": 1615, "ts": 1791524896.6057386, "chk": "ok", "code_len": 968}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7410, "tout": 723, "ts": 1791524951.8819187, "chk": null, "code_len": 968}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 2118, "started": 1791524753.0753703}
{"ep": "ok-00586", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7035, "speedup": 0.7035, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 237.9, "calls": 5, "tokens_in": 58920, "tokens_out": 11423, "ctx_chars": 7010, "t_end": 1791524994.6555123, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.7035, "lo95": 0.6354, "mean": 0.7888, "ev_only": 0.7033, "ref_ms": 27.36217, "cand_ms": 38.89298, "n_trials": 36, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0543, "r_wall_s": 36.97, "compile_s": 2.07, "r_error": "", "src_len": 4394, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5751, "tout": 3249, "ts": 1791524783.6809292, "chk": "incorrect", "code_len": 6360}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9133, "tout": 3715, "ts": 1791524824.7061486, "chk": "incorrect", "code_len": 6781}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12982, "tout": 2380, "ts": 1791524866.035691, "chk": "ok", "code_len": 4394}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 15471, "tout": 65, "ts": 1791524941.5554128, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 15583, "tout": 2014, "ts": 1791524957.638141, "chk": null, "code_len": 4394}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5751, "started": 1791524756.7254114}
{"ep": "ok-00576", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.023, "speedup": 1.023, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 268.0, "calls": 3, "tokens_in": 28974, "tokens_out": 2924, "ctx_chars": 15603, "t_end": 1791524996.5328336, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.023, "lo95": 1.0226, "mean": 1.0231, "ev_only": 1.0234, "ref_ms": 29.74359, "cand_ms": 29.07626, "n_trials": 37, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.034, "r_wall_s": 136.86, "compile_s": 38.45, "r_error": "", "src_len": 2630, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8528, "tout": 1535, "ts": 1791524742.5157182, "chk": "ok", "code_len": 2812}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10175, "tout": 72, "ts": 1791524848.1327052, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10271, "tout": 1317, "ts": 1791524859.179587, "chk": null, "code_len": 2630}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 8528, "started": 1791524728.4918892}
{"ep": "ok-00569", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.7471, "speedup": 0.7471, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 293.3, "calls": 2, "tokens_in": 13675, "tokens_out": 7023, "ctx_chars": 5888, "t_end": 1791525000.4404693, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7471, "lo95": 0.7437, "mean": 0.7483, "ev_only": 0.7471, "ref_ms": 16.12742, "cand_ms": 21.58528, "n_trials": 55, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0175, "r_wall_s": 147.23, "compile_s": 31.87, "r_error": "", "src_len": 5130, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5353, "tout": 4536, "ts": 1791524746.4918866, "chk": "ok", "code_len": 5130}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8322, "tout": 2487, "ts": 1791524853.1723356, "chk": null, "code_len": 5130}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5353, "started": 1791524707.1545732}
{"ep": "ok-00553", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7487, "speedup": 0.7487, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 349.1, "calls": 3, "tokens_in": 28684, "tokens_out": 10079, "ctx_chars": 6513, "t_end": 1791525002.4539495, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7487, "lo95": 0.7475, "mean": 0.7484, "ev_only": 0.7487, "ref_ms": 16.28339, "cand_ms": 21.74819, "n_trials": 43, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.04, "r_wall_s": 131.35, "compile_s": 43.89, "r_error": "", "src_len": 3789, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 3135, "ts": 1791524679.8235443, "chk": "incorrect", "code_len": 6294}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8888, "tout": 5179, "ts": 1791524802.8497427, "chk": "ok", "code_len": 3789}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14176, "tout": 1765, "ts": 1791524871.0560179, "chk": null, "code_len": 3789}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5620, "started": 1791524653.3536925}
{"ep": "ok-00502", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 6.3316, "speedup": 6.3316, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 594.2, "calls": 3, "tokens_in": 25062, "tokens_out": 20452, "ctx_chars": 2713, "t_end": 1791525010.9393122, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 6.3316, "lo95": 6.3257, "mean": 6.3291, "ev_only": 6.2908, "ref_ms": 4.02062, "cand_ms": 0.63501, "n_trials": 193, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.8717, "r_wall_s": 150.39, "compile_s": 86.76, "r_error": "", "src_len": 9467, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3326, "tout": 10725, "ts": 1791524507.1383367, "chk": "no_custom_kernel", "code_len": 9468}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8459, "tout": 5159, "ts": 1791524769.5205936, "chk": "ok", "code_len": 9467}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13277, "tout": 4568, "ts": 1791524860.5231352, "chk": null, "code_len": 9467}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 3326, "started": 1791524416.6954012}
{"ep": "ok-00647", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 25.6, "calls": 1, "tokens_in": 1814, "tokens_out": 1982, "ctx_chars": 495, "t_end": 1791525016.7661438, "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": 0.1252, "r_wall_s": 7.29, "compile_s": 1.89, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1145, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1814, "tout": 1982, "ts": 1791525009.3756711, "chk": null, "code_len": 1145}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1814, "started": 1791524991.1681576}
{"ep": "ok-00596", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7862, "speedup": 0.7862, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 212.4, "calls": 2, "tokens_in": 13358, "tokens_out": 5780, "ctx_chars": 6861, "t_end": 1791525019.7407217, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7862, "lo95": 0.7845, "mean": 0.7937, "ev_only": 0.786, "ref_ms": 3.33839, "cand_ms": 4.24651, "n_trials": 192, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0031, "r_wall_s": 12.31, "compile_s": 1.87, "r_error": "", "src_len": 3953, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5402, "tout": 3685, "ts": 1791524859.02237, "chk": "ok", "code_len": 3953}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7956, "tout": 2095, "ts": 1791525007.4134529, "chk": null, "code_len": 3953}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5402, "started": 1791524827.663305}
{"ep": "ok-00496", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 6.7965, "speedup": 6.7965, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 641.5, "calls": 3, "tokens_in": 21324, "tokens_out": 23756, "ctx_chars": 1495, "t_end": 1791525023.3372273, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 6.7965, "lo95": 6.7464, "mean": 7.5794, "ev_only": 6.8582, "ref_ms": 31.87176, "cand_ms": 4.68941, "n_trials": 29, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9995, "r_wall_s": 226.99, "compile_s": 18.62, "r_error": "", "src_len": 7668, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2464, "tout": 14737, "ts": 1791524512.562771, "chk": "no_custom_kernel", "code_len": 7561}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7242, "tout": 4911, "ts": 1791524649.1093745, "chk": "ok", "code_len": 7668}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11618, "tout": 4108, "ts": 1791524796.3213832, "chk": null, "code_len": 7668}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2464, "started": 1791524381.8545926}
{"ep": "ok-00514", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.6484, "speedup": 0.6484, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 549.1, "calls": 3, "tokens_in": 244465, "tokens_out": 12594, "ctx_chars": 182830, "t_end": 1791525026.5741494, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.6484, "lo95": 0.6433, "mean": 0.6484, "ev_only": 0.6485, "ref_ms": 8.25923, "cand_ms": 12.73819, "n_trials": 116, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 208.83, "compile_s": 6.2, "r_error": "", "src_len": 4508, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78369, "tout": 4970, "ts": 1791524521.4581223, "chk": "incorrect", "code_len": 4366}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81554, "tout": 4622, "ts": 1791524660.460179, "chk": "ok", "code_len": 4508}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 84542, "tout": 3002, "ts": 1791524817.713498, "chk": null, "code_len": 4508}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78369, "started": 1791524477.4728377}
{"ep": "ok-00609", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0008, "speedup": 1.0008, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 199.3, "calls": 2, "tokens_in": 12092, "tokens_out": 5219, "ctx_chars": 7261, "t_end": 1791525037.5333037, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0008, "lo95": 0.9992, "mean": 1.0218, "ev_only": 1.0025, "ref_ms": 8.16011, "cand_ms": 8.15383, "n_trials": 145, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0087, "r_wall_s": 67.5, "compile_s": 5.72, "r_error": "", "src_len": 3736, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4818, "tout": 3429, "ts": 1791524867.7426898, "chk": "ok", "code_len": 3736}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7274, "tout": 1790, "ts": 1791524969.8898206, "chk": null, "code_len": 3736}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4818, "started": 1791524838.1956363}
{"ep": "ok-00655", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 19.0, "calls": 1, "tokens_in": 1681, "tokens_out": 698, "ctx_chars": 0, "t_end": 1791525038.7000918, "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": 0.1171, "r_wall_s": 11.58, "compile_s": 3.22, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 1182, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1681, "tout": 698, "ts": 1791525027.075299, "chk": null, "code_len": 1182}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1681, "started": 1791525019.7411733}
{"ep": "ok-00618", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 40.1287, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 167.2, "calls": 2, "tokens_in": 15564, "tokens_out": 7046, "ctx_chars": 10255, "t_end": 1791525041.2064376, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 40.1287, "lo95": 39.4324, "mean": 44.5981, "ev_only": 42.8878, "ref_ms": 22.34416, "cand_ms": 0.55681, "n_trials": 60, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 1.0, "r_wall_s": 69.51, "compile_s": 15.09, "r_error": "", "src_len": 4040, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6434, "tout": 4956, "ts": 1791524918.4878194, "chk": "ok", "code_len": 4040}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9130, "tout": 2090, "ts": 1791524971.4693255, "chk": null, "code_len": 4040}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6434, "started": 1791524873.9635427}
{"ep": "ok-00561", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 8.7859, "speedup": 8.7859, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 357.8, "calls": 3, "tokens_in": 20818, "tokens_out": 21348, "ctx_chars": 696, "t_end": 1791525046.786107, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 8.7859, "lo95": 8.5534, "mean": 8.519, "ev_only": 8.8659, "ref_ms": 43.86213, "cand_ms": 4.99233, "n_trials": 34, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9949, "r_wall_s": 35.0, "compile_s": 11.66, "r_error": "", "src_len": 8115, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2199, "tout": 12669, "ts": 1791524799.3478208, "chk": "no_custom_kernel", "code_len": 8139}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7115, "tout": 4531, "ts": 1791524855.238558, "chk": "ok", "code_len": 8115}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11504, "tout": 4148, "ts": 1791525011.7355247, "chk": null, "code_len": 8115}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2199, "started": 1791524688.9519193}
{"ep": "ok-00642", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0114, "speedup": 1.0114, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 74.9, "calls": 2, "tokens_in": 12025, "tokens_out": 5274, "ctx_chars": 7549, "t_end": 1791525046.82791, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0114, "lo95": 1.0109, "mean": 1.0118, "ev_only": 1.0114, "ref_ms": 8.09639, "cand_ms": 8.00476, "n_trials": 201, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0092, "r_wall_s": 23.37, "compile_s": 2.43, "r_error": "", "src_len": 3302, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4870, "tout": 3502, "ts": 1791525002.073741, "chk": "ok", "code_len": 3302}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7155, "tout": 1772, "ts": 1791525023.170037, "chk": null, "code_len": 3302}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4870, "started": 1791524971.971372}
{"ep": "ok-00611", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.8911, "speedup": 0.8911, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 198.4, "calls": 3, "tokens_in": 20044, "tokens_out": 13350, "ctx_chars": 0, "t_end": 1791525047.542696, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8911, "lo95": 0.8889, "mean": 0.8953, "ev_only": 0.8912, "ref_ms": 16.363, "cand_ms": 18.36299, "n_trials": 65, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.034, "r_wall_s": 17.9, "compile_s": 1.87, "r_error": "", "src_len": 3850, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 8435, "ts": 1791524920.8959134, "chk": "incorrect", "code_len": 7964}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7504, "tout": 3068, "ts": 1791524971.0790012, "chk": "ok", "code_len": 3850}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9621, "tout": 1847, "ts": 1791525029.6219642, "chk": null, "code_len": 3850}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2919, "started": 1791524849.1690764}
{"ep": "ok-00604", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.4947, "speedup": 1.4947, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 230.8, "calls": 2, "tokens_in": 6773, "tokens_out": 9043, "ctx_chars": 0, "t_end": 1791525049.561861, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.4947, "lo95": 1.4941, "mean": 1.5003, "ev_only": 1.497, "ref_ms": 8.03866, "cand_ms": 5.37804, "n_trials": 218, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9995, "r_wall_s": 27.35, "compile_s": 1.91, "r_error": "", "src_len": 5479, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1607, "tout": 5551, "ts": 1791524864.6327803, "chk": "ok", "code_len": 5479}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5166, "tout": 3492, "ts": 1791525022.052856, "chk": null, "code_len": 5479}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1607, "started": 1791524818.7416344}
{"ep": "ok-00621", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0038, "speedup": 1.0038, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 176.2, "calls": 5, "tokens_in": 35838, "tokens_out": 9395, "ctx_chars": 5630, "t_end": 1791525051.4182909, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0038, "lo95": 1.0036, "mean": 1.0045, "ev_only": 1.0046, "ref_ms": 7.96162, "cand_ms": 7.93133, "n_trials": 191, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 17.47, "compile_s": 1.89, "r_error": "", "src_len": 964, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4087, "tout": 2577, "ts": 1791524898.487674, "chk": "incorrect", "code_len": 2601}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5939, "tout": 3571, "ts": 1791524968.2303681, "chk": "incorrect", "code_len": 2646}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7683, "tout": 1289, "ts": 1791524997.7075212, "chk": "incorrect", "code_len": 1070}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8607, "tout": 1352, "ts": 1791525019.0429413, "chk": "ok", "code_len": 964}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9522, "tout": 606, "ts": 1791525033.921281, "chk": null, "code_len": 964}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 4087, "started": 1791524875.205713}
{"ep": "ok-00623", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0248, "speedup": 1.0248, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 153.4, "calls": 3, "tokens_in": 20116, "tokens_out": 1893, "ctx_chars": 9950, "t_end": 1791525054.8353658, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0248, "lo95": 1.0243, "mean": 1.0674, "ev_only": 1.0258, "ref_ms": 8.15482, "cand_ms": 7.95733, "n_trials": 163, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0044, "r_wall_s": 108.07, "compile_s": 2.29, "r_error": "", "src_len": 1866, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5980, "tout": 932, "ts": 1791524910.1503136, "chk": "ok", "code_len": 1866}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7024, "tout": 64, "ts": 1791524938.8748002, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7112, "tout": 897, "ts": 1791524946.6858907, "chk": null, "code_len": 1866}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5980, "started": 1791524901.4627326}
{"ep": "ok-00590", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9237, "speedup": 0.9237, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 272.5, "calls": 3, "tokens_in": 13312, "tokens_out": 5886, "ctx_chars": 495, "t_end": 1791525056.193924, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9237, "lo95": 0.9162, "mean": 0.8724, "ev_only": 0.9254, "ref_ms": 4.04595, "cand_ms": 4.38, "n_trials": 218, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0931, "r_wall_s": 110.52, "compile_s": 53.04, "r_error": "", "src_len": 4176, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2489, "tout": 1716, "ts": 1791524802.2857049, "chk": "forbidden", "code_len": 118}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4305, "tout": 2101, "ts": 1791524819.3767161, "chk": "ok", "code_len": 4225}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6518, "tout": 2069, "ts": 1791524945.626451, "chk": null, "code_len": 4176}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", null], "first_tin": 2489, "started": 1791524783.7005155}
{"ep": "ok-00638", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0976, "speedup": 1.0976, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 98.5, "calls": 3, "tokens_in": 24211, "tokens_out": 2104, "ctx_chars": 12121, "t_end": 1791525059.6703544, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0976, "lo95": 1.0925, "mean": 1.0954, "ev_only": 1.0976, "ref_ms": 22.31807, "cand_ms": 20.33369, "n_trials": 50, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0328, "r_wall_s": 42.55, "compile_s": 1.86, "r_error": "", "src_len": 2114, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7260, "tout": 1085, "ts": 1791524971.3319113, "chk": "ok", "code_len": 2114}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8457, "tout": 13, "ts": 1791525008.0478756, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8494, "tout": 1006, "ts": 1791525016.852129, "chk": null, "code_len": 2114}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7260, "started": 1791524961.1673152}
{"ep": "ok-00613", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.9985, "speedup": 0.9985, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 204.4, "calls": 5, "tokens_in": 32377, "tokens_out": 4359, "ctx_chars": 6127, "t_end": 1791525062.089153, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9985, "lo95": 0.9983, "mean": 0.9986, "ev_only": 0.9989, "ref_ms": 7.95669, "cand_ms": 7.96871, "n_trials": 139, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 13.23, "compile_s": 1.89, "r_error": "", "src_len": 883, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4216, "tout": 877, "ts": 1791524867.2400196, "chk": "incorrect", "code_len": 1174}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5226, "tout": 1074, "ts": 1791524997.981906, "chk": "incorrect", "code_len": 1186}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6433, "tout": 1257, "ts": 1791525021.149515, "chk": "incorrect", "code_len": 1047}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 7824, "tout": 722, "ts": 1791525036.9731135, "chk": "ok", "code_len": 883}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 8678, "tout": 429, "ts": 1791525048.8339837, "chk": null, "code_len": 883}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 4216, "started": 1791524857.6870704}
{"ep": "ok-00631", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.6554, "speedup": 0.6554, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 133.7, "calls": 2, "tokens_in": 16019, "tokens_out": 10255, "ctx_chars": 9125, "t_end": 1791525065.2302332, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.6554, "lo95": 0.6523, "mean": 0.6589, "ev_only": 0.6529, "ref_ms": 3.48625, "cand_ms": 5.31949, "n_trials": 176, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3761, "r_wall_s": 36.79, "compile_s": 3.33, "r_error": "", "src_len": 5724, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6281, "tout": 7338, "ts": 1791524997.372897, "chk": "ok", "code_len": 5724}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9738, "tout": 2917, "ts": 1791525028.3921313, "chk": null, "code_len": 5724}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6281, "started": 1791524931.4949336}
{"ep": "ok-00637", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "no_custom_kernel", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 115.2, "calls": 1, "tokens_in": 2917, "tokens_out": 5377, "ctx_chars": 0, "t_end": 1791525067.1823332, "error": "none of the candidate's kernels ['_add_relu_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-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": 0.0, "r_wall_s": 71.36, "compile_s": 39.18, "r_error": "none of the candidate's kernels ['_add_relu_kernel', '_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "src_len": 6131, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 2917, "tout": 5377, "ts": 1791524995.7750516, "chk": null, "code_len": 6131}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 2917, "started": 1791524951.9483416}
{"ep": "ok-00606", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9983, "speedup": 0.9983, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 249.0, "calls": 5, "tokens_in": 36767, "tokens_out": 3621, "ctx_chars": 9192, "t_end": 1791525069.2649636, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9983, "lo95": 0.9979, "mean": 0.9982, "ev_only": 0.999, "ref_ms": 7.92211, "cand_ms": 7.9355, "n_trials": 138, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 18.2, "compile_s": 2.68, "r_error": "", "src_len": 940, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 641, "ts": 1791524827.122922, "chk": "incorrect", "code_len": 1119}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6405, "tout": 855, "ts": 1791524899.2583132, "chk": "incorrect", "code_len": 1023}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7393, "tout": 675, "ts": 1791524951.2535267, "chk": "incorrect", "code_len": 1095}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8201, "tout": 804, "ts": 1791524985.5998983, "chk": "ok", "code_len": 940}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9137, "tout": 646, "ts": 1791525050.9583387, "chk": null, "code_len": 940}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 5631, "started": 1791524820.3006494}
{"ep": "ok-00602", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8268, "speedup": 0.8268, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 259.7, "calls": 2, "tokens_in": 161806, "tokens_out": 6480, "ctx_chars": 182830, "t_end": 1791525076.9236763, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.8268, "lo95": 0.824, "mean": 0.8322, "ev_only": 0.8221, "ref_ms": 3.44082, "cand_ms": 4.16183, "n_trials": 230, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0117, "r_wall_s": 116.17, "compile_s": 59.23, "r_error": "", "src_len": 5912, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79193, "tout": 3311, "ts": 1791524847.6436453, "chk": "ok", "code_len": 5912}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82613, "tout": 3169, "ts": 1791524960.7139852, "chk": null, "code_len": 5912}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79193, "started": 1791524817.2262342}
{"ep": "ok-00645", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 98.0, "calls": 1, "tokens_in": 1681, "tokens_out": 1148, "ctx_chars": 0, "t_end": 1791525078.4322453, "error": "RuntimeError: Error building extension 'gemv_sum_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemv_sum_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "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": 86.54, "compile_s": 86.53, "r_error": "RuntimeError: Error building extension 'gemv_sum_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemv_sum_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/lo", "src_len": 2254, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1681, "tout": 1148, "ts": 1791524991.3506868, "chk": null, "code_len": 2254}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1681, "started": 1791524980.4489508}
{"ep": "ok-00517", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 5.5018, "speedup": 5.5018, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 573.1, "calls": 3, "tokens_in": 28331, "tokens_out": 34080, "ctx_chars": 369, "t_end": 1791525078.703284, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 5.5018, "lo95": 5.4794, "mean": 5.4927, "ev_only": 5.5866, "ref_ms": 4.01151, "cand_ms": 0.72913, "n_trials": 192, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 88.37, "compile_s": 44.46, "r_error": "", "src_len": 11285, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2478, "tout": 20573, "ts": 1791524685.094824, "chk": "no_custom_kernel", "code_len": 11355}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9580, "tout": 7143, "ts": 1791524846.7374372, "chk": "ok", "code_len": 11285}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 16273, "tout": 6364, "ts": 1791524990.2915149, "chk": null, "code_len": 11285}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2478, "started": 1791524505.621275}
{"ep": "ok-00656", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "compile_error", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 65.2, "calls": 1, "tokens_in": 1814, "tokens_out": 1256, "ctx_chars": 495, "t_end": 1791525088.570481, "error": "RuntimeError: Error building extension 'gemv_divsum': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemv_divsum -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "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": 52.78, "compile_s": 52.77, "r_error": "RuntimeError: Error building extension 'gemv_divsum': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemv_divsum -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/loca", "src_len": 2271, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1814, "tout": 1256, "ts": 1791525035.7649803, "chk": null, "code_len": 2271}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1814, "started": 1791525023.3376548}
{"ep": "ok-00607", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.4096, "speedup": 1.4096, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 275.9, "calls": 2, "tokens_in": 7118, "tokens_out": 9630, "ctx_chars": 495, "t_end": 1791525103.877298, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.4096, "lo95": 1.4092, "mean": 1.4086, "ev_only": 1.4081, "ref_ms": 8.03569, "cand_ms": 5.70075, "n_trials": 196, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9974, "r_wall_s": 41.03, "compile_s": 4.95, "r_error": "", "src_len": 5935, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1740, "tout": 6086, "ts": 1791524879.62892, "chk": "ok", "code_len": 5935}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5378, "tout": 3544, "ts": 1791525062.680575, "chk": null, "code_len": 5935}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1740, "started": 1791524827.957685}
{"ep": "ok-00579", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.6938, "speedup": 0.6938, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 363.0, "calls": 4, "tokens_in": 38271, "tokens_out": 9096, "ctx_chars": 6513, "t_end": 1791525103.8782446, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.6938, "lo95": 0.6868, "mean": 0.7146, "ev_only": 0.6943, "ref_ms": 17.40017, "cand_ms": 25.07824, "n_trials": 42, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0229, "r_wall_s": 40.15, "compile_s": 4.69, "r_error": "", "src_len": 6289, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 2853, "ts": 1791524764.3514378, "chk": "incorrect", "code_len": 5825}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8606, "tout": 3260, "ts": 1791524812.9900815, "chk": "ok", "code_len": 6454}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11975, "tout": 71, "ts": 1791525040.7864318, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 12070, "tout": 2912, "ts": 1791525063.7072396, "chk": null, "code_len": 6289}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", "no_code", null], "first_tin": 5620, "started": 1791524740.8543165}
{"ep": "ok-00654", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.2994, "speedup": 0.2994, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 88.4, "calls": 3, "tokens_in": 20975, "tokens_out": 4249, "ctx_chars": 7010, "t_end": 1791525105.167462, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.2994, "lo95": 0.2978, "mean": 0.3224, "ev_only": 0.2996, "ref_ms": 3.43758, "cand_ms": 11.48081, "n_trials": 50, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0762, "r_wall_s": 43.99, "compile_s": 3.06, "r_error": "", "src_len": 4154, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5460, "tout": 2150, "ts": 1791525035.0670881, "chk": "ok", "code_len": 4154}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7722, "tout": 47, "ts": 1791525044.6408424, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7793, "tout": 2052, "ts": 1791525061.1501138, "chk": null, "code_len": 4154}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5460, "started": 1791525016.7664356}
{"ep": "ok-00626", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.6973, "speedup": 0.6973, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 192.3, "calls": 3, "tokens_in": 20912, "tokens_out": 13804, "ctx_chars": 0, "t_end": 1791525116.7893162, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.6973, "lo95": 0.6, "mean": 0.7615, "ev_only": 0.6967, "ref_ms": 28.72313, "cand_ms": 41.19396, "n_trials": 33, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0349, "r_wall_s": 34.59, "compile_s": 2.35, "r_error": "", "src_len": 3603, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 6623, "ts": 1791524980.510382, "chk": "incorrect", "code_len": 7097}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6955, "tout": 4702, "ts": 1791525044.152282, "chk": "incorrect", "code_len": 7116}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11038, "tout": 2479, "ts": 1791525082.083609, "chk": null, "code_len": 3603}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", null], "first_tin": 2919, "started": 1791524924.519656}
{"ep": "ok-00663", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9975, "speedup": 0.9975, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 70.1, "calls": 3, "tokens_in": 17313, "tokens_out": 2907, "ctx_chars": 7273, "t_end": 1791525117.664857, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9975, "lo95": 0.9932, "mean": 1.0006, "ev_only": 0.9966, "ref_ms": 8.13952, "cand_ms": 8.16023, "n_trials": 143, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0176, "r_wall_s": 31.13, "compile_s": 7.24, "r_error": "", "src_len": 2893, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4686, "tout": 1497, "ts": 1791525060.7138271, "chk": "ok", "code_len": 2893}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6295, "tout": 13, "ts": 1791525075.0788777, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6332, "tout": 1397, "ts": 1791525086.2640572, "chk": null, "code_len": 2893}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4686, "started": 1791525047.5430117}
{"ep": "ok-00551", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 6.6161, "speedup": 6.6161, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 502.9, "calls": 3, "tokens_in": 30295, "tokens_out": 24058, "ctx_chars": 7644, "t_end": 1791525139.9295797, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 6.6161, "lo95": 6.5381, "mean": 7.5631, "ev_only": 6.659, "ref_ms": 31.74511, "cand_ms": 4.79817, "n_trials": 33, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9932, "r_wall_s": 74.56, "compile_s": 16.5, "r_error": "", "src_len": 9410, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5260, "tout": 14938, "ts": 1791524766.3446293, "chk": "no_custom_kernel", "code_len": 9435}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10244, "tout": 4748, "ts": 1791524814.2828882, "chk": "ok", "code_len": 9410}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14791, "tout": 4372, "ts": 1791525065.3455343, "chk": null, "code_len": 9410}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5260, "started": 1791524636.9999564}
{"ep": "ok-00628", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0256, "speedup": 1.0256, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 212.2, "calls": 3, "tokens_in": 20100, "tokens_out": 1872, "ctx_chars": 9950, "t_end": 1791525140.140464, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0256, "lo95": 1.0246, "mean": 1.0257, "ev_only": 1.0244, "ref_ms": 8.1683, "cand_ms": 7.9643, "n_trials": 150, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 49.93, "compile_s": 2.78, "r_error": "", "src_len": 1866, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5980, "tout": 937, "ts": 1791524936.312895, "chk": "ok", "code_len": 1866}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7029, "tout": 38, "ts": 1791524945.9371362, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7091, "tout": 897, "ts": 1791524953.6662433, "chk": null, "code_len": 1866}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5980, "started": 1791524927.9007368}
{"ep": "ok-00633", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0034, "speedup": 1.0034, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 205.4, "calls": 3, "tokens_in": 17191, "tokens_out": 7557, "ctx_chars": 5978, "t_end": 1791525144.1961966, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0034, "lo95": 1.0025, "mean": 1.0014, "ev_only": 1.0044, "ref_ms": 7.95306, "cand_ms": 7.9264, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 81.67, "compile_s": 3.54, "r_error": "", "src_len": 923, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4158, "tout": 2728, "ts": 1791524962.24156, "chk": "incorrect", "code_len": 2581}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5950, "tout": 4169, "ts": 1791525048.0149465, "chk": "ok", "code_len": 923}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7083, "tout": 660, "ts": 1791525062.5067155, "chk": null, "code_len": 923}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 4158, "started": 1791524938.7513046}
{"ep": "ok-00612", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0266, "speedup": 1.0266, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 287.3, "calls": 2, "tokens_in": 16228, "tokens_out": 2121, "ctx_chars": 13736, "t_end": 1791525144.8939025, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0266, "lo95": 1.023, "mean": 1.0292, "ev_only": 1.0261, "ref_ms": 8.23013, "cand_ms": 8.01691, "n_trials": 192, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 197.8, "compile_s": 2.1, "r_error": "", "src_len": 1798, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7510, "tout": 1096, "ts": 1791524866.0163536, "chk": "ok", "code_len": 1798}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8718, "tout": 1025, "ts": 1791524947.007978, "chk": null, "code_len": 1798}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7510, "started": 1791524857.5593069}
{"ep": "ok-00527", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 8.3297, "speedup": 8.3297, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 612.0, "calls": 4, "tokens_in": 25217, "tokens_out": 25160, "ctx_chars": 0, "t_end": 1791525150.863673, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 8.3297, "lo95": 8.3188, "mean": 8.3116, "ev_only": 8.3199, "ref_ms": 31.76534, "cand_ms": 3.81352, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9994, "r_wall_s": 60.72, "compile_s": 13.35, "r_error": "", "src_len": 8102, "atts": [{"turn": 0, "action": "CHECK", "stop": null, "tin": 1951, "tout": 8876, "ts": 1791524626.153025, "chk": "no_code", "code_len": 0}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3344, "tout": 8212, "ts": 1791524693.9137926, "chk": "no_custom_kernel", "code_len": 8126}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7928, "tout": 4218, "ts": 1791524808.663094, "chk": "ok", "code_len": 8102}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11994, "tout": 3854, "ts": 1791524954.260943, "chk": null, "code_len": 8102}], "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": 1951, "started": 1791524538.816726}
{"ep": "ok-00620", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0332, "speedup": 1.0332, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 278.7, "calls": 2, "tokens_in": 6013, "tokens_out": 5375, "ctx_chars": 495, "t_end": 1791525153.4768965, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0332, "lo95": 1.0325, "mean": 1.0496, "ev_only": 1.0332, "ref_ms": 29.78312, "cand_ms": 28.82614, "n_trials": 46, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0199, "r_wall_s": 62.85, "compile_s": 2.83, "r_error": "", "src_len": 3157, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1878, "tout": 3670, "ts": 1791524907.344849, "chk": "ok", "code_len": 3157}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4135, "tout": 1705, "ts": 1791524955.2561574, "chk": null, "code_len": 3157}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1878, "started": 1791524874.800195}
{"ep": "ok-00589", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 6.2841, "speedup": 6.2841, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 379.2, "calls": 2, "tokens_in": 12273, "tokens_out": 25158, "ctx_chars": 0, "t_end": 1791525159.980517, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 6.2841, "lo95": 6.2637, "mean": 6.463, "ev_only": 6.3773, "ref_ms": 4.23634, "cand_ms": 0.67413, "n_trials": 214, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 20.67, "compile_s": 12.02, "r_error": "", "src_len": 13354, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 18257, "ts": 1791524935.3644602, "chk": "ok", "code_len": 13354}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 9915, "tout": 6901, "ts": 1791525005.8518288, "chk": null, "code_len": 13354}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2358, "started": 1791524780.7342434}
{"ep": "ok-00636", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0329, "speedup": 1.0329, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 209.5, "calls": 2, "tokens_in": 7333, "tokens_out": 4551, "ctx_chars": 2175, "t_end": 1791525161.4178455, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0329, "lo95": 1.0326, "mean": 1.033, "ev_only": 1.0332, "ref_ms": 29.68797, "cand_ms": 28.74199, "n_trials": 47, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0281, "r_wall_s": 99.42, "compile_s": 3.95, "r_error": "", "src_len": 3013, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2546, "tout": 2889, "ts": 1791524976.7231257, "chk": "ok", "code_len": 3013}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4787, "tout": 1662, "ts": 1791525061.446503, "chk": null, "code_len": 3013}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2546, "started": 1791524951.9297922}
{"ep": "ok-00653", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9334, "speedup": 0.9334, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 154.0, "calls": 3, "tokens_in": 242020, "tokens_out": 6687, "ctx_chars": 182830, "t_end": 1791525164.900723, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9334, "lo95": 0.9331, "mean": 0.9326, "ev_only": 0.9339, "ref_ms": 8.19547, "cand_ms": 8.78039, "n_trials": 155, "fast1": false, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 23.9, "compile_s": 1.85, "r_error": "", "src_len": 3786, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78290, "tout": 2332, "ts": 1791525034.3326113, "chk": "incorrect", "code_len": 3779}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 80754, "tout": 2110, "ts": 1791525076.6874814, "chk": "ok", "code_len": 3859}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 82976, "tout": 2245, "ts": 1791525140.9294636, "chk": null, "code_len": 3786}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78290, "started": 1791525010.9395816}
{"ep": "ok-00644", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9993, "speedup": 0.9993, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 196.1, "calls": 3, "tokens_in": 9050, "tokens_out": 3276, "ctx_chars": 495, "t_end": 1791525174.7010684, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9993, "lo95": 0.9969, "mean": 1.018, "ev_only": 0.9972, "ref_ms": 8.17338, "cand_ms": 8.17918, "n_trials": 94, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0085, "r_wall_s": 88.44, "compile_s": 4.36, "r_error": "", "src_len": 2977, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1738, "tout": 1769, "ts": 1791524995.1098619, "chk": "ok", "code_len": 2977}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3619, "tout": 50, "ts": 1791525074.2724652, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 3693, "tout": 1457, "ts": 1791525086.1123464, "chk": null, "code_len": 2977}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 1738, "started": 1791524978.6058168}
{"ep": "ok-00547", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9326, "speedup": 0.9326, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 552.2, "calls": 4, "tokens_in": 38779, "tokens_out": 22034, "ctx_chars": 0, "t_end": 1791525181.7723734, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9326, "lo95": 0.8333, "mean": 0.9579, "ev_only": 0.9315, "ref_ms": 27.83756, "cand_ms": 29.84933, "n_trials": 23, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0511, "r_wall_s": 97.65, "compile_s": 17.91, "r_error": "", "src_len": 5671, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 8901, "ts": 1791524704.2817016, "chk": "incorrect", "code_len": 9215}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7706, "tout": 6488, "ts": 1791524932.4296966, "chk": "incorrect", "code_len": 9523}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12555, "tout": 3509, "ts": 1791524983.9628696, "chk": "ok", "code_len": 5671}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 15599, "tout": 3136, "ts": 1791525084.006545, "chk": null, "code_len": 5671}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2919, "started": 1791524629.5958016}
{"ep": "ok-00650", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9952, "speedup": 0.9952, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 185.8, "calls": 2, "tokens_in": 17752, "tokens_out": 5333, "ctx_chars": 14186, "t_end": 1791525182.334284, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9952, "lo95": 0.993, "mean": 1.0016, "ev_only": 0.9968, "ref_ms": 8.09267, "cand_ms": 8.13198, "n_trials": 143, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.009, "r_wall_s": 106.66, "compile_s": 3.71, "r_error": "", "src_len": 3855, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7604, "tout": 3291, "ts": 1791525044.2222362, "chk": "ok", "code_len": 3855}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10148, "tout": 2042, "ts": 1791525075.3075147, "chk": null, "code_len": 3855}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 7604, "started": 1791525016.8771982}
{"ep": "ok-00635", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.8434, "speedup": 0.8434, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 238.6, "calls": 2, "tokens_in": 12037, "tokens_out": 5967, "ctx_chars": 4637, "t_end": 1791525182.7389517, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8434, "lo95": 0.7767, "mean": 0.9593, "ev_only": 0.8502, "ref_ms": 4.18627, "cand_ms": 4.96373, "n_trials": 187, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0876, "r_wall_s": 104.29, "compile_s": 42.21, "r_error": "", "src_len": 4487, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4066, "tout": 3793, "ts": 1791524978.5714757, "chk": "ok", "code_len": 4545}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7971, "tout": 2174, "ts": 1791525078.4170678, "chk": null, "code_len": 4487}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4066, "started": 1791524944.179255}
{"ep": "ok-00670", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0262, "speedup": 1.0262, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 119.1, "calls": 3, "tokens_in": 17018, "tokens_out": 2155, "ctx_chars": 7308, "t_end": 1791525184.3424332, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0262, "lo95": 1.0259, "mean": 1.0338, "ev_only": 1.0267, "ref_ms": 8.19976, "cand_ms": 7.99006, "n_trials": 157, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0047, "r_wall_s": 18.63, "compile_s": 2.0, "r_error": "", "src_len": 2156, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4853, "tout": 1076, "ts": 1791525075.0731902, "chk": "ok", "code_len": 2198}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6041, "tout": 59, "ts": 1791525157.0958765, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6124, "tout": 1020, "ts": 1791525165.643324, "chk": null, "code_len": 2156}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4853, "started": 1791525065.2305377}
{"ep": "ok-00639", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0009, "speedup": 1.0009, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 231.5, "calls": 5, "tokens_in": 38613, "tokens_out": 4127, "ctx_chars": 9192, "t_end": 1791525195.329297, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0009, "lo95": 0.9999, "mean": 1.0007, "ev_only": 0.9995, "ref_ms": 7.95381, "cand_ms": 7.94674, "n_trials": 153, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 117.92, "compile_s": 3.78, "r_error": "", "src_len": 992, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 599, "ts": 1791524970.182268, "chk": "incorrect", "code_len": 1099}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6363, "tout": 1576, "ts": 1791525029.6765778, "chk": "incorrect", "code_len": 1161}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8072, "tout": 663, "ts": 1791525044.836312, "chk": "incorrect", "code_len": 1040}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8868, "tout": 679, "ts": 1791525060.0490866, "chk": "ok", "code_len": 992}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9679, "tout": 610, "ts": 1791525077.3865554, "chk": null, "code_len": 992}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 5631, "started": 1791524963.8364859}
{"ep": "ok-00651", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0247, "speedup": 1.0247, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 195.6, "calls": 2, "tokens_in": 13636, "tokens_out": 4698, "ctx_chars": 8788, "t_end": 1791525196.0723321, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0247, "lo95": 1.0244, "mean": 1.0245, "ev_only": 1.0245, "ref_ms": 29.60062, "cand_ms": 28.88766, "n_trials": 44, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0278, "r_wall_s": 124.65, "compile_s": 3.55, "r_error": "", "src_len": 2975, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5761, "tout": 3120, "ts": 1791525027.8955538, "chk": "ok", "code_len": 2975}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7875, "tout": 1578, "ts": 1791525070.9105794, "chk": null, "code_len": 2975}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 5761, "started": 1791525000.4407244}
{"ep": "ok-00657", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.9377, "speedup": 0.9377, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 172.6, "calls": 2, "tokens_in": 7033, "tokens_out": 5304, "ctx_chars": 1383, "t_end": 1791525199.141172, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9377, "lo95": 0.9362, "mean": 0.9297, "ev_only": 0.9372, "ref_ms": 29.75396, "cand_ms": 31.73006, "n_trials": 32, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0176, "r_wall_s": 109.24, "compile_s": 4.52, "r_error": "", "src_len": 3386, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2299, "tout": 3427, "ts": 1791525056.5291646, "chk": "ok", "code_len": 3386}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4734, "tout": 1877, "ts": 1791525089.292048, "chk": null, "code_len": 3386}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2299, "started": 1791525026.574537}
{"ep": "ok-00667", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.3002, "speedup": 0.3002, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 146.5, "calls": 3, "tokens_in": 20102, "tokens_out": 4262, "ctx_chars": 6059, "t_end": 1791525202.6718779, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.3002, "lo95": 0.2991, "mean": 0.2978, "ev_only": 0.2984, "ref_ms": 3.46402, "cand_ms": 11.5403, "n_trials": 122, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0735, "r_wall_s": 26.04, "compile_s": 1.92, "r_error": "", "src_len": 4041, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5136, "tout": 2196, "ts": 1791525075.068894, "chk": "ok", "code_len": 4128}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7444, "tout": 54, "ts": 1791525160.4555397, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7522, "tout": 2012, "ts": 1791525176.6112201, "chk": null, "code_len": 4041}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5136, "started": 1791525056.194211}
{"ep": "ok-00594", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.1547, "speedup": 0.1547, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 404.1, "calls": 2, "tokens_in": 11692, "tokens_out": 22220, "ctx_chars": 495, "t_end": 1791525204.67209, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.1547, "lo95": 0.1531, "mean": 0.1567, "ev_only": 0.1537, "ref_ms": 3.49117, "cand_ms": 22.5608, "n_trials": 48, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.9991, "r_wall_s": 41.42, "compile_s": 2.33, "r_error": "", "src_len": 10712, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2761, "tout": 16523, "ts": 1791524944.4572866, "chk": "ok", "code_len": 10727}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8931, "tout": 5697, "ts": 1791525163.2100003, "chk": null, "code_len": 10712}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2761, "started": 1791524800.5648804}
{"ep": "ok-00632", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.9129, "speedup": 0.9129, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 273.0, "calls": 2, "tokens_in": 8802, "tokens_out": 5451, "ctx_chars": 0, "t_end": 1791525208.3515973, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9129, "lo95": 0.7351, "mean": 0.849, "ev_only": 0.9115, "ref_ms": 5.9378, "cand_ms": 6.50442, "n_trials": 188, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0257, "r_wall_s": 111.87, "compile_s": 29.26, "r_error": "", "src_len": 3060, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2356, "tout": 3978, "ts": 1791524991.0439644, "chk": "ok", "code_len": 3060}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6446, "tout": 1473, "ts": 1791525096.374981, "chk": null, "code_len": 3060}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2356, "started": 1791524955.6699522}
{"ep": "ok-00617", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 9.3978, "speedup": 9.3978, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 337.6, "calls": 2, "tokens_in": 17201, "tokens_out": 17022, "ctx_chars": 10587, "t_end": 1791525209.1985855, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 9.3978, "lo95": 7.6638, "mean": 9.1153, "ev_only": 9.4769, "ref_ms": 43.82425, "cand_ms": 4.66326, "n_trials": 23, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9996, "r_wall_s": 117.41, "compile_s": 68.17, "r_error": "", "src_len": 7335, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 12859, "ts": 1791525008.6065514, "chk": "ok", "code_len": 7392}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10837, "tout": 4163, "ts": 1791525091.6687155, "chk": null, "code_len": 7335}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6364, "started": 1791524891.9676428}
{"ep": "ok-00661", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.035, "speedup": 1.035, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.1, "calls": 3, "tokens_in": 20331, "tokens_out": 2908, "ctx_chars": 9128, "t_end": 1791525209.8969948, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.035, "lo95": 1.0345, "mean": 1.0317, "ev_only": 1.0359, "ref_ms": 29.88989, "cand_ms": 28.87915, "n_trials": 53, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0176, "r_wall_s": 116.77, "compile_s": 8.75, "r_error": "", "src_len": 2748, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5681, "tout": 1507, "ts": 1791525060.7917755, "chk": "ok", "code_len": 2748}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7300, "tout": 26, "ts": 1791525081.1179178, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7350, "tout": 1375, "ts": 1791525092.5684652, "chk": null, "code_len": 2748}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5681, "started": 1791525046.786522}
{"ep": "ok-00584", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 4.9513, "speedup": 4.9513, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 459.4, "calls": 3, "tokens_in": 26800, "tokens_out": 29269, "ctx_chars": 0, "t_end": 1791525211.58747, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 4.9513, "lo95": 4.9021, "mean": 4.9185, "ev_only": 4.9406, "ref_ms": 4.10064, "cand_ms": 0.82819, "n_trials": 189, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.996, "r_wall_s": 105.5, "compile_s": 57.97, "r_error": "", "src_len": 10920, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 16843, "ts": 1791524896.7065868, "chk": "no_custom_kernel", "code_len": 11140}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9101, "tout": 6364, "ts": 1791524961.659988, "chk": "ok", "code_len": 10920}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15341, "tout": 6062, "ts": 1791525105.9702418, "chk": null, "code_len": 10920}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2358, "started": 1791524752.1425557}
{"ep": "ok-00658", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 74.1312, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 178.8, "calls": 2, "tokens_in": 8805, "tokens_out": 8068, "ctx_chars": 2256, "t_end": 1791525216.2835486, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 74.1312, "lo95": 73.554, "mean": 72.1519, "ev_only": 77.9564, "ref_ms": 22.33724, "cand_ms": 0.30132, "n_trials": 58, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 68.9, "compile_s": 12.21, "r_error": "", "src_len": 5939, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2666, "tout": 5175, "ts": 1791525080.774773, "chk": "ok", "code_len": 5939}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6139, "tout": 2893, "ts": 1791525147.1489258, "chk": null, "code_len": 5939}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2666, "started": 1791525037.5336053}
{"ep": "ok-00669", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.9955, "speedup": 0.9955, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.2, "calls": 3, "tokens_in": 17264, "tokens_out": 2849, "ctx_chars": 7333, "t_end": 1791525225.3067944, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.9955, "lo95": 0.9951, "mean": 0.9948, "ev_only": 0.9959, "ref_ms": 8.07358, "cand_ms": 8.11041, "n_trials": 194, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0178, "r_wall_s": 23.67, "compile_s": 2.1, "r_error": "", "src_len": 2883, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4705, "tout": 1444, "ts": 1791525074.3544414, "chk": "ok", "code_len": 2883}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6261, "tout": 13, "ts": 1791525190.0699813, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6298, "tout": 1392, "ts": 1791525201.5570061, "chk": null, "code_len": 2883}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4705, "started": 1791525062.089443}
{"ep": "ok-00648", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0067, "speedup": 1.0067, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 233.4, "calls": 3, "tokens_in": 10511, "tokens_out": 8339, "ctx_chars": 495, "t_end": 1791525225.518648, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0067, "lo95": 1.0063, "mean": 1.066, "ev_only": 1.005, "ref_ms": 7.92461, "cand_ms": 7.87224, "n_trials": 126, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 103.8, "compile_s": 52.73, "r_error": "", "src_len": 952, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1816, "tout": 2864, "ts": 1791525016.7772315, "chk": "incorrect", "code_len": 2834}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3799, "tout": 4490, "ts": 1791525070.569017, "chk": "ok", "code_len": 952}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4896, "tout": 985, "ts": 1791525121.6164615, "chk": null, "code_len": 952}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 1816, "started": 1791524992.1634412}
{"ep": "ok-00603", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.2172, "speedup": 1.2172, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 413.9, "calls": 3, "tokens_in": 243802, "tokens_out": 6114, "ctx_chars": 182830, "t_end": 1791525231.5850227, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.2172, "lo95": 0.9609, "mean": 1.1176, "ev_only": 1.2147, "ref_ms": 4.19671, "cand_ms": 3.44788, "n_trials": 216, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0382, "r_wall_s": 65.48, "compile_s": 42.49, "r_error": "", "src_len": 3623, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78923, "tout": 2298, "ts": 1791524840.412613, "chk": "ok", "code_len": 3912}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81333, "tout": 2104, "ts": 1791525029.6049714, "chk": "ok", "code_len": 3623}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 83546, "tout": 1712, "ts": 1791525166.0814002, "chk": null, "code_len": 3623}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "ok", null], "first_tin": 78923, "started": 1791524817.6954103}
{"ep": "ok-00668", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.1025, "speedup": 1.1025, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 176.6, "calls": 4, "tokens_in": 19836, "tokens_out": 5079, "ctx_chars": 0, "t_end": 1791525236.2636793, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.1025, "lo95": 1.1006, "mean": 1.1022, "ev_only": 1.1013, "ref_ms": 22.34775, "cand_ms": 20.27055, "n_trials": 60, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0323, "r_wall_s": 44.6, "compile_s": 11.58, "r_error": "", "src_len": 3556, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1827, "tout": 1672, "ts": 1791525095.1515436, "chk": "compile_error", "code_len": 3520}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4772, "tout": 1692, "ts": 1791525157.8989005, "chk": "ok", "code_len": 3556}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6576, "tout": 61, "ts": 1791525177.7935596, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 6661, "tout": 1654, "ts": 1791525191.4567063, "chk": null, "code_len": 3556}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1827, "started": 1791525080.0608213}
{"ep": "ok-00659", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 198.1, "calls": 2, "tokens_in": 12123, "tokens_out": 7450, "ctx_chars": 2425, "t_end": 1791525236.8062582, "error": "output mismatch beyond atol=rtol=0.0001", "f_status": "incorrect", "f_error": "", "submit_turn": 1, "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": 0.6881, "r_wall_s": 117.67, "compile_s": 50.52, "r_error": "output mismatch beyond atol=rtol=0.0001", "src_len": 4068, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3272, "tout": 5467, "ts": 1791525084.8566082, "chk": "ok", "code_len": 4068}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8851, "tout": 1983, "ts": 1791525119.029204, "chk": null, "code_len": 4068}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3272, "started": 1791525038.7003407}
{"ep": "ok-00614", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.9987, "speedup": 0.9987, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 377.7, "calls": 5, "tokens_in": 32301, "tokens_out": 4205, "ctx_chars": 6127, "t_end": 1791525237.9109716, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 0.9987, "lo95": 0.9962, "mean": 0.9987, "ev_only": 0.9986, "ref_ms": 8.01632, "cand_ms": 8.02708, "n_trials": 61, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0038, "r_wall_s": 38.4, "compile_s": 2.02, "r_error": "", "src_len": 916, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4216, "tout": 1000, "ts": 1791524870.2861028, "chk": "incorrect", "code_len": 1513}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5349, "tout": 1183, "ts": 1791524964.6484177, "chk": "incorrect", "code_len": 1528}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6665, "tout": 851, "ts": 1791525083.7637954, "chk": "incorrect", "code_len": 1070}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 7650, "tout": 639, "ts": 1791525103.9273872, "chk": "ok", "code_len": 916}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 8421, "tout": 532, "ts": 1791525199.4645321, "chk": null, "code_len": 916}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 4216, "started": 1791524860.2412224}
{"ep": "ok-00674", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0364, "speedup": 1.0364, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 161.4, "calls": 2, "tokens_in": 5317, "tokens_out": 3531, "ctx_chars": 495, "t_end": 1791525239.8636858, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0364, "lo95": 1.0322, "mean": 1.0353, "ev_only": 1.0386, "ref_ms": 8.28523, "cand_ms": 7.99407, "n_trials": 85, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0039, "r_wall_s": 38.32, "compile_s": 2.01, "r_error": "", "src_len": 1780, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1935, "tout": 2546, "ts": 1791525101.900783, "chk": "ok", "code_len": 1824}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3382, "tout": 985, "ts": 1791525201.5016608, "chk": null, "code_len": 1780}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1935, "started": 1791525078.4325287}
{"ep": "ok-00643", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.7563, "speedup": 0.7563, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 266.7, "calls": 3, "tokens_in": 27390, "tokens_out": 13106, "ctx_chars": 5888, "t_end": 1791525243.5329528, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.7563, "lo95": 0.7548, "mean": 0.7564, "ev_only": 0.7563, "ref_ms": 16.12734, "cand_ms": 21.32508, "n_trials": 74, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0355, "r_wall_s": 133.44, "compile_s": 54.19, "r_error": "", "src_len": 3709, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5353, "tout": 8962, "ts": 1791525053.9262455, "chk": "incorrect", "code_len": 7930}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10010, "tout": 2354, "ts": 1791525083.8339686, "chk": "ok", "code_len": 3709}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 12027, "tout": 1790, "ts": 1791525109.9871945, "chk": null, "code_len": 3709}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 5353, "started": 1791524976.798058}
{"ep": "ok-00665", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0336, "speedup": 1.0336, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 193.7, "calls": 3, "tokens_in": 19963, "tokens_out": 3999, "ctx_chars": 6481, "t_end": 1791525245.105885, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0336, "lo95": 1.0333, "mean": 1.0334, "ev_only": 1.0342, "ref_ms": 8.22445, "cand_ms": 7.95719, "n_trials": 178, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0061, "r_wall_s": 14.63, "compile_s": 1.92, "r_error": "", "src_len": 1827, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4520, "tout": 3054, "ts": 1791525078.8478737, "chk": "ok", "code_len": 1827}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7686, "tout": 47, "ts": 1791525222.9158707, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7757, "tout": 898, "ts": 1791525230.4530993, "chk": null, "code_len": 1827}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4520, "started": 1791525051.4185805}
{"ep": "ok-00625", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8148, "speedup": 0.8148, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 322.9, "calls": 2, "tokens_in": 163964, "tokens_out": 17393, "ctx_chars": 182830, "t_end": 1791525245.7606528, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8148, "lo95": 0.8132, "mean": 0.8179, "ev_only": 0.8146, "ref_ms": 3.37761, "cand_ms": 4.14507, "n_trials": 186, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0029, "r_wall_s": 133.44, "compile_s": 106.62, "r_error": "", "src_len": 10161, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79195, "tout": 12080, "ts": 1791525026.3446307, "chk": "ok", "code_len": 10161}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 84769, "tout": 5313, "ts": 1791525112.219306, "chk": null, "code_len": 10161}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79195, "started": 1791524922.885296}
{"ep": "ok-00679", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.0253, "speedup": 1.0253, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 145.7, "calls": 3, "tokens_in": 12570, "tokens_out": 1786, "ctx_chars": 4565, "t_end": 1791525250.8870363, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0253, "lo95": 1.025, "mean": 1.026, "ev_only": 1.0259, "ref_ms": 8.16167, "cand_ms": 7.96048, "n_trials": 115, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0062, "r_wall_s": 24.87, "compile_s": 1.85, "r_error": "", "src_len": 1744, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3499, "tout": 906, "ts": 1791525113.884247, "chk": "ok", "code_len": 1744}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 4517, "tout": 13, "ts": 1791525218.719277, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 4554, "tout": 867, "ts": 1791525225.934223, "chk": null, "code_len": 1744}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3499, "started": 1791525105.1677465}
{"ep": "ok-00685", "task": "L2_061", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0134, "speedup": 1.0134, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 108.4, "calls": 3, "tokens_in": 18330, "tokens_out": 2988, "ctx_chars": 7245, "t_end": 1791525253.2919474, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.0134, "lo95": 1.013, "mean": 1.0133, "ev_only": 1.013, "ref_ms": 29.67284, "cand_ms": 29.28008, "n_trials": 47, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0424, "r_wall_s": 66.14, "compile_s": 1.97, "r_error": "", "src_len": 2698, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4949, "tout": 1611, "ts": 1791525159.6414387, "chk": "ok", "code_len": 2730}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6672, "tout": 13, "ts": 1791525175.1951463, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 6709, "tout": 1364, "ts": 1791525186.628257, "chk": null, "code_len": 2698}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4949, "started": 1791525144.8942003}
{"ep": "ok-00697", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0371, "speedup": 1.0371, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 57.6, "calls": 2, "tokens_in": 5433, "tokens_out": 2690, "ctx_chars": 768, "t_end": 1791525253.6773627, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0371, "lo95": 1.0275, "mean": 1.0514, "ev_only": 1.034, "ref_ms": 8.24708, "cand_ms": 7.95233, "n_trials": 160, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0046, "r_wall_s": 28.04, "compile_s": 2.28, "r_error": "", "src_len": 1927, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2026, "tout": 1636, "ts": 1791525209.7454665, "chk": "ok", "code_len": 1927}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3407, "tout": 1054, "ts": 1791525225.563129, "chk": null, "code_len": 1927}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2026, "started": 1791525196.072656}
{"ep": "ok-00687", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.4088, "speedup": 1.4088, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 105.6, "calls": 2, "tokens_in": 5678, "tokens_out": 5284, "ctx_chars": 0, "t_end": 1791525259.0875092, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.4088, "lo95": 1.4062, "mean": 1.4039, "ev_only": 1.4132, "ref_ms": 8.27557, "cand_ms": 5.8742, "n_trials": 202, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 45.98, "compile_s": 1.9, "r_error": "", "src_len": 3393, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1725, "tout": 3386, "ts": 1791525185.7670581, "chk": "ok", "code_len": 3393}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 3953, "tout": 1898, "ts": 1791525213.006932, "chk": null, "code_len": 3393}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 1725, "started": 1791525153.4771802}
{"ep": "ok-00627", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0348, "speedup": 1.0348, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 333.0, "calls": 2, "tokens_in": 163678, "tokens_out": 13121, "ctx_chars": 182830, "t_end": 1791525260.1994045, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.0348, "lo95": 1.0293, "mean": 1.0351, "ev_only": 1.034, "ref_ms": 16.24727, "cand_ms": 15.70141, "n_trials": 53, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0613, "r_wall_s": 166.86, "compile_s": 71.46, "r_error": "", "src_len": 8681, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79486, "tout": 8405, "ts": 1791525002.5141072, "chk": "ok", "code_len": 8681}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 84192, "tout": 4716, "ts": 1791525093.2289674, "chk": null, "code_len": 8681}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 79486, "started": 1791524927.208423}
{"ep": "ok-00583", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 7.4863, "speedup": 7.4863, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 515.5, "calls": 3, "tokens_in": 247854, "tokens_out": 22318, "ctx_chars": 182830, "t_end": 1791525267.2834542, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 7.4863, "lo95": 7.4054, "mean": 7.5371, "ev_only": 7.5338, "ref_ms": 32.1665, "cand_ms": 4.29669, "n_trials": 45, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9763, "r_wall_s": 150.01, "compile_s": 102.06, "r_error": "", "src_len": 7787, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78518, "tout": 13596, "ts": 1791524876.0715394, "chk": "no_custom_kernel", "code_len": 7790}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 82761, "tout": 4289, "ts": 1791524970.5209486, "chk": "ok", "code_len": 7787}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 86575, "tout": 4433, "ts": 1791525117.1371863, "chk": null, "code_len": 7787}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 78518, "started": 1791524751.8009303}
{"ep": "ok-00700", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.294, "speedup": 0.294, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 65.0, "calls": 3, "tokens_in": 19809, "tokens_out": 4091, "ctx_chars": 6059, "t_end": 1791525269.6972487, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.294, "lo95": 0.2927, "mean": 0.3232, "ev_only": 0.2927, "ref_ms": 3.40315, "cand_ms": 11.57405, "n_trials": 133, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0791, "r_wall_s": 21.93, "compile_s": 2.94, "r_error": "", "src_len": 4044, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5136, "tout": 2070, "ts": 1791525222.0784416, "chk": "ok", "code_len": 4044}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7318, "tout": 13, "ts": 1791525231.4631295, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7355, "tout": 2008, "ts": 1791525247.7459414, "chk": null, "code_len": 4044}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5136, "started": 1791525204.6724055}
{"ep": "ok-00615", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.1019, "speedup": 1.1019, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 408.5, "calls": 4, "tokens_in": 24682, "tokens_out": 6464, "ctx_chars": 0, "t_end": 1791525272.8790588, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 1.1019, "lo95": 1.1015, "mean": 1.1015, "ev_only": 1.1017, "ref_ms": 22.24862, "cand_ms": 20.19195, "n_trials": 67, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0398, "r_wall_s": 166.55, "compile_s": 56.65, "r_error": "", "src_len": 3024, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1827, "tout": 3468, "ts": 1791524896.2605827, "chk": "compile_error", "code_len": 3122}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6531, "tout": 1494, "ts": 1791524966.7262022, "chk": "ok", "code_len": 3024}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8137, "tout": 26, "ts": 1791525093.7750292, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8187, "tout": 1476, "ts": 1791525106.0437298, "chk": null, "code_len": 3024}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1827, "started": 1791524864.345621}
{"ep": "ok-00704", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0189, "speedup": 1.0189, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 64.7, "calls": 2, "tokens_in": 10864, "tokens_out": 2360, "ctx_chars": 6811, "t_end": 1791525276.2745066, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0189, "lo95": 1.0168, "mean": 1.0369, "ev_only": 1.022, "ref_ms": 8.23978, "cand_ms": 8.08732, "n_trials": 182, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.005, "r_wall_s": 37.91, "compile_s": 2.04, "r_error": "", "src_len": 1877, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4724, "tout": 1304, "ts": 1791525222.2709625, "chk": "ok", "code_len": 1877}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6140, "tout": 1056, "ts": 1791525238.2991927, "chk": null, "code_len": 1877}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4724, "started": 1791525211.5877123}
{"ep": "ok-00698", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.0322, "speedup": 1.0322, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 78.6, "calls": 3, "tokens_in": 13927, "tokens_out": 2658, "ctx_chars": 3968, "t_end": 1791525277.736328, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0322, "lo95": 1.0313, "mean": 1.0256, "ev_only": 1.0334, "ref_ms": 8.38565, "cand_ms": 8.12373, "n_trials": 159, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0059, "r_wall_s": 30.59, "compile_s": 3.15, "r_error": "", "src_len": 1787, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3392, "tout": 1729, "ts": 1791525215.9099634, "chk": "ok", "code_len": 1787}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5233, "tout": 45, "ts": 1791525239.6781, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 5302, "tout": 884, "ts": 1791525247.1261017, "chk": null, "code_len": 1787}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 3392, "started": 1791525199.1415772}
{"ep": "ok-00703", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7427, "speedup": 0.7427, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 68.8, "calls": 2, "tokens_in": 9089, "tokens_out": 4140, "ctx_chars": 2169, "t_end": 1791525278.6603389, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7427, "lo95": 0.7417, "mean": 0.7488, "ev_only": 0.7428, "ref_ms": 4.01315, "cand_ms": 5.40333, "n_trials": 175, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0221, "r_wall_s": 12.85, "compile_s": 1.91, "r_error": "", "src_len": 2856, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3083, "tout": 2814, "ts": 1791525238.312603, "chk": "ok", "code_len": 3006}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6006, "tout": 1326, "ts": 1791525265.786263, "chk": null, "code_len": 2856}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3083, "started": 1791525209.8972695}
{"ep": "ok-00689", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0067, "speedup": 1.0067, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 119.9, "calls": 3, "tokens_in": 24402, "tokens_out": 8165, "ctx_chars": 4637, "t_end": 1791525281.2883897, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0067, "lo95": 1.0052, "mean": 1.0118, "ev_only": 1.0071, "ref_ms": 4.10401, "cand_ms": 4.07673, "n_trials": 228, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0907, "r_wall_s": 25.24, "compile_s": 11.7, "r_error": "", "src_len": 4475, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4066, "tout": 5964, "ts": 1791525211.657728, "chk": "ok", "code_len": 4475}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10142, "tout": 28, "ts": 1791525237.9939864, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10194, "tout": 2173, "ts": 1791525256.023224, "chk": null, "code_len": 4475}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4066, "started": 1791525161.418157}
{"ep": "ok-00672", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0277, "speedup": 1.0277, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 213.3, "calls": 2, "tokens_in": 10708, "tokens_out": 2115, "ctx_chars": 6811, "t_end": 1791525282.5983143, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0277, "lo95": 1.0271, "mean": 1.0272, "ev_only": 1.0264, "ref_ms": 8.16612, "cand_ms": 7.9461, "n_trials": 127, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 53.77, "compile_s": 2.01, "r_error": "", "src_len": 1770, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4724, "tout": 1148, "ts": 1791525078.2100403, "chk": "ok", "code_len": 1770}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5984, "tout": 967, "ts": 1791525228.7608163, "chk": null, "code_len": 1770}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4724, "started": 1791525069.2652042}
{"ep": "ok-00677", "task": "L2_022", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 1.0343, "speedup": 1.0343, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 179.7, "calls": 3, "tokens_in": 21665, "tokens_out": 2772, "ctx_chars": 9546, "t_end": 1791525283.5292084, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0343, "lo95": 1.0325, "mean": 1.0336, "ev_only": 1.0342, "ref_ms": 8.28098, "cand_ms": 8.00612, "n_trials": 137, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0056, "r_wall_s": 55.8, "compile_s": 2.1, "r_error": "", "src_len": 1929, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5935, "tout": 1768, "ts": 1791525119.7677271, "chk": "ok", "code_len": 1929}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7815, "tout": 76, "ts": 1791525219.8139114, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7915, "tout": 928, "ts": 1791525227.709278, "chk": null, "code_len": 1929}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5935, "started": 1791525103.8781173}
{"ep": "ok-00568", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.8661, "speedup": 0.8661, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 582.1, "calls": 5, "tokens_in": 52747, "tokens_out": 9851, "ctx_chars": 5802, "t_end": 1791525287.7098382, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.8661, "lo95": 0.8644, "mean": 0.8658, "ev_only": 0.8661, "ref_ms": 16.08577, "cand_ms": 18.57339, "n_trials": 88, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.035, "r_wall_s": 186.36, "compile_s": 45.44, "r_error": "", "src_len": 3931, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 2780, "ts": 1791524728.6959646, "chk": "incorrect", "code_len": 5710}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8244, "tout": 3200, "ts": 1791524908.1078153, "chk": "incorrect", "code_len": 6013}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11578, "tout": 2055, "ts": 1791524956.0925558, "chk": "ok", "code_len": 3931}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13742, "tout": 63, "ts": 1791525087.0282247, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13852, "tout": 1753, "ts": 1791525101.2451713, "chk": null, "code_len": 3931}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5331, "started": 1791524705.6055398}
{"ep": "ok-00701", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0267, "speedup": 1.0267, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 81.8, "calls": 2, "tokens_in": 13796, "tokens_out": 2085, "ctx_chars": 10373, "t_end": 1791525290.1329238, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0267, "lo95": 1.0265, "mean": 1.0269, "ev_only": 1.0277, "ref_ms": 8.14218, "cand_ms": 7.93012, "n_trials": 123, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0043, "r_wall_s": 57.43, "compile_s": 1.93, "r_error": "", "src_len": 1798, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6270, "tout": 1144, "ts": 1791525217.4696376, "chk": "ok", "code_len": 1798}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7526, "tout": 941, "ts": 1791525232.6199887, "chk": null, "code_len": 1798}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 6270, "started": 1791525208.3520212}
{"ep": "ok-00673", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.9948, "speedup": 0.9948, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.1, "calls": 3, "tokens_in": 22333, "tokens_out": 2898, "ctx_chars": 10823, "t_end": 1791525292.063885, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-06", "gpu": 0, "r_speedup": 0.9948, "lo95": 0.9945, "mean": 0.9948, "ev_only": 0.9953, "ref_ms": 8.02638, "cand_ms": 8.06821, "n_trials": 120, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0085, "r_wall_s": 171.58, "compile_s": 50.78, "r_error": "", "src_len": 2872, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6362, "tout": 1493, "ts": 1791525090.1421118, "chk": "ok", "code_len": 2872}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7967, "tout": 13, "ts": 1791525108.678209, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8004, "tout": 1392, "ts": 1791525120.3276854, "chk": null, "code_len": 2872}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 6362, "started": 1791525076.9239666}
{"ep": "ok-00681", "task": "L2_033", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.9977, "speedup": 0.9977, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 177.8, "calls": 4, "tokens_in": 24263, "tokens_out": 7571, "ctx_chars": 495, "t_end": 1791525295.4910061, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9977, "lo95": 0.9953, "mean": 0.9973, "ev_only": 0.9971, "ref_ms": 8.12898, "cand_ms": 8.14781, "n_trials": 199, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0217, "r_wall_s": 37.93, "compile_s": 11.34, "r_error": "", "src_len": 5069, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1738, "tout": 2817, "ts": 1791525143.4517863, "chk": "compile_error", "code_len": 5414}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 5837, "tout": 2353, "ts": 1791525209.6585577, "chk": "ok", "code_len": 5069}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8302, "tout": 60, "ts": 1791525238.9159453, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8386, "tout": 2341, "ts": 1791525257.4605792, "chk": null, "code_len": 5069}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1738, "started": 1791525117.6651645}
{"ep": "ok-00694", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 27.8537, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 113.2, "calls": 3, "tokens_in": 29294, "tokens_out": 7032, "ctx_chars": 12888, "t_end": 1791525295.9011288, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 27.8537, "lo95": 27.6669, "mean": 24.8846, "ev_only": 27.9276, "ref_ms": 22.31146, "cand_ms": 0.80102, "n_trials": 67, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "triton", "own_frac": 0.8353, "r_wall_s": 27.71, "compile_s": 2.03, "r_error": "", "src_len": 2719, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7686, "tout": 3731, "ts": 1791525216.0605798, "chk": "runtime_error", "code_len": 2750}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9971, "tout": 1837, "ts": 1791525236.3852901, "chk": "ok", "code_len": 2719}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11637, "tout": 1464, "ts": 1791525267.969582, "chk": null, "code_len": 2719}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 7686, "started": 1791525182.7392502}
{"ep": "ok-00666", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.9951, "speedup": 0.9951, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 248.6, "calls": 4, "tokens_in": 30855, "tokens_out": 7273, "ctx_chars": 9192, "t_end": 1791525303.4294882, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9951, "lo95": 0.9923, "mean": 0.9986, "ev_only": 0.9996, "ref_ms": 8.00813, "cand_ms": 8.04717, "n_trials": 134, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 32.63, "compile_s": 2.78, "r_error": "", "src_len": 979, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5633, "tout": 2811, "ts": 1791525080.2201817, "chk": "incorrect", "code_len": 2486}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7421, "tout": 2439, "ts": 1791525116.09285, "chk": "incorrect", "code_len": 1049}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 8427, "tout": 1405, "ts": 1791525230.2286751, "chk": "ok", "code_len": 979}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9374, "tout": 618, "ts": 1791525270.7751195, "chk": null, "code_len": 979}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5633, "started": 1791525054.8356547}
{"ep": "ok-00684", "task": "L2_030", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.026, "speedup": 1.026, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.4, "calls": 1, "tokens_in": 1856, "tokens_out": 1069, "ctx_chars": 495, "t_end": 1791525307.555456, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-02", "gpu": 0, "r_speedup": 1.026, "lo95": 1.0256, "mean": 1.0261, "ev_only": 1.0267, "ref_ms": 8.18875, "cand_ms": 7.98147, "n_trials": 158, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 16.66, "compile_s": 1.94, "r_error": "", "src_len": 1969, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 1856, "tout": 1069, "ts": 1791525155.1318192, "chk": null, "code_len": 1969}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 1856, "started": 1791525144.196463}
{"ep": "ok-00595", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0039, "speedup": 1.0039, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 504.2, "calls": 4, "tokens_in": 322463, "tokens_out": 9378, "ctx_chars": 182830, "t_end": 1791525307.683317, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0039, "lo95": 1.0033, "mean": 1.0044, "ev_only": 1.0046, "ref_ms": 7.98759, "cand_ms": 7.95667, "n_trials": 160, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0003, "r_wall_s": 70.91, "compile_s": 39.76, "r_error": "", "src_len": 1398, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78250, "tout": 2737, "ts": 1791524830.1824253, "chk": "incorrect", "code_len": 2553}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 79933, "tout": 3366, "ts": 1791524965.7977402, "chk": "incorrect", "code_len": 2099}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 81535, "tout": 1990, "ts": 1791525080.9538558, "chk": "ok", "code_len": 1398}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 82745, "tout": 1285, "ts": 1791525236.7453835, "chk": null, "code_len": 1398}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 78250, "started": 1791524803.4704487}
{"ep": "ok-00706", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.0983, "speedup": 1.0983, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 83.0, "calls": 3, "tokens_in": 25613, "tokens_out": 2208, "ctx_chars": 12888, "t_end": 1791525308.3485053, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0983, "lo95": 1.0977, "mean": 1.0976, "ev_only": 1.0982, "ref_ms": 22.2962, "cand_ms": 20.3013, "n_trials": 59, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0396, "r_wall_s": 50.81, "compile_s": 2.94, "r_error": "", "src_len": 2160, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 7684, "tout": 1150, "ts": 1791525237.0292623, "chk": "ok", "code_len": 2160}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8946, "tout": 13, "ts": 1791525247.2387958, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8983, "tout": 1045, "ts": 1791525257.3354764, "chk": null, "code_len": 2160}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 7684, "started": 1791525225.3071036}
{"ep": "ok-00641", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.9985, "speedup": 0.9985, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 346.3, "calls": 5, "tokens_in": 407027, "tokens_out": 6236, "ctx_chars": 182830, "t_end": 1791525311.0558264, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.9985, "lo95": 0.9979, "mean": 1.0404, "ev_only": 0.9992, "ref_ms": 7.96795, "cand_ms": 7.98015, "n_trials": 138, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 17.54, "compile_s": 2.62, "r_error": "", "src_len": 965, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78248, "tout": 1373, "ts": 1791524981.1619875, "chk": "incorrect", "code_len": 1762}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 79754, "tout": 1632, "ts": 1791525109.0171554, "chk": "incorrect", "code_len": 1789}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 81519, "tout": 1605, "ts": 1791525253.415319, "chk": "incorrect", "code_len": 1231}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 83257, "tout": 836, "ts": 1791525271.0584755, "chk": "incorrect", "code_len": 1261}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 84249, "tout": 790, "ts": 1791525293.4669797, "chk": null, "code_len": 965}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 78248, "started": 1791524964.7863278}
{"ep": "ok-00718", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.0999, "speedup": 1.0999, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 58.3, "calls": 3, "tokens_in": 29093, "tokens_out": 2173, "ctx_chars": 16078, "t_end": 1791525311.9580452, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0999, "lo95": 1.0995, "mean": 1.0996, "ev_only": 1.0997, "ref_ms": 22.26377, "cand_ms": 20.2413, "n_trials": 62, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0326, "r_wall_s": 26.55, "compile_s": 1.94, "r_error": "", "src_len": 2163, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8863, "tout": 1115, "ts": 1791525263.9140484, "chk": "ok", "code_len": 2237}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 10090, "tout": 26, "ts": 1791525276.5039892, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 10140, "tout": 1032, "ts": 1791525285.2082686, "chk": null, "code_len": 2163}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 8863, "started": 1791525253.6776834}
{"ep": "ok-00702", "task": "L2_030", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0324, "speedup": 1.0324, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 104.6, "calls": 2, "tokens_in": 10917, "tokens_out": 2506, "ctx_chars": 7159, "t_end": 1791525313.8103797, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0324, "lo95": 1.03, "mean": 1.0321, "ev_only": 1.0312, "ref_ms": 8.23561, "cand_ms": 7.97698, "n_trials": 161, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0045, "r_wall_s": 74.73, "compile_s": 2.4, "r_error": "", "src_len": 1795, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4795, "tout": 1546, "ts": 1791525222.3220866, "chk": "ok", "code_len": 1795}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6122, "tout": 960, "ts": 1791525238.986141, "chk": null, "code_len": 1795}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 4795, "started": 1791525209.1989317}
{"ep": "ok-00691", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.623, "speedup": 0.623, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 140.2, "calls": 2, "tokens_in": 8607, "tokens_out": 9291, "ctx_chars": 0, "t_end": 1791525314.9063435, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.623, "lo95": 0.5586, "mean": 0.6232, "ev_only": 0.6212, "ref_ms": 4.74556, "cand_ms": 7.61668, "n_trials": 195, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3704, "r_wall_s": 48.47, "compile_s": 2.25, "r_error": "", "src_len": 5532, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 6226, "ts": 1791525228.8581374, "chk": "ok", "code_len": 5532}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 5979, "tout": 3065, "ts": 1791525266.3864522, "chk": null, "code_len": 5532}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791525174.7013326}
{"ep": "ok-00716", "task": "L2_050", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 1.1002, "speedup": 1.1002, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 64.5, "calls": 1, "tokens_in": 7684, "tokens_out": 1081, "ctx_chars": 12888, "t_end": 1791525315.3936625, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 0, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.1002, "lo95": 1.0985, "mean": 1.0986, "ev_only": 1.1001, "ref_ms": 22.2532, "cand_ms": 20.2259, "n_trials": 57, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0328, "r_wall_s": 53.99, "compile_s": 2.75, "r_error": "", "src_len": 2179, "atts": [{"turn": 0, "action": "SUBMIT", "stop": "end_turn", "tin": 7684, "tout": 1081, "ts": 1791525261.1969347, "chk": null, "code_len": 2179}], "n_turns": 1, "n_check": 0, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": [null], "first_tin": 7684, "started": 1791525250.8873372}
{"ep": "ok-00646", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.7948, "speedup": 0.7948, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 332.2, "calls": 3, "tokens_in": 248324, "tokens_out": 9992, "ctx_chars": 182830, "t_end": 1791525321.507936, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7948, "lo95": 0.7932, "mean": 0.8116, "ev_only": 0.7906, "ref_ms": 3.33744, "cand_ms": 4.19897, "n_trials": 153, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.1179, "r_wall_s": 56.41, "compile_s": 45.94, "r_error": "", "src_len": 6292, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79193, "tout": 3602, "ts": 1791525023.6837058, "chk": "no_custom_kernel", "code_len": 6520}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 82948, "tout": 3123, "ts": 1791525103.9029515, "chk": "ok", "code_len": 6292}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 86183, "tout": 3267, "ts": 1791525265.0771055, "chk": null, "code_len": 6292}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 79193, "started": 1791524989.2811487}
{"ep": "ok-00688", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.6873, "speedup": 0.6873, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 163.2, "calls": 3, "tokens_in": 243898, "tokens_out": 5595, "ctx_chars": 182830, "t_end": 1791525323.1453104, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.6873, "lo95": 0.6847, "mean": 0.6891, "ev_only": 0.6865, "ref_ms": 3.38751, "cand_ms": 4.92842, "n_trials": 138, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.1386, "r_wall_s": 59.24, "compile_s": 47.03, "r_error": "", "src_len": 4998, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79193, "tout": 2889, "ts": 1791525186.2679715, "chk": "ok", "code_len": 5220}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 82191, "tout": 299, "ts": 1791525243.031321, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 82514, "tout": 2407, "ts": 1791525263.878893, "chk": null, "code_len": 4998}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 79193, "started": 1791525159.980787}
{"ep": "ok-00652", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 6.2228, "speedup": 6.2228, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 327.3, "calls": 3, "tokens_in": 28418, "tokens_out": 18920, "ctx_chars": 8224, "t_end": 1791525329.742092, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.2228, "lo95": 6.203, "mean": 6.2045, "ev_only": 6.2422, "ref_ms": 32.21925, "cand_ms": 5.17764, "n_trials": 39, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9961, "r_wall_s": 23.45, "compile_s": 11.28, "r_error": "", "src_len": 7095, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5495, "tout": 11471, "ts": 1791525103.634845, "chk": "no_custom_kernel", "code_len": 7081}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9608, "tout": 3979, "ts": 1791525258.353716, "chk": "ok", "code_len": 7095}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 13315, "tout": 3470, "ts": 1791525306.2455127, "chk": null, "code_len": 7095}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5495, "started": 1791525002.4542756}
{"ep": "ok-00616", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.8211, "speedup": 0.8211, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 465.0, "calls": 5, "tokens_in": 59776, "tokens_out": 20414, "ctx_chars": 495, "t_end": 1791525331.03792, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8211, "lo95": 0.8172, "mean": 0.8194, "ev_only": 0.8212, "ref_ms": 16.14116, "cand_ms": 19.65728, "n_trials": 61, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0647, "r_wall_s": 39.46, "compile_s": 13.34, "r_error": "", "src_len": 9546, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3050, "tout": 3916, "ts": 1791524900.9086668, "chk": "compile_error", "code_len": 8307}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8160, "tout": 3600, "ts": 1791524986.3301127, "chk": "incorrect", "code_len": 8145}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11891, "tout": 3893, "ts": 1791525092.886313, "chk": "no_custom_kernel", "code_len": 8552}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 15931, "tout": 4681, "ts": 1791525240.88007, "chk": "ok", "code_len": 9546}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 20744, "tout": 4324, "ts": 1791525291.5553772, "chk": null, "code_len": 9546}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "incorrect", "no_custom_kernel", "ok", null], "first_tin": 3050, "started": 1791524866.0236592}
{"ep": "ok-00622", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.7189, "speedup": 0.7189, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 433.3, "calls": 5, "tokens_in": 51645, "tokens_out": 13930, "ctx_chars": 0, "t_end": 1791525334.6509337, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7189, "lo95": 0.7167, "mean": 0.7193, "ev_only": 0.7195, "ref_ms": 16.25851, "cand_ms": 22.61496, "n_trials": 60, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.04, "r_wall_s": 17.53, "compile_s": 2.02, "r_error": "", "src_len": 6069, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2917, "tout": 5425, "ts": 1791524944.807954, "chk": "forbidden", "code_len": 6240}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8444, "tout": 2750, "ts": 1791525100.3328207, "chk": "no_custom_kernel", "code_len": 6084}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11318, "tout": 3008, "ts": 1791525277.226646, "chk": "ok", "code_len": 6069}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14435, "tout": 49, "ts": 1791525295.989644, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 14531, "tout": 2698, "ts": 1791525317.0954928, "chk": null, "code_len": 6069}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "no_custom_kernel", "ok", "no_code", null], "first_tin": 2917, "started": 1791524901.3964229}
{"ep": "ok-00660", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.998, "speedup": 0.998, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 293.8, "calls": 5, "tokens_in": 35280, "tokens_out": 2621, "ctx_chars": 9192, "t_end": 1791525335.0251896, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.998, "lo95": 0.9978, "mean": 0.9972, "ev_only": 0.9988, "ref_ms": 7.91768, "cand_ms": 7.93383, "n_trials": 197, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 43.65, "compile_s": 2.38, "r_error": "", "src_len": 963, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 594, "ts": 1791525047.3285377, "chk": "incorrect", "code_len": 1037}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6358, "tout": 683, "ts": 1791525062.549335, "chk": "incorrect", "code_len": 1028}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7174, "tout": 632, "ts": 1791525118.2291007, "chk": "ok", "code_len": 963}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 7915, "tout": 240, "ts": 1791525286.7080615, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 8202, "tout": 472, "ts": 1791525291.34938, "chk": null, "code_len": 963}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5631, "started": 1791525041.2069016}
{"ep": "ok-00634", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.8355, "speedup": 0.8355, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 394.7, "calls": 4, "tokens_in": 339015, "tokens_out": 13457, "ctx_chars": 182830, "t_end": 1791525337.220477, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8355, "lo95": 0.8346, "mean": 0.8397, "ev_only": 0.8355, "ref_ms": 16.12129, "cand_ms": 19.29579, "n_trials": 60, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0634, "r_wall_s": 77.37, "compile_s": 48.78, "r_error": "", "src_len": 7143, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 79484, "tout": 3562, "ts": 1791524975.9868274, "chk": "forbidden", "code_len": 7140}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 83148, "tout": 3218, "ts": 1791525002.1501117, "chk": "no_custom_kernel", "code_len": 7149}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 86498, "tout": 3278, "ts": 1791525080.772052, "chk": "ok", "code_len": 7143}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 89885, "tout": 3399, "ts": 1791525259.8244474, "chk": null, "code_len": 7143}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "no_custom_kernel", "ok", null], "first_tin": 79484, "started": 1791524942.539413}
{"ep": "ok-00601", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 0.7693, "speedup": 0.7693, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 521.5, "calls": 5, "tokens_in": 57521, "tokens_out": 11126, "ctx_chars": 6513, "t_end": 1791525337.3005393, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7693, "lo95": 0.7645, "mean": 0.7871, "ev_only": 0.7699, "ref_ms": 16.76067, "cand_ms": 21.78557, "n_trials": 61, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0545, "r_wall_s": 38.37, "compile_s": 1.91, "r_error": "", "src_len": 4277, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5620, "tout": 3200, "ts": 1791524841.5228984, "chk": "incorrect", "code_len": 6433}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8953, "tout": 3575, "ts": 1791524986.5224838, "chk": "incorrect", "code_len": 6581}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12662, "tout": 2319, "ts": 1791525106.6413383, "chk": "ok", "code_len": 4277}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 15090, "tout": 59, "ts": 1791525283.223041, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 15196, "tout": 1973, "ts": 1791525298.9059021, "chk": null, "code_len": 4277}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5620, "started": 1791524815.8371809}
{"ep": "ok-00630", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 6.0002, "speedup": 6.0002, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 409.6, "calls": 3, "tokens_in": 31165, "tokens_out": 20752, "ctx_chars": 10587, "t_end": 1791525339.2697957, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 6.0002, "lo95": 5.9934, "mean": 6.0188, "ev_only": 6.0163, "ref_ms": 31.6561, "cand_ms": 5.27588, "n_trials": 44, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9921, "r_wall_s": 89.76, "compile_s": 14.9, "r_error": "", "src_len": 6253, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 12470, "ts": 1791525039.6353233, "chk": "no_custom_kernel", "code_len": 6256}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10500, "tout": 4442, "ts": 1791525091.653649, "chk": "ok", "code_len": 6253}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14301, "tout": 3840, "ts": 1791525249.4856343, "chk": null, "code_len": 6253}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6364, "started": 1791524929.688389}
{"ep": "ok-00664", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 1.0062, "speedup": 1.0062, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 291.2, "calls": 4, "tokens_in": 25793, "tokens_out": 7534, "ctx_chars": 5978, "t_end": 1791525340.7180445, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0062, "lo95": 1.0059, "mean": 1.0034, "ev_only": 1.0044, "ref_ms": 7.9708, "cand_ms": 7.92208, "n_trials": 165, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0002, "r_wall_s": 52.44, "compile_s": 2.0, "r_error": "", "src_len": 935, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4158, "tout": 3075, "ts": 1791525077.1006374, "chk": "incorrect", "code_len": 2711}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6150, "tout": 2223, "ts": 1791525243.3910527, "chk": "incorrect", "code_len": 1091}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7290, "tout": 1357, "ts": 1791525270.6241586, "chk": "ok", "code_len": 935}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 8195, "tout": 879, "ts": 1791525288.2542834, "chk": null, "code_len": 935}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 4158, "started": 1791525049.5621622}
{"ep": "ok-00683", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 0.0844, "speedup": 0.0844, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 212.8, "calls": 2, "tokens_in": 164493, "tokens_out": 9607, "ctx_chars": 182830, "t_end": 1791525352.961204, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.0844, "lo95": 0.0843, "mean": 0.0878, "ev_only": 0.0843, "ref_ms": 31.23165, "cand_ms": 369.93024, "n_trials": 12, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.9979, "r_wall_s": 69.87, "compile_s": 56.12, "r_error": "", "src_len": 4160, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78516, "tout": 7349, "ts": 1791525206.3354592, "chk": "ok", "code_len": 4160}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 85977, "tout": 2258, "ts": 1791525283.0493703, "chk": null, "code_len": 4160}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78516, "started": 1791525140.140775}
{"ep": "ok-00712", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "ok", "score": 0.1189, "speedup": 0.1189, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.6, "calls": 4, "tokens_in": 38094, "tokens_out": 6753, "ctx_chars": 8224, "t_end": 1791525357.4845521, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 0.1189, "lo95": 0.1185, "mean": 0.1172, "ev_only": 0.1188, "ref_ms": 31.55155, "cand_ms": 265.40745, "n_trials": 14, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.3, "r_wall_s": 33.79, "compile_s": 1.98, "r_error": "", "src_len": 2265, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5493, "tout": 4260, "ts": 1791525277.435979, "chk": "forbidden", "code_len": 2467}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9914, "tout": 1252, "ts": 1791525288.767836, "chk": "ok", "code_len": 2265}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 11278, "tout": 107, "ts": 1791525313.9489658, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 11409, "tout": 1134, "ts": 1791525323.6523123, "chk": null, "code_len": 2265}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["forbidden", "ok", "no_code", null], "first_tin": 5493, "started": 1791525239.8640115}
{"ep": "ok-00715", "task": "L2_033", "reader": "claude-opus-5-5", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 1.007, "speedup": 1.007, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 117.1, "calls": 2, "tokens_in": 9959, "tokens_out": 7296, "ctx_chars": 3636, "t_end": 1791525362.8770676, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.007, "lo95": 1.0065, "mean": 1.0075, "ev_only": 1.0096, "ref_ms": 8.01691, "cand_ms": 7.96114, "n_trials": 126, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0062, "r_wall_s": 40.18, "compile_s": 2.01, "r_error": "", "src_len": 5907, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3285, "tout": 4299, "ts": 1791525279.3585887, "chk": "ok", "code_len": 5937}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 6674, "tout": 2997, "ts": 1791525322.604896, "chk": null, "code_len": 5907}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 3285, "started": 1791525245.7609882}
{"ep": "ok-00708", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 1.7744, "speedup": 1.7744, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 143.8, "calls": 3, "tokens_in": 35263, "tokens_out": 11037, "ctx_chars": 16078, "t_end": 1791525375.3454626, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.7744, "lo95": 1.7735, "mean": 1.7733, "ev_only": 1.7758, "ref_ms": 22.29218, "cand_ms": 12.56304, "n_trials": 68, "fast1": true, "flags": [], "backend": "triton", "own_frac": 1.0, "r_wall_s": 30.01, "compile_s": 1.97, "r_error": "", "src_len": 4585, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 8865, "tout": 5369, "ts": 1791525281.6040363, "chk": "runtime_error", "code_len": 4569}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11880, "tout": 3179, "ts": 1791525312.9372768, "chk": "ok", "code_len": 4585}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14518, "tout": 2489, "ts": 1791525345.1305315, "chk": null, "code_len": 4585}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["runtime_error", "ok", null], "first_tin": 8865, "started": 1791525231.5853696}
{"ep": "ok-00707", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 1.0039, "speedup": 1.0039, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 162.5, "calls": 5, "tokens_in": 23857, "tokens_out": 9219, "ctx_chars": 0, "t_end": 1791525388.0231297, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.0039, "lo95": 1.0037, "mean": 1.0036, "ev_only": 1.0046, "ref_ms": 7.96105, "cand_ms": 7.93013, "n_trials": 141, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 13.97, "compile_s": 2.14, "r_error": "", "src_len": 972, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1683, "tout": 2661, "ts": 1791525249.0619001, "chk": "incorrect", "code_len": 2660}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3527, "tout": 2739, "ts": 1791525288.4715922, "chk": "incorrect", "code_len": 2674}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 1915, "ts": 1791525330.5929158, "chk": "incorrect", "code_len": 1108}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 6229, "tout": 1200, "ts": 1791525351.247213, "chk": "ok", "code_len": 972}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 7087, "tout": 704, "ts": 1791525374.0249026, "chk": null, "code_len": 972}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 1683, "started": 1791525225.5189273}
{"ep": "ok-00699", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_tables_select", "policy": "online", "store": null, "status": "ok", "score": 0.7627, "speedup": 0.7627, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 187.9, "calls": 5, "tokens_in": 55606, "tokens_out": 11081, "ctx_chars": 5802, "t_end": 1791525390.5726595, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.7627, "lo95": 0.7602, "mean": 0.7666, "ev_only": 0.7626, "ref_ms": 16.34148, "cand_ms": 21.4249, "n_trials": 62, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0578, "r_wall_s": 25.04, "compile_s": 1.98, "r_error": "", "src_len": 4565, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5331, "tout": 3181, "ts": 1791525249.5103526, "chk": "incorrect", "code_len": 6343}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8645, "tout": 3394, "ts": 1791525290.7362332, "chk": "incorrect", "code_len": 6571}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12171, "tout": 2399, "ts": 1791525337.448798, "chk": "ok", "code_len": 4565}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14679, "tout": 54, "ts": 1791525348.4749246, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 14780, "tout": 2053, "ts": 1791525365.5081527, "chk": null, "code_len": 4565}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5331, "started": 1791525222.9897473}
{"ep": "ok-00682", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.8136, "speedup": 0.8136, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 253.6, "calls": 5, "tokens_in": 49470, "tokens_out": 10960, "ctx_chars": 495, "t_end": 1791525393.5549157, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 0.8136, "lo95": 0.8122, "mean": 0.8049, "ev_only": 0.8136, "ref_ms": 16.56163, "cand_ms": 20.35641, "n_trials": 68, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0449, "r_wall_s": 34.04, "compile_s": 11.71, "r_error": "", "src_len": 4450, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3050, "tout": 4044, "ts": 1791525195.387334, "chk": "compile_error", "code_len": 5808}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8369, "tout": 2574, "ts": 1791525267.8926046, "chk": "incorrect", "code_len": 5842}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 11074, "tout": 2199, "ts": 1791525314.3032537, "chk": "ok", "code_len": 4450}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 13382, "tout": 166, "ts": 1791525343.349286, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 13595, "tout": 1977, "ts": 1791525359.4921718, "chk": null, "code_len": 4450}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "incorrect", "ok", "no_code", null], "first_tin": 3050, "started": 1791525160.3299625}
{"ep": "ok-00693", "task": "L3_023", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.2429, "speedup": 1.2429, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 215.3, "calls": 2, "tokens_in": 11219, "tokens_out": 20466, "ctx_chars": 0, "t_end": 1791525397.6738179, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.2429, "lo95": 1.2407, "mean": 1.28, "ev_only": 1.2481, "ref_ms": 3.32796, "cand_ms": 2.67755, "n_trials": 194, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.9911, "r_wall_s": 26.1, "compile_s": 1.9, "r_error": "", "src_len": 10437, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2628, "tout": 14985, "ts": 1791525312.160341, "chk": "ok", "code_len": 10452}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8591, "tout": 5481, "ts": 1791525371.5310643, "chk": null, "code_len": 10437}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 2628, "started": 1791525182.3345702}
{"ep": "ok-00692", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "organ_select", "policy": "online", "store": null, "status": "ok", "score": 0.7626, "speedup": 0.7626, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 217.0, "calls": 4, "tokens_in": 46544, "tokens_out": 19559, "ctx_chars": 6861, "t_end": 1791525398.7689216, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7626, "lo95": 0.7597, "mean": 0.7625, "ev_only": 0.7636, "ref_ms": 17.14477, "cand_ms": 22.48294, "n_trials": 63, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0338, "r_wall_s": 14.59, "compile_s": 1.99, "r_error": "", "src_len": 3729, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5693, "tout": 10049, "ts": 1791525270.6337225, "chk": "incorrect", "code_len": 7919}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10135, "tout": 4932, "ts": 1791525324.618999, "chk": "incorrect", "code_len": 7936}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 14346, "tout": 2458, "ts": 1791525360.0144665, "chk": "ok", "code_len": 3729}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 16370, "tout": 2120, "ts": 1791525384.1525698, "chk": null, "code_len": 3729}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 5693, "started": 1791525181.7728653}
{"ep": "ok-00676", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0041, "speedup": 1.0041, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 312.1, "calls": 3, "tokens_in": 239612, "tokens_out": 9369, "ctx_chars": 182830, "t_end": 1791525400.6263936, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 1.0041, "lo95": 1.0037, "mean": 1.0041, "ev_only": 1.0047, "ref_ms": 7.91783, "cand_ms": 7.88523, "n_trials": 159, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0003, "r_wall_s": 65.81, "compile_s": 41.42, "r_error": "", "src_len": 1689, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78250, "tout": 3541, "ts": 1791525146.6233315, "chk": "incorrect", "code_len": 2706}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 80030, "tout": 4330, "ts": 1791525240.683339, "chk": "ok", "code_len": 1689}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 81332, "tout": 1498, "ts": 1791525334.7748797, "chk": null, "code_len": 1689}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78250, "started": 1791525088.5709968}
{"ep": "ok-00709", "task": "L3_040", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.1181, "speedup": 0.1181, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 165.5, "calls": 4, "tokens_in": 28565, "tokens_out": 8336, "ctx_chars": 0, "t_end": 1791525401.7754776, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.1181, "lo95": 0.1179, "mean": 0.1218, "ev_only": 0.118, "ref_ms": 31.95861, "cand_ms": 270.52023, "n_trials": 9, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.2988, "r_wall_s": 26.96, "compile_s": 11.01, "r_error": "", "src_len": 4542, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1949, "tout": 4204, "ts": 1791525273.8918066, "chk": "compile_error", "code_len": 4482}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7405, "tout": 2024, "ts": 1791525339.5610156, "chk": "ok", "code_len": 4542}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9541, "tout": 105, "ts": 1791525358.24395, "chk": "no_code", "code_len": 0}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 9670, "tout": 2003, "ts": 1791525374.7949328, "chk": null, "code_len": 4542}], "n_turns": 4, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "ok", "no_code", null], "first_tin": 1949, "started": 1791525236.264339}
{"ep": "ok-00662", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 5.7398, "speedup": 5.7398, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 371.1, "calls": 2, "tokens_in": 164624, "tokens_out": 28166, "ctx_chars": 182830, "t_end": 1791525417.949381, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 5.7398, "lo95": 5.723, "mean": 5.7342, "ev_only": 5.8513, "ref_ms": 4.07098, "cand_ms": 0.70926, "n_trials": 194, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.1697, "r_wall_s": 50.33, "compile_s": 42.13, "r_error": "", "src_len": 12024, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78925, "tout": 21328, "ts": 1791525240.654272, "chk": "ok", "code_len": 12024}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 85699, "tout": 6838, "ts": 1791525367.588924, "chk": null, "code_len": 12024}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78925, "started": 1791525046.828149}
{"ep": "ok-00686", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 0.8085, "speedup": 0.8085, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 269.4, "calls": 4, "tokens_in": 41944, "tokens_out": 23346, "ctx_chars": 495, "t_end": 1791525420.262749, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.8085, "lo95": 0.804, "mean": 0.8292, "ev_only": 0.8086, "ref_ms": 16.20464, "cand_ms": 20.043, "n_trials": 60, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0314, "r_wall_s": 28.53, "compile_s": 11.57, "r_error": "", "src_len": 4810, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 3052, "tout": 11032, "ts": 1791525246.7380934, "chk": "incorrect", "code_len": 10572}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8490, "tout": 6375, "ts": 1791525310.9774036, "chk": "incorrect", "code_len": 10551}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 13878, "tout": 3218, "ts": 1791525354.1758657, "chk": "ok", "code_len": 4810}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 16524, "tout": 2721, "ts": 1791525391.7110207, "chk": null, "code_len": 4810}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 3052, "started": 1791525150.8641374}
{"ep": "ok-00675", "task": "L3_023", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.3029, "speedup": 0.3029, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 352.3, "calls": 3, "tokens_in": 20122, "tokens_out": 4154, "ctx_chars": 6417, "t_end": 1791525431.0095453, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.3029, "lo95": 0.3018, "mean": 0.3037, "ev_only": 0.3014, "ref_ms": 3.42006, "cand_ms": 11.29179, "n_trials": 112, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0738, "r_wall_s": 21.4, "compile_s": 2.03, "r_error": "", "src_len": 4027, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5212, "tout": 2090, "ts": 1791525096.261036, "chk": "ok", "code_len": 4090}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 7414, "tout": 58, "ts": 1791525259.677684, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 7496, "tout": 2006, "ts": 1791525276.0230508, "chk": null, "code_len": 4027}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 5212, "started": 1791525078.7037067}
{"ep": "ok-00690", "task": "L2_022", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.3631, "speedup": 1.3631, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 288.6, "calls": 3, "tokens_in": 243672, "tokens_out": 12142, "ctx_chars": 182830, "t_end": 1791525453.5408745, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.3631, "lo95": 1.3628, "mean": 1.3632, "ev_only": 1.3648, "ref_ms": 8.24757, "cand_ms": 6.05046, "n_trials": 186, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.8661, "r_wall_s": 23.45, "compile_s": 1.86, "r_error": "", "src_len": 4322, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78369, "tout": 4466, "ts": 1791525204.6864867, "chk": "incorrect", "code_len": 4203}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 81218, "tout": 4412, "ts": 1791525252.142669, "chk": "ok", "code_len": 4537}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 84085, "tout": 3264, "ts": 1791525295.6960378, "chk": null, "code_len": 4322}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 78369, "started": 1791525164.9010117}
{"ep": "ok-00640", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 0.8089, "speedup": 0.8089, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 490.8, "calls": 5, "tokens_in": 45654, "tokens_out": 10199, "ctx_chars": 0, "t_end": 1791525455.3710194, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 0.8089, "lo95": 0.8037, "mean": 0.8121, "ev_only": 0.8088, "ref_ms": 16.35227, "cand_ms": 20.2166, "n_trials": 64, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0392, "r_wall_s": 21.19, "compile_s": 10.79, "r_error": "", "src_len": 4196, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2917, "tout": 2991, "ts": 1791524990.15543, "chk": "compile_error", "code_len": 6348}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 7144, "tout": 2884, "ts": 1791525098.0199213, "chk": "incorrect", "code_len": 6297}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 10159, "tout": 2389, "ts": 1791525245.61519, "chk": "ok", "code_len": 4196}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 12657, "tout": 73, "ts": 1791525282.407269, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 12777, "tout": 1862, "ts": 1791525298.0448537, "chk": null, "code_len": 4196}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["compile_error", "incorrect", "ok", "no_code", null], "first_tin": 2917, "started": 1791524964.6074543}
{"ep": "ok-00695", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 5.997, "speedup": 5.997, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 279.3, "calls": 3, "tokens_in": 26013, "tokens_out": 28274, "ctx_chars": 369, "t_end": 1791525463.6561944, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 5.997, "lo95": 5.9791, "mean": 5.9712, "ev_only": 6.0999, "ref_ms": 4.08041, "cand_ms": 0.68041, "n_trials": 213, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9961, "r_wall_s": 19.76, "compile_s": 11.44, "r_error": "", "src_len": 11602, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2478, "tout": 16608, "ts": 1791525332.9738736, "chk": "no_custom_kernel", "code_len": 11812}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8870, "tout": 6091, "ts": 1791525390.445317, "chk": "ok", "code_len": 11602}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14665, "tout": 5575, "ts": 1791525443.870392, "chk": null, "code_len": 11602}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2478, "started": 1791525184.3426986}
{"ep": "ok-00624", "task": "L3_010", "reader": "claude-opus-4-8", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.6236, "speedup": 0.6236, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 557.6, "calls": 5, "tokens_in": 56807, "tokens_out": 11103, "ctx_chars": 6417, "t_end": 1791525474.1388545, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.6236, "lo95": 0.6203, "mean": 0.648, "ev_only": 0.6242, "ref_ms": 16.51381, "cand_ms": 26.47934, "n_trials": 56, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0534, "r_wall_s": 15.38, "compile_s": 1.9, "r_error": "", "src_len": 4244, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5503, "tout": 3143, "ts": 1791524942.3153448, "chk": "incorrect", "code_len": 6310}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8779, "tout": 3530, "ts": 1791525120.3936212, "chk": "incorrect", "code_len": 6500}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 12441, "tout": 2442, "ts": 1791525299.0720818, "chk": "ok", "code_len": 4244}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 14992, "tout": 53, "ts": 1791525309.6425836, "chk": "no_code", "code_len": 0}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 15092, "tout": 1935, "ts": 1791525325.366675, "chk": null, "code_len": 4244}], "n_turns": 5, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", "no_code", null], "first_tin": 5503, "started": 1791524916.5784535}
{"ep": "ok-00705", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 7.6355, "speedup": 7.6355, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 260.7, "calls": 3, "tokens_in": 33547, "tokens_out": 24170, "ctx_chars": 10587, "t_end": 1791525476.9684334, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 7.6355, "lo95": 7.6094, "mean": 7.6743, "ev_only": 7.6751, "ref_ms": 31.81656, "cand_ms": 4.16692, "n_trials": 54, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9744, "r_wall_s": 19.8, "compile_s": 11.0, "r_error": "", "src_len": 8642, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 6364, "tout": 14545, "ts": 1791525345.532684, "chk": "no_custom_kernel", "code_len": 8667}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 11340, "tout": 4906, "ts": 1791525399.8581467, "chk": "ok", "code_len": 8642}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15843, "tout": 4719, "ts": 1791525457.138169, "chk": null, "code_len": 8642}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 6364, "started": 1791525216.2839248}
{"ep": "ok-00680", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 1.004, "speedup": 1.004, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 373.8, "calls": 4, "tokens_in": 16690, "tokens_out": 7269, "ctx_chars": 1080, "t_end": 1791525490.617981, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 3, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 1.004, "lo95": 1.0038, "mean": 1.019, "ev_only": 1.0047, "ref_ms": 7.96445, "cand_ms": 7.9324, "n_trials": 161, "fast1": true, "flags": [], "backend": "triton", "own_frac": 0.0003, "r_wall_s": 13.67, "compile_s": 1.89, "r_error": "", "src_len": 1021, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2118, "tout": 2211, "ts": 1791525136.0512414, "chk": "incorrect", "code_len": 2189}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 3814, "tout": 3098, "ts": 1791525308.9610841, "chk": "incorrect", "code_len": 1098}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 4913, "tout": 1376, "ts": 1791525463.4820697, "chk": "ok", "code_len": 1021}, {"turn": 3, "action": "SUBMIT", "stop": "end_turn", "tin": 5845, "tout": 584, "ts": 1791525476.8954954, "chk": null, "code_len": 1021}], "n_turns": 4, "n_check": 3, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "ok", null], "first_tin": 2118, "started": 1791525116.789644}
{"ep": "ok-00696", "task": "L3_032", "reader": "claude-opus-4-8", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 0.9367, "speedup": 0.9367, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 299.7, "calls": 3, "tokens_in": 22110, "tokens_out": 6509, "ctx_chars": 4637, "t_end": 1791525495.0300927, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.9367, "lo95": 0.9346, "mean": 0.9354, "ev_only": 0.9374, "ref_ms": 4.05858, "cand_ms": 4.33301, "n_trials": 208, "fast1": false, "flags": [], "backend": "cuda", "own_frac": 0.0283, "r_wall_s": 48.56, "compile_s": 39.33, "r_error": "", "src_len": 3429, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4066, "tout": 4815, "ts": 1791525237.9870772, "chk": "ok", "code_len": 3429}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 8993, "tout": 34, "ts": 1791525298.3628113, "chk": "no_code", "code_len": 0}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 9051, "tout": 1660, "ts": 1791525312.5166678, "chk": null, "code_len": 3429}], "n_turns": 3, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", "no_code", null], "first_tin": 4066, "started": 1791525195.329626}
{"ep": "ok-00678", "task": "L2_014", "reader": "claude-opus-4-8", "arm": "provenance", "policy": "online", "store": null, "status": "incorrect", "score": 0.0, "speedup": 0.0, "correct": false, "infra": false, "infra_reruns": 0, "wall_s": 398.0, "calls": 5, "tokens_in": 37856, "tokens_out": 4485, "ctx_chars": 9192, "t_end": 1791525501.9116762, "error": "outputs produced during timing do not match the reference (output mismatch beyond atol=rtol=0.0001); results must not be cached or skipped", "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": "triton", "own_frac": 0.003, "r_wall_s": 12.72, "compile_s": 1.84, "r_error": "outputs produced during timing do not match the reference (output mismatch beyond atol=rtol=0.0001); results must not be cached or skipped", "src_len": 1038, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5631, "tout": 578, "ts": 1791525110.335953, "chk": "incorrect", "code_len": 1053}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6342, "tout": 1375, "ts": 1791525292.7456417, "chk": "incorrect", "code_len": 926}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 7850, "tout": 609, "ts": 1791525320.912836, "chk": "incorrect", "code_len": 1023}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8593, "tout": 690, "ts": 1791525469.5655906, "chk": "incorrect", "code_len": 951}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9440, "tout": 1233, "ts": 1791525489.166928, "chk": null, "code_len": 1038}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "incorrect", null], "first_tin": 5631, "started": 1791525103.8794303}
{"ep": "ok-00717", "task": "L3_040", "reader": "claude-opus-5-5", "arm": "show_all", "policy": "online", "store": null, "status": "ok", "score": 6.9873, "speedup": 6.9873, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 283.0, "calls": 3, "tokens_in": 31898, "tokens_out": 28245, "ctx_chars": 8224, "t_end": 1791525536.3312848, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 6.9873, "lo95": 6.9731, "mean": 6.9825, "ev_only": 7.0073, "ref_ms": 31.90217, "cand_ms": 4.56573, "n_trials": 46, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 19.27, "compile_s": 10.89, "r_error": "", "src_len": 9135, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 5495, "tout": 18274, "ts": 1791525417.0336843, "chk": "no_custom_kernel", "code_len": 9160}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 10785, "tout": 5170, "ts": 1791525469.6027517, "chk": "ok", "code_len": 9135}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15618, "tout": 4801, "ts": 1791525517.0363834, "chk": null, "code_len": 9135}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 5495, "started": 1791525253.2922845}
{"ep": "ok-00713", "task": "L2_050", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 10.0, "speedup": 83.2035, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 311.8, "calls": 2, "tokens_in": 160323, "tokens_out": 8631, "ctx_chars": 182830, "t_end": 1791525555.3022435, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-20", "gpu": 0, "r_speedup": 83.2035, "lo95": 81.4818, "mean": 78.7574, "ev_only": 88.2525, "ref_ms": 22.25494, "cand_ms": 0.26748, "n_trials": 71, "fast1": true, "flags": ["excessive_speedup>10.0x: audit"], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 59.77, "compile_s": 39.68, "r_error": "", "src_len": 5825, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78396, "tout": 5472, "ts": 1791525290.3681912, "chk": "ok", "code_len": 5825}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81927, "tout": 3159, "ts": 1791525495.3317406, "chk": null, "code_len": 5825}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78396, "started": 1791525243.5332}
{"ep": "ok-00671", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "annotated_all", "policy": "online", "store": null, "status": "ok", "score": 6.5574, "speedup": 6.5574, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 527.0, "calls": 3, "tokens_in": 37036, "tokens_out": 42863, "ctx_chars": 4637, "t_end": 1791525594.1745322, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 6.5574, "lo95": 6.5281, "mean": 6.5015, "ev_only": 6.6717, "ref_ms": 4.00899, "cand_ms": 0.61137, "n_trials": 201, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9893, "r_wall_s": 18.58, "compile_s": 10.41, "r_error": "", "src_len": 14438, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 4068, "tout": 26653, "ts": 1791525302.278273, "chk": "no_custom_kernel", "code_len": 14680}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 12513, "tout": 8191, "ts": 1791525373.2363033, "chk": "ok", "code_len": 14438}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 20455, "tout": 8019, "ts": 1791525575.528231, "chk": null, "code_len": 14438}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 4068, "started": 1791525067.1828883}
{"ep": "ok-00710", "task": "L2_014", "reader": "claude-opus-5-5", "arm": "prior", "policy": "online", "store": null, "status": "ok", "score": 1.0039, "speedup": 1.0039, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 357.6, "calls": 5, "tokens_in": 31214, "tokens_out": 14580, "ctx_chars": 495, "t_end": 1791525594.3953302, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 4, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 1.0039, "lo95": 1.0036, "mean": 1.0035, "ev_only": 1.0045, "ref_ms": 7.93267, "cand_ms": 7.90178, "n_trials": 158, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0003, "r_wall_s": 21.59, "compile_s": 11.2, "r_error": "", "src_len": 1639, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 1816, "tout": 3871, "ts": 1791525269.689298, "chk": "incorrect", "code_len": 3948}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 4278, "tout": 4916, "ts": 1791525338.5521946, "chk": "incorrect", "code_len": 4110}, {"turn": 2, "action": "CHECK", "stop": "end_turn", "tin": 6804, "tout": 2974, "ts": 1791525383.281411, "chk": "incorrect", "code_len": 2318}, {"turn": 3, "action": "CHECK", "stop": "end_turn", "tin": 8519, "tout": 1720, "ts": 1791525547.4510355, "chk": "ok", "code_len": 1639}, {"turn": 4, "action": "SUBMIT", "stop": "end_turn", "tin": 9797, "tout": 1099, "ts": 1791525572.7827337, "chk": null, "code_len": 1639}], "n_turns": 5, "n_check": 4, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "incorrect", "incorrect", "ok", null], "first_tin": 1816, "started": 1791525236.8065186}
{"ep": "ok-00719", "task": "L2_061", "reader": "claude-opus-5-5", "arm": "ace", "policy": "online", "store": null, "status": "ok", "score": 1.0361, "speedup": 1.0361, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 356.6, "calls": 2, "tokens_in": 159882, "tokens_out": 7728, "ctx_chars": 182830, "t_end": 1791525615.729736, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 1, "resumed": false, "endpoint": "endpoint-21", "gpu": 0, "r_speedup": 1.0361, "lo95": 1.0355, "mean": 1.0877, "ev_only": 1.0364, "ref_ms": 29.67007, "cand_ms": 28.63552, "n_trials": 38, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.0207, "r_wall_s": 86.88, "compile_s": 38.73, "r_error": "", "src_len": 5280, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 78312, "tout": 4845, "ts": 1791525301.1754105, "chk": "ok", "code_len": 5280}, {"turn": 1, "action": "SUBMIT", "stop": "end_turn", "tin": 81570, "tout": 2883, "ts": 1791525392.265302, "chk": null, "code_len": 5280}], "n_turns": 2, "n_check": 1, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["ok", null], "first_tin": 78312, "started": 1791525259.0877802}
{"ep": "ok-00714", "task": "L3_010", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 0.7437, "speedup": 0.7437, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 387.5, "calls": 3, "tokens_in": 18614, "tokens_out": 10528, "ctx_chars": 0, "t_end": 1791525632.603011, "error": "ok", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 0.7437, "lo95": 0.7424, "mean": 0.7446, "ev_only": 0.744, "ref_ms": 16.34406, "cand_ms": 21.97589, "n_trials": 67, "fast1": false, "flags": [], "backend": "triton", "own_frac": 0.0335, "r_wall_s": 13.78, "compile_s": 1.89, "r_error": "", "src_len": 3566, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2919, "tout": 6226, "ts": 1791525297.7125134, "chk": "incorrect", "code_len": 6627}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 6843, "tout": 2575, "ts": 1791525465.471661, "chk": "ok", "code_len": 3632}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 8852, "tout": 1727, "ts": 1791525618.798692, "chk": null, "code_len": 3566}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["incorrect", "ok", null], "first_tin": 2919, "started": 1791525245.1064062}
{"ep": "ok-00649", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "opus_digest_select", "policy": "online", "store": null, "status": "ok", "score": 5.4235, "speedup": 5.4235, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 699.3, "calls": 3, "tokens_in": 25770, "tokens_out": 28975, "ctx_chars": 369, "t_end": 1791525693.9229095, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-22", "gpu": 0, "r_speedup": 5.4235, "lo95": 5.4076, "mean": 5.3986, "ev_only": 5.4985, "ref_ms": 4.02832, "cand_ms": 0.74275, "n_trials": 194, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 0.9916, "r_wall_s": 19.48, "compile_s": 11.4, "r_error": "", "src_len": 10396, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2478, "tout": 17736, "ts": 1791525151.0065567, "chk": "no_custom_kernel", "code_len": 10615}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 8773, "tout": 5715, "ts": 1791525351.832341, "chk": "ok", "code_len": 10396}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 14519, "tout": 5524, "ts": 1791525674.4210172, "chk": null, "code_len": 10396}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2478, "started": 1791524994.6558073}
{"ep": "ok-00711", "task": "L3_032", "reader": "claude-opus-5-5", "arm": "bare", "policy": "online", "store": null, "status": "ok", "score": 7.2076, "speedup": 7.2076, "correct": true, "infra": false, "infra_reruns": 0, "wall_s": 468.1, "calls": 3, "tokens_in": 27732, "tokens_out": 33734, "ctx_chars": 0, "t_end": 1791525706.011594, "error": "", "f_status": "ok", "f_error": "", "submit_turn": 2, "resumed": false, "endpoint": "endpoint-03", "gpu": 0, "r_speedup": 7.2076, "lo95": 7.1588, "mean": 7.0694, "ev_only": 7.3612, "ref_ms": 3.8914, "cand_ms": 0.5399, "n_trials": 179, "fast1": true, "flags": [], "backend": "cuda", "own_frac": 1.0, "r_wall_s": 18.84, "compile_s": 10.97, "r_error": "", "src_len": 11214, "atts": [{"turn": 0, "action": "CHECK", "stop": "end_turn", "tin": 2358, "tout": 20313, "ts": 1791525415.0249028, "chk": "no_custom_kernel", "code_len": 11440}, {"turn": 1, "action": "CHECK", "stop": "end_turn", "tin": 9440, "tout": 7077, "ts": 1791525479.278807, "chk": "ok", "code_len": 11214}, {"turn": 2, "action": "SUBMIT", "stop": "end_turn", "tin": 15934, "tout": 6344, "ts": 1791525687.1262236, "chk": null, "code_len": 11214}], "n_turns": 3, "n_check": 2, "max_tok_hits": 0, "stops": ["end_turn"], "chk_statuses": ["no_custom_kernel", "ok", null], "first_tin": 2358, "started": 1791525237.9113932}