{"ep": "h2-00040", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "forbidden", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "static check failed: line 87: getattr needs a literal, non-private attribute name; line 88: getattr needs a literal, non-private attribute name; line 89: getattr needs a literal, non-private attribute name; line 90: getattr needs a literal, non-private attribute name", "wall_s": 29.3, "calls": 1, "tokens_in": 1964, "tokens_out": 2207, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533678.6238859}
{"ep": "h2-00036", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0071, "status": "ok", "correct": true, "speedup": 1.0071, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 32.1, "calls": 1, "tokens_in": 6367, "tokens_out": 544, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791533681.3513434}
{"ep": "h2-00045", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0065, "status": "ok", "correct": true, "speedup": 1.0065, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 38.2, "calls": 1, "tokens_in": 6367, "tokens_out": 540, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791533687.4797099}
{"ep": "h2-00049", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7712, "status": "ok", "correct": true, "speedup": 0.7712, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 52.4, "calls": 3, "tokens_in": 19133, "tokens_out": 1896, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791533701.6443832}
{"ep": "h2-00016", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0539, "status": "ok", "correct": true, "speedup": 1.0539, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 54.6, "calls": 3, "tokens_in": 22602, "tokens_out": 2236, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791533703.9076455}
{"ep": "h2-00001", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0059, "status": "ok", "correct": true, "speedup": 1.0059, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 59.9, "calls": 2, "tokens_in": 4021, "tokens_out": 2043, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533709.1684303}
{"ep": "h2-00046", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0037, "status": "ok", "correct": true, "speedup": 1.0037, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 60.8, "calls": 3, "tokens_in": 23795, "tokens_out": 2581, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791533710.135085}
{"ep": "h2-00056", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0212, "status": "ok", "correct": true, "speedup": 1.0212, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 61.9, "calls": 2, "tokens_in": 4617, "tokens_out": 2280, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533711.1532133}
{"ep": "h2-00034", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'fuse_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/", "wall_s": 63.3, "calls": 1, "tokens_in": 1723, "tokens_out": 978, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533712.5358968}
{"ep": "h2-00013", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6433, "status": "ok", "correct": true, "speedup": 0.6433, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 64.5, "calls": 2, "tokens_in": 15352, "tokens_out": 3261, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791533713.8201044}
{"ep": "h2-00030", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8852, "status": "ok", "correct": true, "speedup": 0.8852, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 65.7, "calls": 3, "tokens_in": 18997, "tokens_out": 1679, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791533714.9944487}
{"ep": "h2-00022", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7916, "status": "ok", "correct": true, "speedup": 0.7916, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 66.5, "calls": 4, "tokens_in": 29576, "tokens_out": 1463, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791533715.812234}
{"ep": "h2-00015", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0036, "status": "ok", "correct": true, "speedup": 1.0036, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 67.0, "calls": 2, "tokens_in": 17298, "tokens_out": 4566, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791533716.2444172}
{"ep": "h2-00007", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0227, "status": "ok", "correct": true, "speedup": 1.0227, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 80.7, "calls": 3, "tokens_in": 15465, "tokens_out": 2441, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791533729.9671552}
{"ep": "h2-00062", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9989, "status": "ok", "correct": true, "speedup": 0.9989, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 80.7, "calls": 2, "tokens_in": 13705, "tokens_out": 1179, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791533729.9847534}
{"ep": "h2-00051", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8558, "status": "ok", "correct": true, "speedup": 0.8558, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 80.9, "calls": 3, "tokens_in": 19089, "tokens_out": 1754, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791533730.1453485}
{"ep": "h2-00048", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0643, "status": "ok", "correct": true, "speedup": 1.0643, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.4, "calls": 3, "tokens_in": 23326, "tokens_out": 2737, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791533730.7150457}
{"ep": "h2-00044", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0183, "status": "ok", "correct": true, "speedup": 1.0183, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.9, "calls": 3, "tokens_in": 24881, "tokens_out": 2288, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791533731.1739185}
{"ep": "h2-00037", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7159, "status": "ok", "correct": true, "speedup": 0.7159, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 82.4, "calls": 2, "tokens_in": 16327, "tokens_out": 3810, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791533731.724488}
{"ep": "h2-00058", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0031, "status": "ok", "correct": true, "speedup": 1.0031, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 84.3, "calls": 3, "tokens_in": 23960, "tokens_out": 2692, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791533733.6331742}
{"ep": "h2-00039", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9378, "status": "ok", "correct": true, "speedup": 0.9378, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 90.8, "calls": 2, "tokens_in": 17201, "tokens_out": 4844, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791533740.1108382}
{"ep": "h2-00000", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5494, "status": "ok", "correct": true, "speedup": 1.5494, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 90.9, "calls": 2, "tokens_in": 5188, "tokens_out": 4301, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533740.1600866}
{"ep": "h2-00059", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3452, "status": "ok", "correct": true, "speedup": 2.3452, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 94.2, "calls": 2, "tokens_in": 13717, "tokens_out": 4437, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791533743.4425619}
{"ep": "h2-00061", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.016, "status": "ok", "correct": true, "speedup": 1.016, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 94.5, "calls": 3, "tokens_in": 25227, "tokens_out": 2507, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791533743.772406}
{"ep": "h2-00057", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9756, "status": "ok", "correct": true, "speedup": 0.9756, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 95.6, "calls": 1, "tokens_in": 7032, "tokens_out": 1156, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791533744.8943644}
{"ep": "h2-00017", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.754, "status": "ok", "correct": true, "speedup": 0.754, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 96.3, "calls": 2, "tokens_in": 12111, "tokens_out": 1550, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791533745.5235782}
{"ep": "h2-00010", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0626, "status": "ok", "correct": true, "speedup": 1.0626, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 97.0, "calls": 1, "tokens_in": 4605, "tokens_out": 1161, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533746.267331}
{"ep": "h2-00025", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8849, "status": "ok", "correct": true, "speedup": 0.8849, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 99.2, "calls": 2, "tokens_in": 4781, "tokens_out": 2610, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533748.5028522}
{"ep": "h2-00009", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0152, "status": "ok", "correct": true, "speedup": 1.0152, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 102.4, "calls": 3, "tokens_in": 24728, "tokens_out": 2188, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791533751.6785705}
{"ep": "h2-00029", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0054, "status": "ok", "correct": true, "speedup": 1.0054, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 103.9, "calls": 3, "tokens_in": 20113, "tokens_out": 2774, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791533753.1778765}
{"ep": "h2-00043", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0093, "status": "ok", "correct": true, "speedup": 1.0093, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 104.7, "calls": 3, "tokens_in": 25332, "tokens_out": 2590, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791533754.0171568}
{"ep": "h2-00038", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.325, "status": "ok", "correct": true, "speedup": 1.325, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 106.5, "calls": 1, "tokens_in": 5998, "tokens_out": 735, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791533755.8085637}
{"ep": "h2-00019", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.01, "status": "ok", "correct": true, "speedup": 1.01, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 107.1, "calls": 2, "tokens_in": 16203, "tokens_out": 2577, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791533756.3399673}
{"ep": "h2-00011", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0514, "status": "ok", "correct": true, "speedup": 1.0514, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 108.8, "calls": 3, "tokens_in": 18684, "tokens_out": 3801, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533758.0351768}
{"ep": "h2-00002", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0049, "status": "ok", "correct": true, "speedup": 1.0049, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 109.4, "calls": 1, "tokens_in": 1623, "tokens_out": 2097, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533758.7138653}
{"ep": "h2-00014", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9713, "status": "ok", "correct": true, "speedup": 0.9713, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 111.6, "calls": 2, "tokens_in": 12255, "tokens_out": 3112, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791533760.8258991}
{"ep": "h2-00050", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9979, "status": "ok", "correct": true, "speedup": 0.9979, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 111.8, "calls": 3, "tokens_in": 23097, "tokens_out": 3438, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791533761.1211636}
{"ep": "h2-00023", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9793, "status": "ok", "correct": true, "speedup": 0.9793, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 113.0, "calls": 2, "tokens_in": 12519, "tokens_out": 3656, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791533762.316682}
{"ep": "h2-00068", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7208, "status": "ok", "correct": true, "speedup": 0.7208, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 74.5, "calls": 1, "tokens_in": 6622, "tokens_out": 505, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791533778.402674}
{"ep": "h2-00070", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'pt_passthrough': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=pt_passthrough -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include", "wall_s": 71.1, "calls": 1, "tokens_in": 2181, "tokens_out": 1022, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533781.1865263}
{"ep": "h2-00063", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4591, "status": "ok", "correct": true, "speedup": 1.4591, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 139.5, "calls": 2, "tokens_in": 11216, "tokens_out": 5074, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533788.7697291}
{"ep": "h2-00052", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.993, "status": "ok", "correct": true, "speedup": 0.993, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 140.2, "calls": 3, "tokens_in": 26546, "tokens_out": 5371, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791533789.4504995}
{"ep": "h2-00066", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7122, "status": "ok", "correct": true, "speedup": 0.7122, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 105.7, "calls": 2, "tokens_in": 16364, "tokens_out": 3856, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791533793.148018}
{"ep": "h2-00026", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0653, "status": "ok", "correct": true, "speedup": 1.0653, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 145.7, "calls": 2, "tokens_in": 10510, "tokens_out": 2310, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533795.010232}
{"ep": "h2-00055", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9926, "status": "ok", "correct": true, "speedup": 0.9926, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 153.7, "calls": 3, "tokens_in": 24790, "tokens_out": 4031, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791533802.9974284}
{"ep": "h2-00041", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0258, "status": "ok", "correct": true, "speedup": 1.0258, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 157.8, "calls": 3, "tokens_in": 15531, "tokens_out": 6423, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791533807.075003}
{"ep": "h2-00031", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.6675, "status": "ok", "correct": true, "speedup": 3.6675, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 163.4, "calls": 2, "tokens_in": 6074, "tokens_out": 9514, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533812.6669052}
{"ep": "h2-00006", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0067, "status": "ok", "correct": true, "speedup": 1.0067, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 166.9, "calls": 2, "tokens_in": 5699, "tokens_out": 5876, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533816.1408408}
{"ep": "h2-00032", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7808, "status": "ok", "correct": true, "speedup": 2.7808, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 169.4, "calls": 2, "tokens_in": 13906, "tokens_out": 4387, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791533818.6598034}
{"ep": "h2-00035", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6064, "status": "ok", "correct": true, "speedup": 0.6064, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 169.4, "calls": 2, "tokens_in": 15280, "tokens_out": 11050, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533818.6958876}
{"ep": "h2-00008", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7915, "status": "ok", "correct": true, "speedup": 0.7915, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 172.9, "calls": 3, "tokens_in": 50140, "tokens_out": 14983, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791533822.2172344}
{"ep": "h2-00060", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0176, "status": "ok", "correct": true, "speedup": 1.0176, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 173.7, "calls": 2, "tokens_in": 15387, "tokens_out": 3233, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791533822.9989917}
{"ep": "h2-00077", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0081, "status": "ok", "correct": true, "speedup": 1.0081, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 97.7, "calls": 1, "tokens_in": 6367, "tokens_out": 545, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791533827.7004654}
{"ep": "h2-00099", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0625, "status": "ok", "correct": true, "speedup": 1.0625, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.3, "calls": 2, "tokens_in": 4925, "tokens_out": 4057, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533829.1418555}
{"ep": "h2-00065", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0069, "status": "ok", "correct": true, "speedup": 1.0069, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 150.8, "calls": 2, "tokens_in": 4118, "tokens_out": 2263, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533832.154856}
{"ep": "h2-00095", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0612, "status": "ok", "correct": true, "speedup": 1.0612, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 76.8, "calls": 2, "tokens_in": 14982, "tokens_out": 3562, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791533832.582637}
{"ep": "h2-00103", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'fuse_conv3d_act': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fuse_conv3d_act -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/inclu", "wall_s": 56.0, "calls": 1, "tokens_in": 1723, "tokens_out": 1115, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533837.2187164}
{"ep": "h2-00107", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0277, "status": "ok", "correct": true, "speedup": 1.0277, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 47.7, "calls": 2, "tokens_in": 4760, "tokens_out": 2466, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533842.6872501}
{"ep": "h2-00089", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.509, "status": "ok", "correct": true, "speedup": 5.509, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 100.4, "calls": 2, "tokens_in": 5935, "tokens_out": 8777, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533845.915913}
{"ep": "h2-00100", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5412, "status": "ok", "correct": true, "speedup": 0.5412, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 85.9, "calls": 3, "tokens_in": 21192, "tokens_out": 1010, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791533846.9826348}
{"ep": "h2-00098", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.4207, "status": "ok", "correct": true, "speedup": 2.4207, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 90.8, "calls": 2, "tokens_in": 12928, "tokens_out": 3883, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791533849.5308928}
{"ep": "h2-00012", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0196, "status": "ok", "correct": true, "speedup": 1.0196, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 204.9, "calls": 3, "tokens_in": 13281, "tokens_out": 8961, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533854.183165}
{"ep": "h2-00020", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3666, "status": "ok", "correct": true, "speedup": 1.3666, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 208.5, "calls": 2, "tokens_in": 16394, "tokens_out": 7138, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791533857.7544677}
{"ep": "h2-00102", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0079, "status": "ok", "correct": true, "speedup": 1.0079, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 83.5, "calls": 2, "tokens_in": 18245, "tokens_out": 4539, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791533861.9033878}
{"ep": "h2-00105", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0528, "status": "ok", "correct": true, "speedup": 1.0528, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 75.6, "calls": 2, "tokens_in": 11449, "tokens_out": 3175, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533865.0790184}
{"ep": "h2-00024", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0695, "status": "ok", "correct": true, "speedup": 1.0695, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 217.8, "calls": 2, "tokens_in": 28562, "tokens_out": 17943, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533867.0345907}
{"ep": "h2-00064", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.034, "status": "ok", "correct": true, "speedup": 1.034, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 189.5, "calls": 4, "tokens_in": 19950, "tokens_out": 5004, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533868.0951405}
{"ep": "h2-00113", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0012, "status": "ok", "correct": true, "speedup": 1.0012, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 53.9, "calls": 2, "tokens_in": 13463, "tokens_out": 1136, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791533872.591003}
{"ep": "h2-00101", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0079, "status": "ok", "correct": true, "speedup": 1.0079, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 115.0, "calls": 3, "tokens_in": 19853, "tokens_out": 2128, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791533877.317239}
{"ep": "h2-00072", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0406, "status": "ok", "correct": true, "speedup": 1.0406, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 166.3, "calls": 2, "tokens_in": 13177, "tokens_out": 2611, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791533878.8825011}
{"ep": "h2-00054", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9329, "status": "ok", "correct": true, "speedup": 0.9329, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 229.6, "calls": 2, "tokens_in": 14488, "tokens_out": 8404, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533878.8919432}
{"ep": "h2-00106", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.017, "status": "ok", "correct": true, "speedup": 1.017, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 86.9, "calls": 2, "tokens_in": 15594, "tokens_out": 3719, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791533880.011174}
{"ep": "h2-00086", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0181, "status": "ok", "correct": true, "speedup": 1.0181, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 150.8, "calls": 2, "tokens_in": 13639, "tokens_out": 5566, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791533894.2102656}
{"ep": "h2-00115", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'mish_tanh_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=mish_tanh_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/inclu", "wall_s": 72.0, "calls": 1, "tokens_in": 1666, "tokens_out": 767, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533894.9663093}
{"ep": "h2-00073", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0065, "status": "ok", "correct": true, "speedup": 1.0065, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 181.9, "calls": 2, "tokens_in": 4211, "tokens_out": 2139, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533895.6988146}
{"ep": "h2-00097", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8867, "status": "ok", "correct": true, "speedup": 0.8867, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 138.9, "calls": 2, "tokens_in": 14641, "tokens_out": 10298, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533896.897302}
{"ep": "h2-00090", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6346, "status": "ok", "correct": true, "speedup": 2.6346, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 152.3, "calls": 2, "tokens_in": 5844, "tokens_out": 6529, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533898.519243}
{"ep": "h2-00084", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8551, "status": "ok", "correct": true, "speedup": 0.8551, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 166.5, "calls": 1, "tokens_in": 7030, "tokens_out": 1213, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791533906.6439242}
{"ep": "h2-00018", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9987, "status": "ok", "correct": true, "speedup": 0.9987, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 257.4, "calls": 4, "tokens_in": 34465, "tokens_out": 3133, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791533906.7203655}
{"ep": "h2-00003", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.8562, "status": "ok", "correct": true, "speedup": 2.8562, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 258.1, "calls": 2, "tokens_in": 6961, "tokens_out": 8538, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533907.354147}
{"ep": "h2-00075", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0085, "status": "ok", "correct": true, "speedup": 1.0085, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 194.1, "calls": 1, "tokens_in": 6477, "tokens_out": 515, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791533909.9205499}
{"ep": "h2-00093", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8136, "status": "ok", "correct": true, "speedup": 0.8136, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 156.8, "calls": 1, "tokens_in": 1647, "tokens_out": 445, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533910.0007112}
{"ep": "h2-00033", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.1788, "status": "ok", "correct": true, "speedup": 4.1788, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 261.4, "calls": 2, "tokens_in": 8256, "tokens_out": 12231, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533910.6763413}
{"ep": "h2-00087", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0503, "status": "ok", "correct": true, "speedup": 1.0503, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 175.5, "calls": 1, "tokens_in": 4605, "tokens_out": 1154, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533919.246128}
{"ep": "h2-00074", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8291, "status": "ok", "correct": true, "speedup": 0.8291, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 212.5, "calls": 2, "tokens_in": 5812, "tokens_out": 5692, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533927.5179422}
{"ep": "h2-00027", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8081, "status": "ok", "correct": true, "speedup": 0.8081, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 278.9, "calls": 2, "tokens_in": 14059, "tokens_out": 7276, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533928.1450453}
{"ep": "h2-00119", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.058, "status": "ok", "correct": true, "speedup": 1.058, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 96.7, "calls": 3, "tokens_in": 22996, "tokens_out": 2465, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791533929.2704194}
{"ep": "h2-00071", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0129, "status": "ok", "correct": true, "speedup": 1.0129, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 220.8, "calls": 2, "tokens_in": 5585, "tokens_out": 5616, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533931.9846532}
{"ep": "h2-00092", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7074, "status": "ok", "correct": true, "speedup": 0.7074, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 190.7, "calls": 2, "tokens_in": 14266, "tokens_out": 1923, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791533942.3653123}
{"ep": "h2-00080", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6883, "status": "ok", "correct": true, "speedup": 0.6883, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 211.7, "calls": 2, "tokens_in": 13860, "tokens_out": 13714, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533942.3953354}
{"ep": "h2-00028", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.8835, "status": "ok", "correct": true, "speedup": 2.8835, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 296.1, "calls": 2, "tokens_in": 7726, "tokens_out": 13049, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533945.4213667}
{"ep": "h2-00042", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0287, "status": "ok", "correct": true, "speedup": 1.0287, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 297.3, "calls": 2, "tokens_in": 14079, "tokens_out": 6272, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791533946.6146872}
{"ep": "h2-00081", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0513, "status": "ok", "correct": true, "speedup": 1.0513, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 215.5, "calls": 2, "tokens_in": 11432, "tokens_out": 3126, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791533946.6251063}
{"ep": "h2-00079", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0427, "status": "ok", "correct": true, "speedup": 1.0427, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 222.6, "calls": 2, "tokens_in": 13021, "tokens_out": 2326, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791533952.7556581}
{"ep": "h2-00112", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0282, "status": "ok", "correct": true, "speedup": 1.0282, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 138.6, "calls": 2, "tokens_in": 4489, "tokens_out": 2314, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533957.2120297}
{"ep": "h2-00137", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8457, "status": "ok", "correct": true, "speedup": 0.8457, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 71.8, "calls": 1, "tokens_in": 7030, "tokens_out": 1211, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791533966.8116472}
{"ep": "h2-00122", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.326, "status": "ok", "correct": true, "speedup": 1.326, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 125.5, "calls": 1, "tokens_in": 5998, "tokens_out": 733, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791533971.4549634}
{"ep": "h2-00004", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.768, "status": "ok", "correct": true, "speedup": 6.768, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 334.8, "calls": 3, "tokens_in": 30360, "tokens_out": 24918, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791533984.1163528}
{"ep": "h2-00141", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0147, "status": "ok", "correct": true, "speedup": 1.0147, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 78.5, "calls": 3, "tokens_in": 14997, "tokens_out": 2437, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791533985.1527202}
{"ep": "h2-00138", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0123, "status": "ok", "correct": true, "speedup": 1.0123, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 97.2, "calls": 2, "tokens_in": 4140, "tokens_out": 2292, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533992.8557513}
{"ep": "h2-00145", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0171, "status": "ok", "correct": true, "speedup": 1.0171, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 85.7, "calls": 3, "tokens_in": 25367, "tokens_out": 2610, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791533995.7101128}
{"ep": "h2-00139", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0047, "status": "ok", "correct": true, "speedup": 1.0047, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 99.5, "calls": 1, "tokens_in": 6477, "tokens_out": 518, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791533996.403858}
{"ep": "h2-00133", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0114, "status": "ok", "correct": true, "speedup": 1.0114, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 118.9, "calls": 2, "tokens_in": 6441, "tokens_out": 7999, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791533997.7841272}
{"ep": "h2-00047", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4637, "status": "ok", "correct": true, "speedup": 1.4637, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 351.0, "calls": 2, "tokens_in": 15998, "tokens_out": 13821, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534000.241417}
{"ep": "h2-00078", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0036, "status": "ok", "correct": true, "speedup": 1.0036, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 270.3, "calls": 2, "tokens_in": 11408, "tokens_out": 1106, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791534000.2902095}
{"ep": "h2-00149", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0005, "status": "ok", "correct": true, "speedup": 1.0005, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 75.2, "calls": 2, "tokens_in": 11406, "tokens_out": 1121, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791534003.3388324}
{"ep": "h2-00021", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.188, "status": "ok", "correct": true, "speedup": 1.188, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 354.8, "calls": 2, "tokens_in": 29024, "tokens_out": 18358, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534004.1043231}
{"ep": "h2-00110", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0081, "status": "ok", "correct": true, "speedup": 1.0081, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 195.4, "calls": 3, "tokens_in": 12687, "tokens_out": 5141, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534008.045378}
{"ep": "h2-00096", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4689, "status": "ok", "correct": true, "speedup": 1.4689, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 253.6, "calls": 3, "tokens_in": 15863, "tokens_out": 12517, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534009.9373574}
{"ep": "h2-00118", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0406, "status": "ok", "correct": true, "speedup": 1.0406, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 178.5, "calls": 2, "tokens_in": 5183, "tokens_out": 3210, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534010.6604135}
{"ep": "h2-00053", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6403, "status": "ok", "correct": true, "speedup": 0.6403, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 364.1, "calls": 5, "tokens_in": 52462, "tokens_out": 12956, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534013.4218593}
{"ep": "h2-00130", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "incorrect", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 154.1, "calls": 1, "tokens_in": 2159, "tokens_out": 3029, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534022.245214}
{"ep": "h2-00147", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0672, "status": "ok", "correct": true, "speedup": 1.0672, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 104.9, "calls": 2, "tokens_in": 4887, "tokens_out": 3310, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534024.1332724}
{"ep": "h2-00135", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5517, "status": "ok", "correct": true, "speedup": 0.5517, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 145.6, "calls": 3, "tokens_in": 20134, "tokens_out": 3179, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534025.567588}
{"ep": "h2-00088", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0267, "status": "ok", "correct": true, "speedup": 1.0267, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 281.8, "calls": 2, "tokens_in": 4387, "tokens_out": 2282, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534026.679945}
{"ep": "h2-00082", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 27.1824, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 295.0, "calls": 2, "tokens_in": 7469, "tokens_out": 7726, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534026.7676365}
{"ep": "h2-00116", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0092, "status": "ok", "correct": true, "speedup": 1.0092, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 199.9, "calls": 2, "tokens_in": 5879, "tokens_out": 6671, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534027.580391}
{"ep": "h2-00123", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.004, "status": "ok", "correct": true, "speedup": 1.004, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 180.8, "calls": 2, "tokens_in": 11683, "tokens_out": 1403, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791534027.8136597}
{"ep": "h2-00150", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9757, "status": "ok", "correct": true, "speedup": 0.9757, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 99.1, "calls": 1, "tokens_in": 7032, "tokens_out": 1152, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534028.4014952}
{"ep": "h2-00076", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4824, "status": "ok", "correct": true, "speedup": 1.4824, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 312.5, "calls": 2, "tokens_in": 6915, "tokens_out": 8215, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534028.7656894}
{"ep": "h2-00091", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6426, "status": "ok", "correct": true, "speedup": 0.6426, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 281.6, "calls": 5, "tokens_in": 51168, "tokens_out": 13754, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534030.065289}
{"ep": "h2-00126", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3305, "status": "ok", "correct": true, "speedup": 1.3305, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 173.5, "calls": 1, "tokens_in": 5998, "tokens_out": 735, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791534031.2512033}
{"ep": "h2-00104", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0249, "status": "ok", "correct": true, "speedup": 1.0249, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 247.3, "calls": 3, "tokens_in": 23576, "tokens_out": 7094, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534036.0887265}
{"ep": "h2-00005", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8741, "status": "ok", "correct": true, "speedup": 0.8741, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 390.1, "calls": 3, "tokens_in": 64470, "tokens_out": 22035, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534039.3414466}
{"ep": "h2-00144", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8765, "status": "ok", "correct": true, "speedup": 0.8765, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 131.8, "calls": 2, "tokens_in": 4583, "tokens_out": 2226, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534041.6933684}
{"ep": "h2-00143", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0018, "status": "ok", "correct": true, "speedup": 1.0018, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 134.7, "calls": 3, "tokens_in": 24757, "tokens_out": 2255, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791534042.0839484}
{"ep": "h2-00121", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.8157, "status": "ok", "correct": true, "speedup": 2.8157, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 200.2, "calls": 2, "tokens_in": 7579, "tokens_out": 11250, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534042.93297}
{"ep": "h2-00152", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3296, "status": "ok", "correct": true, "speedup": 1.3296, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 108.0, "calls": 1, "tokens_in": 5998, "tokens_out": 718, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791534050.3249507}
{"ep": "h2-00129", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9217, "status": "ok", "correct": true, "speedup": 0.9217, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 184.8, "calls": 3, "tokens_in": 24018, "tokens_out": 2114, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534051.884637}
{"ep": "h2-00083", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.6076, "status": "ok", "correct": true, "speedup": 1.6076, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 324.0, "calls": 3, "tokens_in": 15869, "tokens_out": 16102, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534057.6698227}
{"ep": "h2-00125", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8054, "status": "ok", "correct": true, "speedup": 0.8054, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 203.6, "calls": 3, "tokens_in": 50101, "tokens_out": 14965, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534057.7627254}
{"ep": "h2-00094", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.1468, "status": "ok", "correct": true, "speedup": 6.1468, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 312.1, "calls": 3, "tokens_in": 28178, "tokens_out": 17861, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534066.1237001}
{"ep": "h2-00132", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2994, "status": "ok", "correct": true, "speedup": 0.2994, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 190.3, "calls": 3, "tokens_in": 21843, "tokens_out": 5202, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534067.6573184}
{"ep": "h2-00111", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.0184, "status": "ok", "correct": true, "speedup": 3.0184, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 252.2, "calls": 2, "tokens_in": 6181, "tokens_out": 8026, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534068.3269534}
{"ep": "h2-00188", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0056, "status": "ok", "correct": true, "speedup": 1.0056, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 27.8, "calls": 1, "tokens_in": 6477, "tokens_out": 490, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791534069.527296}
{"ep": "h2-00134", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.1219, "status": "ok", "correct": true, "speedup": 0.1219, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 191.3, "calls": 3, "tokens_in": 10439, "tokens_out": 3617, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534070.2191768}
{"ep": "h2-00124", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6597, "status": "ok", "correct": true, "speedup": 0.6597, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 220.9, "calls": 3, "tokens_in": 18683, "tokens_out": 1469, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534070.382136}
{"ep": "h2-00114", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4874, "status": "ok", "correct": true, "speedup": 1.4874, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 248.4, "calls": 2, "tokens_in": 30358, "tokens_out": 16323, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534070.6416333}
{"ep": "h2-00177", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0069, "status": "ok", "correct": true, "speedup": 1.0069, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 45.1, "calls": 2, "tokens_in": 11683, "tokens_out": 1407, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791534070.6646059}
{"ep": "h2-00175", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0052, "status": "ok", "correct": true, "speedup": 1.0052, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 50.8, "calls": 2, "tokens_in": 13696, "tokens_out": 1158, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791534073.0744648}
{"ep": "h2-00067", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0216, "status": "ok", "correct": true, "speedup": 1.0216, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 372.4, "calls": 3, "tokens_in": 13840, "tokens_out": 9818, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534074.0928867}
{"ep": "h2-00128", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0435, "status": "ok", "correct": true, "speedup": 1.0435, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 210.8, "calls": 2, "tokens_in": 12746, "tokens_out": 1951, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791534075.902323}
{"ep": "h2-00153", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0282, "status": "ok", "correct": true, "speedup": 1.0282, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 135.2, "calls": 1, "tokens_in": 5832, "tokens_out": 542, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534077.5854049}
{"ep": "h2-00186", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.011, "status": "ok", "correct": true, "speedup": 1.011, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 44.6, "calls": 1, "tokens_in": 1599, "tokens_out": 594, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534080.6674793}
{"ep": "h2-00155", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.016, "status": "ok", "correct": true, "speedup": 1.016, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 142.7, "calls": 3, "tokens_in": 24697, "tokens_out": 2177, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791534089.3391457}
{"ep": "h2-00154", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0059, "status": "ok", "correct": true, "speedup": 1.0059, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 144.7, "calls": 3, "tokens_in": 19851, "tokens_out": 2135, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791534090.1034703}
{"ep": "h2-00085", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5826, "status": "ok", "correct": true, "speedup": 1.5826, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 366.3, "calls": 3, "tokens_in": 15965, "tokens_out": 12873, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534106.459955}
{"ep": "h2-00159", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0212, "status": "ok", "correct": true, "speedup": 1.0212, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 140.1, "calls": 2, "tokens_in": 9215, "tokens_out": 2504, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534106.930869}
{"ep": "h2-00156", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9995, "status": "ok", "correct": true, "speedup": 0.9995, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 162.9, "calls": 3, "tokens_in": 11412, "tokens_out": 3854, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534109.5202253}
{"ep": "h2-00194", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8629, "status": "ok", "correct": true, "speedup": 0.8629, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 54.2, "calls": 1, "tokens_in": 1647, "tokens_out": 434, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534111.939261}
{"ep": "h2-00178", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0043, "status": "ok", "correct": true, "speedup": 1.0043, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 88.2, "calls": 3, "tokens_in": 20093, "tokens_out": 2780, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534114.9255865}
{"ep": "h2-00157", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0077, "status": "ok", "correct": true, "speedup": 1.0077, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 163.9, "calls": 2, "tokens_in": 16164, "tokens_out": 2369, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791534116.6848114}
{"ep": "h2-00140", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4376, "status": "ok", "correct": true, "speedup": 1.4376, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 220.3, "calls": 2, "tokens_in": 12015, "tokens_out": 8416, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534118.8401976}
{"ep": "h2-00171", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8455, "status": "ok", "correct": true, "speedup": 0.8455, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 112.0, "calls": 2, "tokens_in": 15743, "tokens_out": 3118, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791534120.0491502}
{"ep": "h2-00120", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.8224, "status": "ok", "correct": true, "speedup": 2.8224, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 284.7, "calls": 2, "tokens_in": 6362, "tokens_out": 7059, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534121.941968}
{"ep": "h2-00136", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.024, "status": "ok", "correct": true, "speedup": 5.024, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 228.5, "calls": 2, "tokens_in": 6325, "tokens_out": 6718, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534122.7262993}
{"ep": "h2-00151", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0231, "status": "ok", "correct": true, "speedup": 1.0231, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 191.0, "calls": 2, "tokens_in": 13648, "tokens_out": 5100, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534122.9659188}
{"ep": "h2-00117", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.968, "status": "ok", "correct": true, "speedup": 0.968, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 303.0, "calls": 2, "tokens_in": 12362, "tokens_out": 20091, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534132.1208863}
{"ep": "h2-00184", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3777, "status": "ok", "correct": true, "speedup": 2.3777, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 102.4, "calls": 2, "tokens_in": 15194, "tokens_out": 5831, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534132.4521425}
{"ep": "h2-00176", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7117, "status": "ok", "correct": true, "speedup": 0.7117, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 110.4, "calls": 2, "tokens_in": 16440, "tokens_out": 4416, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791534134.579805}
{"ep": "h2-00127", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2938, "status": "ok", "correct": true, "speedup": 1.2938, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 277.2, "calls": 2, "tokens_in": 30768, "tokens_out": 17522, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534139.0642288}
{"ep": "h2-00146", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.6654, "status": "ok", "correct": true, "speedup": 1.6654, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 235.5, "calls": 2, "tokens_in": 7412, "tokens_out": 8306, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534146.2023764}
{"ep": "h2-00206", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0451, "status": "ok", "correct": true, "speedup": 1.0451, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 70.5, "calls": 2, "tokens_in": 4997, "tokens_out": 2905, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534148.0890687}
{"ep": "h2-00158", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0222, "status": "ok", "correct": true, "speedup": 1.0222, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 191.8, "calls": 2, "tokens_in": 6003, "tokens_out": 6175, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534149.038913}
{"ep": "h2-00192", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0545, "status": "ok", "correct": true, "speedup": 1.0545, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 101.6, "calls": 2, "tokens_in": 13891, "tokens_out": 3492, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534153.515171}
{"ep": "h2-00190", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.8958, "status": "ok", "correct": true, "speedup": 1.8958, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 112.4, "calls": 2, "tokens_in": 15169, "tokens_out": 4910, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791534155.3623838}
{"ep": "h2-00165", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9685, "status": "ok", "correct": true, "speedup": 0.9685, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 160.5, "calls": 2, "tokens_in": 12085, "tokens_out": 2583, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534156.868565}
{"ep": "h2-00172", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0117, "status": "ok", "correct": true, "speedup": 1.0117, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 154.3, "calls": 3, "tokens_in": 23721, "tokens_out": 3539, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534164.2242534}
{"ep": "h2-00196", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9786, "status": "ok", "correct": true, "speedup": 0.9786, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 97.8, "calls": 2, "tokens_in": 12245, "tokens_out": 2857, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534165.4091477}
{"ep": "h2-00148", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0079, "status": "ok", "correct": true, "speedup": 1.0079, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 238.1, "calls": 3, "tokens_in": 19983, "tokens_out": 2693, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534165.61285}
{"ep": "h2-00168", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8024, "status": "ok", "correct": true, "speedup": 0.8024, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 166.0, "calls": 1, "tokens_in": 1902, "tokens_out": 2081, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534166.3385444}
{"ep": "h2-00162", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0297, "status": "ok", "correct": true, "speedup": 1.0297, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 183.2, "calls": 2, "tokens_in": 9284, "tokens_out": 2690, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534168.3104527}
{"ep": "h2-00185", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5972, "status": "ok", "correct": true, "speedup": 1.5972, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 140.4, "calls": 2, "tokens_in": 5715, "tokens_out": 4621, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534171.6375625}
{"ep": "h2-00164", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0072, "status": "ok", "correct": true, "speedup": 1.0072, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 179.5, "calls": 2, "tokens_in": 4080, "tokens_out": 1886, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534175.1978574}
{"ep": "h2-00169", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0254, "status": "ok", "correct": true, "speedup": 1.0254, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 172.8, "calls": 2, "tokens_in": 12581, "tokens_out": 1715, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534176.13709}
{"ep": "h2-00161", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.44, "status": "ok", "correct": true, "speedup": 1.44, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 195.3, "calls": 2, "tokens_in": 12035, "tokens_out": 8065, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534179.426407}
{"ep": "h2-00180", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.004, "status": "ok", "correct": true, "speedup": 1.004, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 152.6, "calls": 3, "tokens_in": 24932, "tokens_out": 2339, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791534180.1519277}
{"ep": "h2-00229", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0059, "status": "ok", "correct": true, "speedup": 1.0059, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 26.1, "calls": 1, "tokens_in": 6367, "tokens_out": 544, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791534181.4635472}
{"ep": "h2-00193", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0049, "status": "ok", "correct": true, "speedup": 1.0049, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 128.2, "calls": 2, "tokens_in": 11396, "tokens_out": 1101, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791534185.8760545}
{"ep": "h2-00131", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2935, "status": "ok", "correct": true, "speedup": 0.2935, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 318.2, "calls": 4, "tokens_in": 37254, "tokens_out": 8126, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534190.786426}
{"ep": "h2-00167", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6402, "status": "ok", "correct": true, "speedup": 2.6402, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 193.9, "calls": 2, "tokens_in": 13037, "tokens_out": 4383, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534194.1378274}
{"ep": "h2-00221", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'mish2_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=mish2_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csr", "wall_s": 64.2, "calls": 1, "tokens_in": 1501, "tokens_out": 839, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534196.302429}
{"ep": "h2-00173", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8196, "status": "ok", "correct": true, "speedup": 0.8196, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 189.7, "calls": 3, "tokens_in": 49977, "tokens_out": 14939, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534200.370654}
{"ep": "h2-00109", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.784, "status": "ok", "correct": true, "speedup": 0.784, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 395.6, "calls": 5, "tokens_in": 75849, "tokens_out": 18117, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534202.6764076}
{"ep": "h2-00219", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0618, "status": "ok", "correct": true, "speedup": 1.0618, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 83.1, "calls": 2, "tokens_in": 13930, "tokens_out": 3368, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534205.8458543}
{"ep": "h2-00225", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8435, "status": "ok", "correct": true, "speedup": 0.8435, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 63.7, "calls": 2, "tokens_in": 15685, "tokens_out": 2927, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791534209.909908}
{"ep": "h2-00212", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0161, "status": "ok", "correct": true, "speedup": 1.0161, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 100.7, "calls": 4, "tokens_in": 36338, "tokens_out": 4661, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791534210.2017426}
{"ep": "h2-00218", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7205, "status": "ok", "correct": true, "speedup": 0.7205, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 90.7, "calls": 2, "tokens_in": 14295, "tokens_out": 1979, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534212.6491573}
{"ep": "h2-00142", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 26.7379, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 308.6, "calls": 2, "tokens_in": 7239, "tokens_out": 7663, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534215.299059}
{"ep": "h2-00166", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0184, "status": "ok", "correct": true, "speedup": 1.0184, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 218.5, "calls": 3, "tokens_in": 16081, "tokens_out": 2729, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534216.2366953}
{"ep": "h2-00203", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0301, "status": "ok", "correct": true, "speedup": 1.0301, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 144.7, "calls": 3, "tokens_in": 27629, "tokens_out": 4770, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791534217.745791}
{"ep": "h2-00197", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9761, "status": "ok", "correct": true, "speedup": 0.9761, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 154.5, "calls": 1, "tokens_in": 7032, "tokens_out": 998, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534222.8701599}
{"ep": "h2-00069", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.2053, "status": "ok", "correct": true, "speedup": 7.2053, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 516.8, "calls": 3, "tokens_in": 29686, "tokens_out": 24869, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534225.9315653}
{"ep": "h2-00208", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6423, "status": "ok", "correct": true, "speedup": 0.6423, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 139.3, "calls": 2, "tokens_in": 15023, "tokens_out": 10977, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534228.6075327}
{"ep": "h2-00205", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.067, "status": "ok", "correct": true, "speedup": 0.067, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 154.5, "calls": 2, "tokens_in": 14060, "tokens_out": 4763, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791534230.361815}
{"ep": "h2-00202", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4294, "status": "ok", "correct": true, "speedup": 1.4294, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 160.3, "calls": 2, "tokens_in": 9487, "tokens_out": 9236, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534230.9845183}
{"ep": "h2-00211", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1933, "status": "ok", "correct": true, "speedup": 1.1933, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 127.8, "calls": 2, "tokens_in": 5181, "tokens_out": 4292, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534234.7531717}
{"ep": "h2-00181", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0072, "status": "ok", "correct": true, "speedup": 1.0072, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 209.3, "calls": 3, "tokens_in": 24688, "tokens_out": 2180, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791534237.0771048}
{"ep": "h2-00201", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0186, "status": "ok", "correct": true, "speedup": 1.0186, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 167.5, "calls": 2, "tokens_in": 16256, "tokens_out": 2648, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791534238.1737006}
{"ep": "h2-00234", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0069, "status": "ok", "correct": true, "speedup": 1.0069, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 72.9, "calls": 3, "tokens_in": 19855, "tokens_out": 2104, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791534239.2227454}
{"ep": "h2-00240", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0089, "status": "ok", "correct": true, "speedup": 1.0089, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 59.5, "calls": 1, "tokens_in": 1501, "tokens_out": 726, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534239.6604762}
{"ep": "h2-00227", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0452, "status": "ok", "correct": true, "speedup": 1.0452, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 95.0, "calls": 2, "tokens_in": 5106, "tokens_out": 3173, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534244.0123234}
{"ep": "h2-00199", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.024, "status": "ok", "correct": true, "speedup": 1.024, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 176.0, "calls": 2, "tokens_in": 5824, "tokens_out": 6041, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534246.2656896}
{"ep": "h2-00183", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.7535, "status": "ok", "correct": true, "speedup": 4.7535, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 218.4, "calls": 2, "tokens_in": 7336, "tokens_out": 17751, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534247.119609}
{"ep": "h2-00204", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.0966, "status": "ok", "correct": true, "speedup": 4.0966, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 174.3, "calls": 2, "tokens_in": 8389, "tokens_out": 15073, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534248.3776977}
{"ep": "h2-00170", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0193, "status": "ok", "correct": true, "speedup": 1.0193, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 246.0, "calls": 4, "tokens_in": 35695, "tokens_out": 4390, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791534250.1270258}
{"ep": "h2-00249", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0522, "status": "ok", "correct": true, "speedup": 1.0522, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 42.0, "calls": 1, "tokens_in": 4862, "tokens_out": 1923, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534251.9246354}
{"ep": "h2-00214", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0039, "status": "ok", "correct": true, "speedup": 1.0039, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 140.6, "calls": 2, "tokens_in": 13488, "tokens_out": 1091, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791534255.4818249}
{"ep": "h2-00223", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0233, "status": "ok", "correct": true, "speedup": 1.0233, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 124.7, "calls": 2, "tokens_in": 9117, "tokens_out": 2341, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534259.255548}
{"ep": "h2-00108", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4986, "status": "ok", "correct": true, "speedup": 1.4986, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 456.4, "calls": 3, "tokens_in": 16476, "tokens_out": 12227, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534259.4375832}
{"ep": "h2-00198", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3849, "status": "ok", "correct": true, "speedup": 0.3849, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 200.0, "calls": 4, "tokens_in": 18481, "tokens_out": 5566, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534269.4775944}
{"ep": "h2-00226", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9956, "status": "ok", "correct": true, "speedup": 0.9956, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 122.6, "calls": 2, "tokens_in": 4681, "tokens_out": 2324, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534270.726633}
{"ep": "h2-00187", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.378, "status": "ok", "correct": true, "speedup": 1.378, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 234.1, "calls": 2, "tokens_in": 15552, "tokens_out": 12555, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534273.3941073}
{"ep": "h2-00200", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8632, "status": "ok", "correct": true, "speedup": 0.8632, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 203.2, "calls": 3, "tokens_in": 49408, "tokens_out": 14181, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534273.6155922}
{"ep": "h2-00189", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1046, "status": "ok", "correct": true, "speedup": 1.1046, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 233.4, "calls": 2, "tokens_in": 13963, "tokens_out": 14321, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534275.452566}
{"ep": "h2-00231", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0568, "status": "ok", "correct": true, "speedup": 1.0568, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 111.5, "calls": 2, "tokens_in": 11753, "tokens_out": 3781, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534275.7555149}
{"ep": "h2-00210", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.992, "status": "ok", "correct": true, "speedup": 0.992, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 170.2, "calls": 3, "tokens_in": 22876, "tokens_out": 3321, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791534276.6160874}
{"ep": "h2-00215", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0279, "status": "ok", "correct": true, "speedup": 1.0279, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 160.8, "calls": 2, "tokens_in": 12732, "tokens_out": 1605, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534277.4518838}
{"ep": "h2-00230", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5543, "status": "ok", "correct": true, "speedup": 0.5543, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 122.3, "calls": 2, "tokens_in": 12655, "tokens_out": 3055, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534279.212331}
{"ep": "h2-00259", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "forbidden", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "static check failed: line 124: getattr needs a literal, non-private attribute name; line 126: getattr needs a literal, non-private attribute name; line 127: getattr needs a literal, non-private attribute name; line 125: getattr needs a literal, non-private attribute name", "wall_s": 51.6, "calls": 1, "tokens_in": 1964, "tokens_out": 4940, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534282.53761}
{"ep": "h2-00195", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0235, "status": "ok", "correct": true, "speedup": 1.0235, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 221.2, "calls": 2, "tokens_in": 12592, "tokens_out": 1693, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534287.2981582}
{"ep": "h2-00224", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7935, "status": "ok", "correct": true, "speedup": 0.7935, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 149.0, "calls": 3, "tokens_in": 19095, "tokens_out": 1781, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534288.0247116}
{"ep": "h2-00275", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0076, "status": "ok", "correct": true, "speedup": 1.0076, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 23.7, "calls": 1, "tokens_in": 6367, "tokens_out": 541, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791534294.4256284}
{"ep": "h2-00213", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9934, "status": "ok", "correct": true, "speedup": 0.9934, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 189.8, "calls": 3, "tokens_in": 22606, "tokens_out": 3079, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791534301.7808504}
{"ep": "h2-00244", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7174, "status": "ok", "correct": true, "speedup": 0.7174, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 115.7, "calls": 2, "tokens_in": 16483, "tokens_out": 4355, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791534309.789981}
{"ep": "h2-00248", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0041, "status": "ok", "correct": true, "speedup": 1.0041, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 104.4, "calls": 2, "tokens_in": 4037, "tokens_out": 2027, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534310.2676067}
{"ep": "h2-00274", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8305, "status": "ok", "correct": true, "speedup": 0.8305, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 52.8, "calls": 1, "tokens_in": 5528, "tokens_out": 829, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534322.2641578}
{"ep": "h2-00160", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.5931, "status": "ok", "correct": true, "speedup": 3.5931, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 359.5, "calls": 3, "tokens_in": 16565, "tokens_out": 17554, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534330.925888}
{"ep": "h2-00283", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7673, "status": "ok", "correct": true, "speedup": 0.7673, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 50.4, "calls": 1, "tokens_in": 6622, "tokens_out": 489, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534332.924789}
{"ep": "h2-00255", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3302, "status": "ok", "correct": true, "speedup": 1.3302, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 112.2, "calls": 1, "tokens_in": 5998, "tokens_out": 746, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791534335.0335734}
{"ep": "h2-00245", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0198, "status": "ok", "correct": true, "speedup": 1.0198, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 142.6, "calls": 2, "tokens_in": 9091, "tokens_out": 2229, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534338.8581607}
{"ep": "h2-00246", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.866, "status": "ok", "correct": true, "speedup": 0.866, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 144.9, "calls": 2, "tokens_in": 4138, "tokens_out": 1318, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534345.2752159}
{"ep": "h2-00271", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9538, "status": "ok", "correct": true, "speedup": 0.9538, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 90.5, "calls": 2, "tokens_in": 8301, "tokens_out": 6483, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534345.935058}
{"ep": "h2-00222", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0139, "status": "ok", "correct": true, "speedup": 1.0139, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 215.8, "calls": 3, "tokens_in": 24727, "tokens_out": 2208, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791534348.2666223}
{"ep": "h2-00243", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5235, "status": "ok", "correct": true, "speedup": 1.5235, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 164.0, "calls": 2, "tokens_in": 6351, "tokens_out": 7806, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534354.7396657}
{"ep": "h2-00237", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5292, "status": "ok", "correct": true, "speedup": 1.5292, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 180.4, "calls": 2, "tokens_in": 9975, "tokens_out": 11357, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534355.6133854}
{"ep": "h2-00267", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0442, "status": "ok", "correct": true, "speedup": 1.0442, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 108.5, "calls": 2, "tokens_in": 5239, "tokens_out": 3300, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534355.6349373}
{"ep": "h2-00268", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9841, "status": "ok", "correct": true, "speedup": 0.9841, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 108.6, "calls": 2, "tokens_in": 15295, "tokens_out": 6809, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791534356.9312658}
{"ep": "h2-00258", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0642, "status": "ok", "correct": true, "speedup": 1.0642, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 126.6, "calls": 3, "tokens_in": 16372, "tokens_out": 2272, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534356.9751103}
{"ep": "h2-00286", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0093, "status": "ok", "correct": true, "speedup": 1.0093, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 64.2, "calls": 2, "tokens_in": 4116, "tokens_out": 2405, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534358.6057916}
{"ep": "h2-00233", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3476, "status": "ok", "correct": true, "speedup": 1.3476, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 196.9, "calls": 2, "tokens_in": 6786, "tokens_out": 7268, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534362.555685}
{"ep": "h2-00263", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8456, "status": "ok", "correct": true, "speedup": 0.8456, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 126.7, "calls": 1, "tokens_in": 7030, "tokens_out": 1255, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791534365.888269}
{"ep": "h2-00256", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6832, "status": "ok", "correct": true, "speedup": 0.6832, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 147.9, "calls": 2, "tokens_in": 14158, "tokens_out": 1834, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534373.859916}
{"ep": "h2-00282", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.992, "status": "ok", "correct": true, "speedup": 0.992, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 98.4, "calls": 3, "tokens_in": 22455, "tokens_out": 2992, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791534377.6235993}
{"ep": "h2-00236", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3239, "status": "ok", "correct": true, "speedup": 0.3239, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 206.8, "calls": 3, "tokens_in": 22552, "tokens_out": 5899, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534378.4849794}
{"ep": "h2-00209", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.9708, "status": "ok", "correct": true, "speedup": 4.9708, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 288.5, "calls": 3, "tokens_in": 14375, "tokens_out": 10776, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534378.5760522}
{"ep": "h2-00191", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.3683, "status": "ok", "correct": true, "speedup": 4.3683, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 330.0, "calls": 3, "tokens_in": 18104, "tokens_out": 17536, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534380.2792616}
{"ep": "h2-00280", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8906, "status": "ok", "correct": true, "speedup": 0.8906, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 108.4, "calls": 2, "tokens_in": 5301, "tokens_out": 4457, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534384.9808362}
{"ep": "h2-00289", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3289, "status": "ok", "correct": true, "speedup": 1.3289, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 80.2, "calls": 1, "tokens_in": 1723, "tokens_out": 763, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534390.4532447}
{"ep": "h2-00217", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2887, "status": "ok", "correct": true, "speedup": 0.2887, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 270.5, "calls": 5, "tokens_in": 54126, "tokens_out": 10682, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534390.5006256}
{"ep": "h2-00163", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.1173, "status": "ok", "correct": true, "speedup": 0.1173, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 399.7, "calls": 5, "tokens_in": 76628, "tokens_out": 17498, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534392.5526109}
{"ep": "h2-00241", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.9886, "status": "ok", "correct": true, "speedup": 1.9886, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 213.2, "calls": 2, "tokens_in": 15230, "tokens_out": 5774, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791534394.6805577}
{"ep": "h2-00287", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7719, "status": "ok", "correct": true, "speedup": 0.7719, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 93.7, "calls": 3, "tokens_in": 19004, "tokens_out": 1741, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534395.4680233}
{"ep": "h2-00284", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0873, "status": "ok", "correct": true, "speedup": 1.0873, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 112.9, "calls": 2, "tokens_in": 15448, "tokens_out": 4722, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534400.2205613}
{"ep": "h2-00269", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4143, "status": "ok", "correct": true, "speedup": 1.4143, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 164.3, "calls": 2, "tokens_in": 6638, "tokens_out": 7456, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534414.4171996}
{"ep": "h2-00179", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5594, "status": "ok", "correct": true, "speedup": 1.5594, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 388.8, "calls": 3, "tokens_in": 32126, "tokens_out": 14602, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534415.57679}
{"ep": "h2-00279", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7909, "status": "ok", "correct": true, "speedup": 2.7909, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 144.2, "calls": 2, "tokens_in": 14095, "tokens_out": 4775, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791534419.956918}
{"ep": "h2-00266", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6271, "status": "ok", "correct": true, "speedup": 2.6271, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 175.5, "calls": 2, "tokens_in": 12948, "tokens_out": 4111, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534421.8052092}
{"ep": "h2-00242", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.012, "status": "ok", "correct": true, "speedup": 1.012, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 236.3, "calls": 3, "tokens_in": 19793, "tokens_out": 2069, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791534422.143746}
{"ep": "h2-00174", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0032, "status": "ok", "correct": true, "speedup": 1.0032, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 413.5, "calls": 3, "tokens_in": 19989, "tokens_out": 2744, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534426.8908634}
{"ep": "h2-00281", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0233, "status": "ok", "correct": true, "speedup": 1.0233, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 153.9, "calls": 2, "tokens_in": 12572, "tokens_out": 1442, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534431.360105}
{"ep": "h2-00228", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.5041, "status": "ok", "correct": true, "speedup": 4.5041, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 283.6, "calls": 3, "tokens_in": 13757, "tokens_out": 9524, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534437.1150713}
{"ep": "h2-00220", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9951, "status": "ok", "correct": true, "speedup": 0.9951, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 314.8, "calls": 4, "tokens_in": 17652, "tokens_out": 2809, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534437.802685}
{"ep": "h2-00315", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7907, "status": "ok", "correct": true, "speedup": 0.7907, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 43.6, "calls": 2, "tokens_in": 14070, "tokens_out": 1672, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534438.3214402}
{"ep": "h2-00235", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9772, "status": "ok", "correct": true, "speedup": 0.9772, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 270.6, "calls": 2, "tokens_in": 12176, "tokens_out": 2878, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534438.91347}
{"ep": "h2-00316", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0079, "status": "ok", "correct": true, "speedup": 1.0079, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 44.9, "calls": 2, "tokens_in": 13720, "tokens_out": 1209, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791534440.3584683}
{"ep": "h2-00247", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5576, "status": "ok", "correct": true, "speedup": 0.5576, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 237.7, "calls": 2, "tokens_in": 12819, "tokens_out": 3105, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534440.413085}
{"ep": "h2-00314", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0561, "status": "ok", "correct": true, "speedup": 1.0561, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 49.1, "calls": 3, "tokens_in": 23154, "tokens_out": 2631, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534441.624998}
{"ep": "h2-00254", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0661, "status": "ok", "correct": true, "speedup": 1.0661, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 226.0, "calls": 2, "tokens_in": 4947, "tokens_out": 3701, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534443.7792153}
{"ep": "h2-00262", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0267, "status": "ok", "correct": true, "speedup": 1.0267, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 206.2, "calls": 1, "tokens_in": 5832, "tokens_out": 538, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534444.3936174}
{"ep": "h2-00292", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8143, "status": "ok", "correct": true, "speedup": 0.8143, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 111.9, "calls": 3, "tokens_in": 18871, "tokens_out": 1591, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534444.8694766}
{"ep": "h2-00257", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0047, "status": "ok", "correct": true, "speedup": 1.0047, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 222.1, "calls": 2, "tokens_in": 13442, "tokens_out": 1037, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791534450.7093408}
{"ep": "h2-00182", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.6859, "status": "ok", "correct": true, "speedup": 4.6859, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 428.6, "calls": 3, "tokens_in": 28655, "tokens_out": 23531, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534456.981717}
{"ep": "h2-00301", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9193, "status": "ok", "correct": true, "speedup": 0.9193, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 107.8, "calls": 2, "tokens_in": 14615, "tokens_out": 9268, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534464.7672594}
{"ep": "h2-00273", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'fused_bn039': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_bn039 -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch", "wall_s": 218.5, "calls": 1, "tokens_in": 1596, "tokens_out": 2397, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534477.9262}
{"ep": "h2-00295", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0268, "status": "ok", "correct": true, "speedup": 1.0268, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 134.9, "calls": 1, "tokens_in": 5832, "tokens_out": 538, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534480.1256676}
{"ep": "h2-00307", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0167, "status": "ok", "correct": true, "speedup": 1.0167, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 105.1, "calls": 3, "tokens_in": 25156, "tokens_out": 2511, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791534482.7475374}
{"ep": "h2-00330", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0065, "status": "ok", "correct": true, "speedup": 1.0065, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 43.0, "calls": 2, "tokens_in": 4154, "tokens_out": 1828, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534483.4381742}
{"ep": "h2-00306", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0898, "status": "ok", "correct": true, "speedup": 1.0898, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 115.1, "calls": 2, "tokens_in": 15367, "tokens_out": 4268, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534488.9511933}
{"ep": "h2-00261", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.9206, "status": "ok", "correct": true, "speedup": 1.9206, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 252.2, "calls": 2, "tokens_in": 30339, "tokens_out": 23216, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534489.296347}
{"ep": "h2-00302", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0066, "status": "ok", "correct": true, "speedup": 1.0066, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 137.4, "calls": 3, "tokens_in": 20722, "tokens_out": 1005, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791534494.3921556}
{"ep": "h2-00328", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0599, "status": "ok", "correct": true, "speedup": 1.0599, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 56.4, "calls": 1, "tokens_in": 1633, "tokens_out": 2695, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534495.3412185}
{"ep": "h2-00251", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0936, "status": "ok", "correct": true, "speedup": 0.0936, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 287.1, "calls": 4, "tokens_in": 26377, "tokens_out": 7688, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534499.777756}
{"ep": "h2-00297", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3265, "status": "ok", "correct": true, "speedup": 0.3265, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 152.3, "calls": 3, "tokens_in": 22095, "tokens_out": 5449, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534500.560595}
{"ep": "h2-00265", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0069, "status": "ok", "correct": true, "speedup": 1.0069, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 256.8, "calls": 3, "tokens_in": 24613, "tokens_out": 2142, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791534500.7923713}
{"ep": "h2-00318", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.4429, "status": "ok", "correct": true, "speedup": 2.4429, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 88.1, "calls": 3, "tokens_in": 22659, "tokens_out": 4838, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534502.4954119}
{"ep": "h2-00288", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.788, "status": "ok", "correct": true, "speedup": 0.788, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 194.1, "calls": 5, "tokens_in": 44822, "tokens_out": 9904, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534503.917375}
{"ep": "h2-00276", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.4923, "status": "ok", "correct": true, "speedup": 5.4923, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 235.6, "calls": 3, "tokens_in": 18969, "tokens_out": 22055, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534508.969463}
{"ep": "h2-00299", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7753, "status": "ok", "correct": true, "speedup": 0.7753, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 163.0, "calls": 3, "tokens_in": 50704, "tokens_out": 15562, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534518.5750763}
{"ep": "h2-00325", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0045, "status": "ok", "correct": true, "speedup": 1.0045, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.7, "calls": 1, "tokens_in": 1622, "tokens_out": 676, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534518.8427045}
{"ep": "h2-00326", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0055, "status": "ok", "correct": true, "speedup": 1.0055, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 88.9, "calls": 1, "tokens_in": 1623, "tokens_out": 2705, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534526.7070904}
{"ep": "h2-00310", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9236, "status": "ok", "correct": true, "speedup": 0.9236, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 151.7, "calls": 1, "tokens_in": 2157, "tokens_out": 723, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534531.9341455}
{"ep": "h2-00252", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0082, "status": "ok", "correct": true, "speedup": 1.0082, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 318.8, "calls": 2, "tokens_in": 7387, "tokens_out": 10005, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534534.0725048}
{"ep": "h2-00338", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0029, "status": "ok", "correct": true, "speedup": 1.0029, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 63.4, "calls": 2, "tokens_in": 4187, "tokens_out": 1894, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534541.312969}
{"ep": "h2-00351", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0044, "status": "ok", "correct": true, "speedup": 1.0044, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 36.9, "calls": 1, "tokens_in": 6367, "tokens_out": 531, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791534545.8624146}
{"ep": "h2-00333", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 16.0996, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 103.9, "calls": 2, "tokens_in": 15673, "tokens_out": 6378, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534548.2599776}
{"ep": "h2-00293", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0085, "status": "ok", "correct": true, "speedup": 1.0085, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 213.9, "calls": 2, "tokens_in": 6295, "tokens_out": 7331, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534548.8949406}
{"ep": "h2-00346", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.797, "status": "ok", "correct": true, "speedup": 0.797, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 49.5, "calls": 2, "tokens_in": 13845, "tokens_out": 914, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534549.2691083}
{"ep": "h2-00238", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.2036, "status": "ok", "correct": true, "speedup": 3.2036, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 374.1, "calls": 3, "tokens_in": 27215, "tokens_out": 15152, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534550.2424495}
{"ep": "h2-00323", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4354, "status": "ok", "correct": true, "speedup": 1.4354, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 126.0, "calls": 2, "tokens_in": 13110, "tokens_out": 5680, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534552.8822782}
{"ep": "h2-00329", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.7651, "status": "ok", "correct": true, "speedup": 3.7651, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 116.8, "calls": 2, "tokens_in": 6139, "tokens_out": 6043, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534557.1450372}
{"ep": "h2-00332", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0649, "status": "ok", "correct": true, "speedup": 1.0649, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 114.8, "calls": 2, "tokens_in": 6258, "tokens_out": 6298, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534558.5904062}
{"ep": "h2-00344", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0389, "status": "ok", "correct": true, "speedup": 1.0389, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.3, "calls": 3, "tokens_in": 11988, "tokens_out": 4261, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534562.684518}
{"ep": "h2-00353", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6821, "status": "ok", "correct": true, "speedup": 0.6821, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 48.5, "calls": 3, "tokens_in": 21095, "tokens_out": 932, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534567.2932436}
{"ep": "h2-00350", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0634, "status": "ok", "correct": true, "speedup": 1.0634, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 64.0, "calls": 2, "tokens_in": 13764, "tokens_out": 3123, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534567.8740919}
{"ep": "h2-00253", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0113, "status": "ok", "correct": true, "speedup": 1.0113, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 353.6, "calls": 2, "tokens_in": 6037, "tokens_out": 7307, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534569.8146503}
{"ep": "h2-00320", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0991, "status": "ok", "correct": true, "speedup": 1.0991, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 152.4, "calls": 2, "tokens_in": 16916, "tokens_out": 7246, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534572.331283}
{"ep": "h2-00303", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4766, "status": "ok", "correct": true, "speedup": 1.4766, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 220.7, "calls": 2, "tokens_in": 7805, "tokens_out": 10163, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534579.2902274}
{"ep": "h2-00335", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0672, "status": "ok", "correct": true, "speedup": 1.0672, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 137.7, "calls": 2, "tokens_in": 10506, "tokens_out": 2307, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534588.4209168}
{"ep": "h2-00312", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6513, "status": "ok", "correct": true, "speedup": 2.6513, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 209.7, "calls": 3, "tokens_in": 17565, "tokens_out": 16224, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534600.1345193}
{"ep": "h2-00369", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8699, "status": "ok", "correct": true, "speedup": 0.8699, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 32.6, "calls": 1, "tokens_in": 1728, "tokens_out": 2154, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534602.4570634}
{"ep": "h2-00291", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.026, "status": "ok", "correct": true, "speedup": 1.026, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 277.7, "calls": 3, "tokens_in": 8655, "tokens_out": 4484, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534608.5899413}
{"ep": "h2-00277", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5509, "status": "ok", "correct": true, "speedup": 0.5509, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 337.5, "calls": 3, "tokens_in": 20225, "tokens_out": 3279, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534611.0737152}
{"ep": "h2-00345", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0225, "status": "ok", "correct": true, "speedup": 1.0225, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 118.2, "calls": 2, "tokens_in": 6454, "tokens_out": 7388, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534613.5426176}
{"ep": "h2-00294", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 24.2597, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 280.2, "calls": 2, "tokens_in": 16285, "tokens_out": 8900, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534619.0951548}
{"ep": "h2-00298", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7031, "status": "ok", "correct": true, "speedup": 0.7031, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 265.1, "calls": 2, "tokens_in": 13905, "tokens_out": 1027, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534619.7992194}
{"ep": "h2-00313", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0267, "status": "ok", "correct": true, "speedup": 1.0267, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 229.9, "calls": 2, "tokens_in": 9181, "tokens_out": 2629, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534620.4057024}
{"ep": "h2-00348", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3294, "status": "ok", "correct": true, "speedup": 0.3294, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 120.8, "calls": 3, "tokens_in": 22515, "tokens_out": 5881, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534621.5768392}
{"ep": "h2-00334", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.9179, "status": "ok", "correct": true, "speedup": 6.9179, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 178.2, "calls": 2, "tokens_in": 6499, "tokens_out": 12764, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534623.0741463}
{"ep": "h2-00354", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0137, "status": "ok", "correct": true, "speedup": 1.0137, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 101.1, "calls": 3, "tokens_in": 12176, "tokens_out": 5089, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534627.8457432}
{"ep": "h2-00342", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7172, "status": "ok", "correct": true, "speedup": 0.7172, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 141.1, "calls": 2, "tokens_in": 14229, "tokens_out": 1936, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534630.0177314}
{"ep": "h2-00207", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3466, "status": "ok", "correct": true, "speedup": 0.3466, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 552.7, "calls": 2, "tokens_in": 16772, "tokens_out": 6529, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534633.3939037}
{"ep": "h2-00340", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8219, "status": "ok", "correct": true, "speedup": 0.8219, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 151.3, "calls": 3, "tokens_in": 49268, "tokens_out": 14134, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791534634.0071156}
{"ep": "h2-00327", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.8639, "status": "ok", "correct": true, "speedup": 1.8639, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 198.5, "calls": 2, "tokens_in": 29128, "tokens_out": 19059, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534636.8041933}
{"ep": "h2-00352", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9915, "status": "ok", "correct": true, "speedup": 0.9915, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 119.1, "calls": 3, "tokens_in": 22373, "tokens_out": 2948, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791534637.655516}
{"ep": "h2-00364", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0208, "status": "ok", "correct": true, "speedup": 1.0208, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 83.4, "calls": 2, "tokens_in": 9814, "tokens_out": 2558, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534640.5690067}
{"ep": "h2-00264", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0593, "status": "ok", "correct": true, "speedup": 1.0593, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 401.6, "calls": 3, "tokens_in": 18677, "tokens_out": 3793, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534641.3068812}
{"ep": "h2-00361", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4607, "status": "ok", "correct": true, "speedup": 0.4607, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 92.4, "calls": 4, "tokens_in": 35394, "tokens_out": 7649, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534641.6439006}
{"ep": "h2-00370", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9796, "status": "ok", "correct": true, "speedup": 0.9796, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 69.7, "calls": 2, "tokens_in": 12159, "tokens_out": 2721, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534642.033949}
{"ep": "h2-00359", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0281, "status": "ok", "correct": true, "speedup": 1.0281, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 94.7, "calls": 1, "tokens_in": 5832, "tokens_out": 524, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534642.9811265}
{"ep": "h2-00317", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3366, "status": "ok", "correct": true, "speedup": 1.3366, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 245.2, "calls": 2, "tokens_in": 12816, "tokens_out": 1418, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791534645.4127114}
{"ep": "h2-00322", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0056, "status": "ok", "correct": true, "speedup": 1.0056, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 226.3, "calls": 3, "tokens_in": 19857, "tokens_out": 2123, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791534648.4742405}
{"ep": "h2-00365", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.5253, "status": "ok", "correct": true, "speedup": 3.5253, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 91.4, "calls": 2, "tokens_in": 15393, "tokens_out": 5757, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791534650.0236394}
{"ep": "h2-00270", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1183, "status": "ok", "correct": true, "speedup": 1.1183, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 398.8, "calls": 2, "tokens_in": 12745, "tokens_out": 22134, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534650.7069197}
{"ep": "h2-00319", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0049, "status": "ok", "correct": true, "speedup": 1.0049, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 235.3, "calls": 2, "tokens_in": 4111, "tokens_out": 2091, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534650.8958783}
{"ep": "h2-00290", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0282, "status": "ok", "correct": true, "speedup": 1.0282, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 329.1, "calls": 2, "tokens_in": 4505, "tokens_out": 2334, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534651.4043958}
{"ep": "h2-00300", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7855, "status": "ok", "correct": true, "speedup": 0.7855, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 297.0, "calls": 3, "tokens_in": 18905, "tokens_out": 1628, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534652.6395075}
{"ep": "h2-00358", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0165, "status": "ok", "correct": true, "speedup": 1.0165, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 111.9, "calls": 2, "tokens_in": 16259, "tokens_out": 2605, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791534657.7716906}
{"ep": "h2-00305", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5282, "status": "ok", "correct": true, "speedup": 1.5282, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 294.5, "calls": 2, "tokens_in": 6172, "tokens_out": 7588, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534660.3654943}
{"ep": "h2-00216", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5712, "status": "ok", "correct": true, "speedup": 0.5712, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 541.6, "calls": 2, "tokens_in": 10213, "tokens_out": 19605, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534660.414899}
{"ep": "h2-00232", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9888, "status": "ok", "correct": true, "speedup": 0.9888, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 496.4, "calls": 5, "tokens_in": 27604, "tokens_out": 4913, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534661.7637053}
{"ep": "h2-00372", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0437, "status": "ok", "correct": true, "speedup": 1.0437, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 73.4, "calls": 2, "tokens_in": 4968, "tokens_out": 2933, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534661.803781}
{"ep": "h2-00381", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7525, "status": "ok", "correct": true, "speedup": 0.7525, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 44.5, "calls": 1, "tokens_in": 6622, "tokens_out": 478, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534666.0507789}
{"ep": "h2-00347", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.1931, "status": "ok", "correct": true, "speedup": 3.1931, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 173.9, "calls": 2, "tokens_in": 5402, "tokens_out": 6455, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534674.4654868}
{"ep": "h2-00371", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5576, "status": "ok", "correct": true, "speedup": 0.5576, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 100.9, "calls": 2, "tokens_in": 12656, "tokens_out": 3078, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534680.213751}
{"ep": "h2-00308", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0655, "status": "ok", "correct": true, "speedup": 1.0655, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 302.7, "calls": 2, "tokens_in": 15698, "tokens_out": 4628, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534681.1682734}
{"ep": "h2-00296", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0544, "status": "ok", "correct": true, "speedup": 1.0544, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 335.3, "calls": 3, "tokens_in": 19620, "tokens_out": 4735, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534681.1979938}
{"ep": "h2-00260", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1526, "status": "ok", "correct": true, "speedup": 1.1526, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 453.7, "calls": 2, "tokens_in": 13046, "tokens_out": 5487, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534688.4899776}
{"ep": "h2-00337", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.6537, "status": "ok", "correct": true, "speedup": 3.6537, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 225.1, "calls": 2, "tokens_in": 7717, "tokens_out": 14304, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534689.8289812}
{"ep": "h2-00311", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8485, "status": "ok", "correct": true, "speedup": 0.8485, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 311.4, "calls": 1, "tokens_in": 7030, "tokens_out": 1239, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791534696.4248753}
{"ep": "h2-00324", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4086, "status": "ok", "correct": true, "speedup": 1.4086, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 272.1, "calls": 3, "tokens_in": 15831, "tokens_out": 13509, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534703.429933}
{"ep": "h2-00343", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1978, "status": "ok", "correct": true, "speedup": 1.1978, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 216.4, "calls": 2, "tokens_in": 6497, "tokens_out": 6797, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534705.671654}
{"ep": "h2-00336", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.0124, "status": "ok", "correct": true, "speedup": 5.0124, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 252.8, "calls": 3, "tokens_in": 15985, "tokens_out": 12655, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534709.8088372}
{"ep": "h2-00393", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0012, "status": "ok", "correct": true, "speedup": 1.0012, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 69.1, "calls": 1, "tokens_in": 6477, "tokens_out": 539, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791534712.0794044}
{"ep": "h2-00272", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6474, "status": "ok", "correct": true, "speedup": 0.6474, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 454.2, "calls": 3, "tokens_in": 12998, "tokens_out": 10515, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534713.498742}
{"ep": "h2-00239", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3923, "status": "ok", "correct": true, "speedup": 0.3923, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 534.8, "calls": 4, "tokens_in": 24267, "tokens_out": 8725, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534714.1854718}
{"ep": "h2-00418", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0104, "status": "ok", "correct": true, "speedup": 1.0104, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 23.9, "calls": 1, "tokens_in": 1599, "tokens_out": 661, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534737.4180899}
{"ep": "h2-00399", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'bias_relu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bias_relu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/t", "wall_s": 87.4, "calls": 1, "tokens_in": 1622, "tokens_out": 821, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534738.7956314}
{"ep": "h2-00362", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0569, "status": "ok", "correct": true, "speedup": 1.0569, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 200.6, "calls": 2, "tokens_in": 4745, "tokens_out": 3132, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534750.8604612}
{"ep": "h2-00412", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0595, "status": "ok", "correct": true, "speedup": 1.0595, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 70.1, "calls": 2, "tokens_in": 13836, "tokens_out": 3369, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534759.9568381}
{"ep": "h2-00278", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2157, "status": "ok", "correct": true, "speedup": 1.2157, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 485.5, "calls": 2, "tokens_in": 13865, "tokens_out": 13006, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534761.0007403}
{"ep": "h2-00304", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.666, "status": "ok", "correct": true, "speedup": 2.666, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 398.9, "calls": 4, "tokens_in": 36765, "tokens_out": 6971, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534761.458331}
{"ep": "h2-00400", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7291, "status": "ok", "correct": true, "speedup": 0.7291, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 121.9, "calls": 2, "tokens_in": 14258, "tokens_out": 1968, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534774.53614}
{"ep": "h2-00411", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9903, "status": "ok", "correct": true, "speedup": 0.9903, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 86.4, "calls": 2, "tokens_in": 15668, "tokens_out": 4624, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534774.8966146}
{"ep": "h2-00420", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0221, "status": "ok", "correct": true, "speedup": 1.0221, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 47.1, "calls": 2, "tokens_in": 9221, "tokens_out": 2502, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534784.5595438}
{"ep": "h2-00391", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0034, "status": "ok", "correct": true, "speedup": 1.0034, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 143.8, "calls": 3, "tokens_in": 19846, "tokens_out": 2646, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534785.4302316}
{"ep": "h2-00423", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8454, "status": "ok", "correct": true, "speedup": 0.8454, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 28.3, "calls": 1, "tokens_in": 7030, "tokens_out": 1232, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791534788.2621503}
{"ep": "h2-00360", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4192, "status": "ok", "correct": true, "speedup": 0.4192, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 246.7, "calls": 2, "tokens_in": 6326, "tokens_out": 7785, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534795.6029367}
{"ep": "h2-00376", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4986, "status": "ok", "correct": true, "speedup": 0.4986, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 187.8, "calls": 2, "tokens_in": 14419, "tokens_out": 2268, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534798.8907473}
{"ep": "h2-00363", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7691, "status": "ok", "correct": true, "speedup": 0.7691, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 255.1, "calls": 5, "tokens_in": 65748, "tokens_out": 13094, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534807.978145}
{"ep": "h2-00378", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 14.8663, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 190.9, "calls": 2, "tokens_in": 15448, "tokens_out": 5789, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534809.98801}
{"ep": "h2-00413", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9942, "status": "ok", "correct": true, "speedup": 0.9942, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 116.8, "calls": 3, "tokens_in": 8315, "tokens_out": 2995, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534813.271484}
{"ep": "h2-00419", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.074, "status": "ok", "correct": true, "speedup": 0.074, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 100.8, "calls": 4, "tokens_in": 33825, "tokens_out": 5791, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534814.9590702}
{"ep": "h2-00417", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0636, "status": "ok", "correct": true, "speedup": 1.0636, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 104.1, "calls": 3, "tokens_in": 16433, "tokens_out": 2321, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534816.1395943}
{"ep": "h2-00375", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4239, "status": "ok", "correct": true, "speedup": 1.4239, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 211.0, "calls": 2, "tokens_in": 29141, "tokens_out": 18930, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534819.5958073}
{"ep": "h2-00422", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0061, "status": "ok", "correct": true, "speedup": 1.0061, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 69.6, "calls": 3, "tokens_in": 19800, "tokens_out": 2079, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791534820.499634}
{"ep": "h2-00341", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.8422, "status": "ok", "correct": true, "speedup": 3.8422, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 349.2, "calls": 3, "tokens_in": 16283, "tokens_out": 15400, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534832.6422548}
{"ep": "h2-00421", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.006, "status": "ok", "correct": true, "speedup": 1.006, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 102.8, "calls": 3, "tokens_in": 20077, "tokens_out": 2807, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534841.603665}
{"ep": "h2-00321", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8444, "status": "ok", "correct": true, "speedup": 0.8444, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 421.2, "calls": 2, "tokens_in": 15634, "tokens_out": 2927, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791534842.996521}
{"ep": "h2-00395", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9913, "status": "ok", "correct": true, "speedup": 0.9913, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 196.6, "calls": 2, "tokens_in": 4191, "tokens_out": 1972, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534845.0316098}
{"ep": "h2-00390", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9224, "status": "ok", "correct": true, "speedup": 0.9224, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 208.2, "calls": 2, "tokens_in": 15315, "tokens_out": 1779, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534849.480255}
{"ep": "h2-00405", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0201, "status": "ok", "correct": true, "speedup": 1.0201, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 188.2, "calls": 2, "tokens_in": 15435, "tokens_out": 3176, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791534849.986235}
{"ep": "h2-00386", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.6413, "status": "ok", "correct": true, "speedup": 1.6413, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 216.1, "calls": 2, "tokens_in": 7701, "tokens_out": 12170, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534850.0939336}
{"ep": "h2-00424", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.2994, "status": "ok", "correct": true, "speedup": 2.2994, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 91.5, "calls": 2, "tokens_in": 13659, "tokens_out": 4309, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534852.4940858}
{"ep": "h2-00368", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0489, "status": "ok", "correct": true, "speedup": 1.0489, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 284.7, "calls": 3, "tokens_in": 18617, "tokens_out": 3743, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534852.5457141}
{"ep": "h2-00437", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0075, "status": "ok", "correct": true, "speedup": 1.0075, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 40.1, "calls": 1, "tokens_in": 6367, "tokens_out": 531, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791534856.2461112}
{"ep": "h2-00394", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9231, "status": "ok", "correct": true, "speedup": 0.9231, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 213.2, "calls": 3, "tokens_in": 23988, "tokens_out": 2055, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534858.588036}
{"ep": "h2-00427", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7779, "status": "ok", "correct": true, "speedup": 0.7779, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 86.7, "calls": 3, "tokens_in": 21108, "tokens_out": 950, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534861.6310134}
{"ep": "h2-00425", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.002, "status": "ok", "correct": true, "speedup": 1.002, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 103.3, "calls": 3, "tokens_in": 20258, "tokens_out": 2919, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791534864.7816317}
{"ep": "h2-00374", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0279, "status": "ok", "correct": true, "speedup": 1.0279, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 266.5, "calls": 2, "tokens_in": 12844, "tokens_out": 1733, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534868.9655492}
{"ep": "h2-00339", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8587, "status": "ok", "correct": true, "speedup": 0.8587, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 389.0, "calls": 5, "tokens_in": 58295, "tokens_out": 12801, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534869.1548867}
{"ep": "h2-00435", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0007, "status": "ok", "correct": true, "speedup": 1.0007, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 55.9, "calls": 1, "tokens_in": 6477, "tokens_out": 496, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791534869.2001722}
{"ep": "h2-00416", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5208, "status": "ok", "correct": true, "speedup": 1.5208, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 159.4, "calls": 2, "tokens_in": 16777, "tokens_out": 6790, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534869.2245526}
{"ep": "h2-00409", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.5602, "status": "ok", "correct": true, "speedup": 7.5602, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 189.2, "calls": 2, "tokens_in": 6655, "tokens_out": 14152, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534870.333891}
{"ep": "h2-00309", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0546, "status": "ok", "correct": true, "speedup": 1.0546, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 497.0, "calls": 3, "tokens_in": 22794, "tokens_out": 2375, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534875.5685782}
{"ep": "h2-00410", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9247, "status": "ok", "correct": true, "speedup": 0.9247, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 203.8, "calls": 3, "tokens_in": 24120, "tokens_out": 2191, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534885.004364}
{"ep": "h2-00403", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0066, "status": "ok", "correct": true, "speedup": 1.0066, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 226.4, "calls": 1, "tokens_in": 1623, "tokens_out": 2277, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534886.782191}
{"ep": "h2-00384", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0165, "status": "ok", "correct": true, "speedup": 1.0165, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 259.2, "calls": 3, "tokens_in": 15046, "tokens_out": 2459, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534889.2547333}
{"ep": "h2-00396", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.062, "status": "ok", "correct": true, "speedup": 1.062, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 242.5, "calls": 1, "tokens_in": 1633, "tokens_out": 3791, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534892.476615}
{"ep": "h2-00355", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 36.9905, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 360.7, "calls": 2, "tokens_in": 7204, "tokens_out": 7927, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534892.5844405}
{"ep": "h2-00367", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.1306, "status": "ok", "correct": true, "speedup": 5.1306, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 337.8, "calls": 2, "tokens_in": 6569, "tokens_out": 7554, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534905.1195333}
{"ep": "h2-00440", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0587, "status": "ok", "correct": true, "speedup": 1.0587, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 74.9, "calls": 2, "tokens_in": 14718, "tokens_out": 2348, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534907.5333228}
{"ep": "h2-00430", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0064, "status": "ok", "correct": true, "speedup": 1.0064, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 121.7, "calls": 2, "tokens_in": 14984, "tokens_out": 6074, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791534909.9955127}
{"ep": "h2-00428", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0194, "status": "ok", "correct": true, "speedup": 1.0194, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 130.0, "calls": 2, "tokens_in": 5564, "tokens_out": 5553, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534914.5103164}
{"ep": "h2-00382", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9985, "status": "ok", "correct": true, "speedup": 0.9985, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 300.6, "calls": 4, "tokens_in": 25742, "tokens_out": 1582, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791534923.6548934}
{"ep": "h2-00436", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9753, "status": "ok", "correct": true, "speedup": 0.9753, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 118.0, "calls": 1, "tokens_in": 7032, "tokens_out": 1247, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534932.94979}
{"ep": "h2-00442", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9963, "status": "ok", "correct": true, "speedup": 0.9963, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 92.0, "calls": 1, "tokens_in": 7032, "tokens_out": 1141, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534935.0013993}
{"ep": "h2-00377", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0132, "status": "ok", "correct": true, "speedup": 1.0132, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 324.7, "calls": 2, "tokens_in": 17450, "tokens_out": 6047, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791534938.2071862}
{"ep": "h2-00445", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0226, "status": "ok", "correct": true, "speedup": 1.0226, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 89.1, "calls": 2, "tokens_in": 9220, "tokens_out": 2442, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791534939.082468}
{"ep": "h2-00459", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0044, "status": "ok", "correct": true, "speedup": 1.0044, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 57.0, "calls": 2, "tokens_in": 11404, "tokens_out": 1110, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791534941.997227}
{"ep": "h2-00431", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9219, "status": "ok", "correct": true, "speedup": 0.9219, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 146.7, "calls": 1, "tokens_in": 7113, "tokens_out": 1141, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534942.288455}
{"ep": "h2-00444", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0279, "status": "ok", "correct": true, "speedup": 1.0279, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 93.3, "calls": 1, "tokens_in": 5832, "tokens_out": 526, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791534942.7378263}
{"ep": "h2-00454", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "runtime_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "CompilationError: at 12:8:\ndef lstm_cell_kernel(xg_ptr, hg_ptr, c_ptr, cnew_ptr, hnew_ptr, H, BLOCK: tl.constexpr):\n    row = tl.program_id(0)\n    col = tl.program_id(1) * BLOCK + tl.arange(0, BLOCK)\n    mask = col < H\n    base = row * 4 * H\n    i = tl.load(xg_ptr + base + 0 * H + col, mask=mask) + ", "wall_s": 76.2, "calls": 1, "tokens_in": 1964, "tokens_out": 6252, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534945.3209767}
{"ep": "h2-00429", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9185, "status": "ok", "correct": true, "speedup": 0.9185, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 160.7, "calls": 3, "tokens_in": 24357, "tokens_out": 2272, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534946.111399}
{"ep": "h2-00451", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.005, "status": "ok", "correct": true, "speedup": 1.005, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 89.6, "calls": 2, "tokens_in": 11396, "tokens_out": 1094, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791534951.202369}
{"ep": "h2-00397", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 14.9367, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 301.6, "calls": 2, "tokens_in": 15655, "tokens_out": 6770, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791534952.2599058}
{"ep": "h2-00460", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0225, "status": "ok", "correct": true, "speedup": 1.0225, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 67.1, "calls": 2, "tokens_in": 14647, "tokens_out": 2577, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791534953.8596303}
{"ep": "h2-00443", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3618, "status": "ok", "correct": true, "speedup": 2.3618, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 112.0, "calls": 3, "tokens_in": 20860, "tokens_out": 3961, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534957.009485}
{"ep": "h2-00349", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2497, "status": "ok", "correct": true, "speedup": 1.2497, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 456.8, "calls": 2, "tokens_in": 28941, "tokens_out": 18912, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534959.3309932}
{"ep": "h2-00356", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0579, "status": "ok", "correct": true, "speedup": 0.0579, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 434.2, "calls": 5, "tokens_in": 63298, "tokens_out": 12411, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534968.3018441}
{"ep": "h2-00407", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0167, "status": "ok", "correct": true, "speedup": 1.0167, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 295.0, "calls": 1, "tokens_in": 6367, "tokens_out": 543, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791534969.4950528}
{"ep": "h2-00449", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7988, "status": "ok", "correct": true, "speedup": 0.7988, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 114.5, "calls": 2, "tokens_in": 12452, "tokens_out": 2103, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534970.7580528}
{"ep": "h2-00404", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 39.1082, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 309.1, "calls": 2, "tokens_in": 7031, "tokens_out": 7083, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534970.837035}
{"ep": "h2-00392", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 8.1076, "status": "ok", "correct": true, "speedup": 8.1076, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 332.9, "calls": 2, "tokens_in": 7010, "tokens_out": 19662, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534974.948235}
{"ep": "h2-00398", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3233, "status": "ok", "correct": true, "speedup": 0.3233, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 327.6, "calls": 3, "tokens_in": 23171, "tokens_out": 6479, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534978.5420127}
{"ep": "h2-00450", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9015, "status": "ok", "correct": true, "speedup": 0.9015, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 120.2, "calls": 2, "tokens_in": 13832, "tokens_out": 899, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534978.805267}
{"ep": "h2-00331", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.993, "status": "ok", "correct": true, "speedup": 0.993, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 539.3, "calls": 3, "tokens_in": 23001, "tokens_out": 3321, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791534980.9743326}
{"ep": "h2-00389", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3259, "status": "ok", "correct": true, "speedup": 2.3259, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 341.6, "calls": 2, "tokens_in": 13162, "tokens_out": 3822, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791534982.2025454}
{"ep": "h2-00426", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4549, "status": "ok", "correct": true, "speedup": 1.4549, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 208.3, "calls": 2, "tokens_in": 11168, "tokens_out": 4960, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791534982.8677845}
{"ep": "h2-00401", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 36.9305, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 326.4, "calls": 2, "tokens_in": 7055, "tokens_out": 7432, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534984.1964917}
{"ep": "h2-00373", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7823, "status": "ok", "correct": true, "speedup": 2.7823, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 386.5, "calls": 2, "tokens_in": 13758, "tokens_out": 4379, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791534986.6062043}
{"ep": "h2-00452", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0614, "status": "ok", "correct": true, "speedup": 1.0614, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 125.9, "calls": 2, "tokens_in": 4959, "tokens_out": 3474, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534990.6717858}
{"ep": "h2-00432", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.405, "status": "ok", "correct": true, "speedup": 1.405, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 196.7, "calls": 2, "tokens_in": 16784, "tokens_out": 8261, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791534995.6079493}
{"ep": "h2-00448", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.07, "status": "ok", "correct": true, "speedup": 0.07, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 143.1, "calls": 3, "tokens_in": 29345, "tokens_out": 8053, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791534995.6102037}
{"ep": "h2-00446", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.0917, "status": "ok", "correct": true, "speedup": 3.0917, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 147.7, "calls": 2, "tokens_in": 5856, "tokens_out": 7919, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791534997.7870471}
{"ep": "h2-00477", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7401, "status": "ok", "correct": true, "speedup": 0.7401, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 52.4, "calls": 1, "tokens_in": 6622, "tokens_out": 508, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791534998.4881063}
{"ep": "h2-00461", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0198, "status": "ok", "correct": true, "speedup": 1.0198, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 111.4, "calls": 3, "tokens_in": 15120, "tokens_out": 2555, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791535000.6613467}
{"ep": "h2-00415", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.3526, "status": "ok", "correct": true, "speedup": 3.3526, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 295.6, "calls": 3, "tokens_in": 17101, "tokens_out": 16574, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535001.2739866}
{"ep": "h2-00478", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.997, "status": "ok", "correct": true, "speedup": 0.997, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 50.1, "calls": 2, "tokens_in": 13450, "tokens_out": 1081, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791535001.3395143}
{"ep": "h2-00438", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6743, "status": "ok", "correct": true, "speedup": 0.6743, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 183.3, "calls": 3, "tokens_in": 50025, "tokens_out": 14949, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535002.866107}
{"ep": "h2-00250", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.3079, "status": "ok", "correct": true, "speedup": 5.3079, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 795.6, "calls": 3, "tokens_in": 13585, "tokens_out": 9649, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535005.831944}
{"ep": "h2-00447", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.0075, "status": "ok", "correct": true, "speedup": 3.0075, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 154.7, "calls": 2, "tokens_in": 6544, "tokens_out": 7191, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535007.215925}
{"ep": "h2-00406", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5495, "status": "ok", "correct": true, "speedup": 1.5495, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 341.8, "calls": 3, "tokens_in": 16242, "tokens_out": 12928, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535007.861391}
{"ep": "h2-00387", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.295, "status": "ok", "correct": true, "speedup": 5.295, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 374.0, "calls": 3, "tokens_in": 33562, "tokens_out": 28082, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535010.7673645}
{"ep": "h2-00379", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 25.7059, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 396.3, "calls": 3, "tokens_in": 15155, "tokens_out": 10138, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535016.1352882}
{"ep": "h2-00458", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2138, "status": "ok", "correct": true, "speedup": 1.2138, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 141.1, "calls": 2, "tokens_in": 6498, "tokens_out": 6056, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535016.6995087}
{"ep": "h2-00357", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1388, "status": "ok", "correct": true, "speedup": 1.1388, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 476.2, "calls": 2, "tokens_in": 31725, "tokens_out": 18879, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535017.5537236}
{"ep": "h2-00366", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.7152, "status": "ok", "correct": true, "speedup": 4.7152, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 455.9, "calls": 3, "tokens_in": 27089, "tokens_out": 14462, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535018.5852501}
{"ep": "h2-00455", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0667, "status": "ok", "correct": true, "speedup": 1.0667, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 150.8, "calls": 3, "tokens_in": 16407, "tokens_out": 2307, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535020.032495}
{"ep": "h2-00453", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0527, "status": "ok", "correct": true, "speedup": 1.0527, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 153.7, "calls": 2, "tokens_in": 11975, "tokens_out": 4228, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535022.6615376}
{"ep": "h2-00388", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0096, "status": "ok", "correct": true, "speedup": 1.0096, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 388.8, "calls": 3, "tokens_in": 24641, "tokens_out": 2141, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791535026.4987001}
{"ep": "h2-00465", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.042, "status": "ok", "correct": true, "speedup": 1.042, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 129.9, "calls": 2, "tokens_in": 4874, "tokens_out": 2690, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535037.403879}
{"ep": "h2-00408", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.2083, "status": "ok", "correct": true, "speedup": 4.2083, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 357.3, "calls": 3, "tokens_in": 31488, "tokens_out": 27331, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535037.5545387}
{"ep": "h2-00489", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'fused_conv3d_act': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_conv3d_act -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/inc", "wall_s": 78.8, "calls": 1, "tokens_in": 1723, "tokens_out": 1076, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535057.5893996}
{"ep": "h2-00434", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7704, "status": "ok", "correct": true, "speedup": 0.7704, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 257.2, "calls": 3, "tokens_in": 49830, "tokens_out": 14790, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535067.2367172}
{"ep": "h2-00491", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3292, "status": "ok", "correct": true, "speedup": 0.3292, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 85.8, "calls": 3, "tokens_in": 22626, "tokens_out": 5965, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535068.032277}
{"ep": "h2-00457", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.965, "status": "ok", "correct": true, "speedup": 0.965, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 199.1, "calls": 2, "tokens_in": 4847, "tokens_out": 2766, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535069.3895032}
{"ep": "h2-00441", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7243, "status": "ok", "correct": true, "speedup": 2.7243, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 229.1, "calls": 3, "tokens_in": 26598, "tokens_out": 14085, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535070.6812353}
{"ep": "h2-00479", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8766, "status": "ok", "correct": true, "speedup": 0.8766, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 125.3, "calls": 3, "tokens_in": 18899, "tokens_out": 1656, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535077.5323188}
{"ep": "h2-00464", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0236, "status": "ok", "correct": true, "speedup": 1.0236, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 173.9, "calls": 2, "tokens_in": 6315, "tokens_out": 7010, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535079.0160208}
{"ep": "h2-00439", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3148, "status": "ok", "correct": true, "speedup": 1.3148, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 263.1, "calls": 3, "tokens_in": 10333, "tokens_out": 6935, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535083.6358476}
{"ep": "h2-00467", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9767, "status": "ok", "correct": true, "speedup": 0.9767, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 170.4, "calls": 3, "tokens_in": 23797, "tokens_out": 2130, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535084.9572966}
{"ep": "h2-00497", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9175, "status": "ok", "correct": true, "speedup": 0.9175, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 92.9, "calls": 2, "tokens_in": 14577, "tokens_out": 8831, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535088.4721217}
{"ep": "h2-00463", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0588, "status": "ok", "correct": true, "speedup": 1.0588, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 197.5, "calls": 2, "tokens_in": 10501, "tokens_out": 2295, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535090.1006124}
{"ep": "h2-00483", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9241, "status": "ok", "correct": true, "speedup": 0.9241, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 123.1, "calls": 3, "tokens_in": 24261, "tokens_out": 2336, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535091.359124}
{"ep": "h2-00506", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.2965, "status": "ok", "correct": true, "speedup": 5.2965, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 87.5, "calls": 2, "tokens_in": 6428, "tokens_out": 6699, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535095.3562539}
{"ep": "h2-00466", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9268, "status": "ok", "correct": true, "speedup": 0.9268, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 197.3, "calls": 3, "tokens_in": 24291, "tokens_out": 2400, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535107.255046}
{"ep": "h2-00469", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0451, "status": "ok", "correct": true, "speedup": 1.0451, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 174.9, "calls": 2, "tokens_in": 12994, "tokens_out": 2191, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535107.8995123}
{"ep": "h2-00490", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6842, "status": "ok", "correct": true, "speedup": 0.6842, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 128.1, "calls": 2, "tokens_in": 14118, "tokens_out": 1658, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535109.1218405}
{"ep": "h2-00522", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0191, "status": "ok", "correct": true, "speedup": 1.0191, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 33.5, "calls": 1, "tokens_in": 1750, "tokens_out": 1679, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535111.0766208}
{"ep": "h2-00383", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0702, "status": "ok", "correct": true, "speedup": 0.0702, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 488.2, "calls": 4, "tokens_in": 51417, "tokens_out": 17428, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535116.0403461}
{"ep": "h2-00524", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8028, "status": "ok", "correct": true, "speedup": 0.8028, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 38.1, "calls": 3, "tokens_in": 18432, "tokens_out": 1386, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535121.7571075}
{"ep": "h2-00492", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9803, "status": "ok", "correct": true, "speedup": 0.9803, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 139.9, "calls": 2, "tokens_in": 12172, "tokens_out": 2802, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535122.768575}
{"ep": "h2-00516", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0059, "status": "ok", "correct": true, "speedup": 1.0059, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 92.9, "calls": 3, "tokens_in": 20191, "tokens_out": 2830, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791535130.432178}
{"ep": "h2-00530", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.843, "status": "ok", "correct": true, "speedup": 0.843, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 29.2, "calls": 1, "tokens_in": 7030, "tokens_out": 1241, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535136.4057276}
{"ep": "h2-00501", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4473, "status": "ok", "correct": true, "speedup": 1.4473, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 149.6, "calls": 2, "tokens_in": 6382, "tokens_out": 7142, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535150.917485}
{"ep": "h2-00525", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0429, "status": "ok", "correct": true, "speedup": 1.0429, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.4, "calls": 2, "tokens_in": 5087, "tokens_out": 3188, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535153.3153641}
{"ep": "h2-00535", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0024, "status": "ok", "correct": true, "speedup": 1.0024, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 34.2, "calls": 1, "tokens_in": 1501, "tokens_out": 699, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535155.973448}
{"ep": "h2-00527", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0205, "status": "ok", "correct": true, "speedup": 1.0205, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 69.7, "calls": 2, "tokens_in": 4078, "tokens_out": 1940, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535159.7599344}
{"ep": "h2-00526", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'resnet_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=resnet_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/tor", "wall_s": 77.4, "calls": 1, "tokens_in": 2743, "tokens_out": 2627, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535165.9078584}
{"ep": "h2-00519", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0289, "status": "ok", "correct": true, "speedup": 1.0289, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 100.0, "calls": 1, "tokens_in": 5832, "tokens_out": 542, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791535168.0071757}
{"ep": "h2-00514", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.787, "status": "ok", "correct": true, "speedup": 0.787, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 142.7, "calls": 3, "tokens_in": 50127, "tokens_out": 14996, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535169.1493893}
{"ep": "h2-00470", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.015, "status": "ok", "correct": true, "speedup": 1.015, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 234.9, "calls": 3, "tokens_in": 24763, "tokens_out": 2246, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535169.926421}
{"ep": "h2-00529", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0427, "status": "ok", "correct": true, "speedup": 1.0427, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 77.3, "calls": 2, "tokens_in": 13019, "tokens_out": 2278, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535172.7037854}
{"ep": "h2-00380", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4965, "status": "ok", "correct": true, "speedup": 1.4965, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 553.0, "calls": 3, "tokens_in": 15845, "tokens_out": 12276, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535173.4133482}
{"ep": "h2-00517", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4819, "status": "ok", "correct": true, "speedup": 1.4819, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 130.1, "calls": 2, "tokens_in": 11101, "tokens_out": 5105, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535187.665648}
{"ep": "h2-00484", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0095, "status": "ok", "correct": true, "speedup": 1.0095, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 219.6, "calls": 2, "tokens_in": 12861, "tokens_out": 2802, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791535189.090729}
{"ep": "h2-00480", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.6673, "status": "ok", "correct": true, "speedup": 1.6673, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 239.5, "calls": 2, "tokens_in": 30339, "tokens_out": 21696, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535193.3898273}
{"ep": "h2-00537", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.837, "status": "ok", "correct": true, "speedup": 0.837, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 64.6, "calls": 3, "tokens_in": 21124, "tokens_out": 958, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535195.0376914}
{"ep": "h2-00520", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4385, "status": "ok", "correct": true, "speedup": 1.4385, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 130.7, "calls": 2, "tokens_in": 11165, "tokens_out": 5161, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535200.0913067}
{"ep": "h2-00503", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6464, "status": "ok", "correct": true, "speedup": 2.6464, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 200.6, "calls": 3, "tokens_in": 27141, "tokens_out": 17421, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535203.4613836}
{"ep": "h2-00476", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0301, "status": "ok", "correct": true, "speedup": 1.0301, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 260.2, "calls": 2, "tokens_in": 4493, "tokens_out": 2361, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535205.5586917}
{"ep": "h2-00545", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.003, "status": "ok", "correct": true, "speedup": 1.003, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 41.8, "calls": 2, "tokens_in": 11396, "tokens_out": 1094, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535210.9768634}
{"ep": "h2-00402", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4645, "status": "ok", "correct": true, "speedup": 1.4645, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 552.8, "calls": 2, "tokens_in": 11228, "tokens_out": 5338, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535213.1402438}
{"ep": "h2-00285", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8058, "status": "ok", "correct": true, "speedup": 0.8058, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 937.2, "calls": 5, "tokens_in": 60562, "tokens_out": 14443, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535225.2474113}
{"ep": "h2-00542", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5979, "status": "ok", "correct": true, "speedup": 0.5979, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 71.9, "calls": 1, "tokens_in": 6622, "tokens_out": 496, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535231.620259}
{"ep": "h2-00502", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0195, "status": "ok", "correct": true, "speedup": 1.0195, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 230.4, "calls": 4, "tokens_in": 35584, "tokens_out": 4248, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791535231.7642817}
{"ep": "h2-00544", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6557, "status": "ok", "correct": true, "speedup": 2.6557, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 65.3, "calls": 2, "tokens_in": 13094, "tokens_out": 4418, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535233.3072999}
{"ep": "h2-00523", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9781, "status": "ok", "correct": true, "speedup": 0.9781, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 159.3, "calls": 2, "tokens_in": 12317, "tokens_out": 2978, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535238.3210697}
{"ep": "h2-00534", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2711, "status": "ok", "correct": true, "speedup": 0.2711, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 127.4, "calls": 4, "tokens_in": 36961, "tokens_out": 7973, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535243.4322507}
{"ep": "h2-00462", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0032, "status": "ok", "correct": true, "speedup": 1.0032, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 352.1, "calls": 3, "tokens_in": 19801, "tokens_out": 2104, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535244.54398}
{"ep": "h2-00473", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.9083, "status": "ok", "correct": true, "speedup": 3.9083, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 304.5, "calls": 2, "tokens_in": 7623, "tokens_out": 11442, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535246.5106828}
{"ep": "h2-00510", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0544, "status": "ok", "correct": true, "speedup": 1.0544, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 232.3, "calls": 4, "tokens_in": 19356, "tokens_out": 4346, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535249.8273427}
{"ep": "h2-00512", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9755, "status": "ok", "correct": true, "speedup": 0.9755, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 230.2, "calls": 3, "tokens_in": 24026, "tokens_out": 2354, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535250.191556}
{"ep": "h2-00536", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8957, "status": "ok", "correct": true, "speedup": 0.8957, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 129.2, "calls": 4, "tokens_in": 29571, "tokens_out": 1476, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535251.9969585}
{"ep": "h2-00546", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0094, "status": "ok", "correct": true, "speedup": 1.0094, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 82.1, "calls": 2, "tokens_in": 4006, "tokens_out": 2071, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535252.042514}
{"ep": "h2-00551", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9819, "status": "ok", "correct": true, "speedup": 0.9819, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 62.7, "calls": 1, "tokens_in": 5488, "tokens_out": 752, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535256.0669537}
{"ep": "h2-00552", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0635, "status": "ok", "correct": true, "speedup": 1.0635, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 63.3, "calls": 2, "tokens_in": 4965, "tokens_out": 3585, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535258.3644316}
{"ep": "h2-00509", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3348, "status": "ok", "correct": true, "speedup": 1.3348, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 242.3, "calls": 1, "tokens_in": 5998, "tokens_out": 723, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791535259.0429235}
{"ep": "h2-00549", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0134, "status": "ok", "correct": true, "speedup": 1.0134, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 74.4, "calls": 2, "tokens_in": 10546, "tokens_out": 3239, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791535262.0722847}
{"ep": "h2-00547", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6744, "status": "ok", "correct": true, "speedup": 2.6744, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 90.6, "calls": 2, "tokens_in": 12934, "tokens_out": 4145, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535263.2594864}
{"ep": "h2-00528", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 37.0805, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 173.7, "calls": 2, "tokens_in": 7100, "tokens_out": 7101, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535265.0125403}
{"ep": "h2-00482", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0178, "status": "ok", "correct": true, "speedup": 1.0178, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 308.7, "calls": 2, "tokens_in": 15478, "tokens_out": 3303, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791535268.0451949}
{"ep": "h2-00515", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3478, "status": "ok", "correct": true, "speedup": 1.3478, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 234.1, "calls": 2, "tokens_in": 14707, "tokens_out": 16453, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535271.5262663}
{"ep": "h2-00543", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0652, "status": "ok", "correct": true, "speedup": 1.0652, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 105.7, "calls": 2, "tokens_in": 10492, "tokens_out": 2293, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535271.6006653}
{"ep": "h2-00456", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7077, "status": "ok", "correct": true, "speedup": 0.7077, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 404.4, "calls": 2, "tokens_in": 5942, "tokens_out": 7912, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535273.6644564}
{"ep": "h2-00471", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0104, "status": "ok", "correct": true, "speedup": 1.0104, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 336.7, "calls": 2, "tokens_in": 4178, "tokens_out": 2230, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535274.9128532}
{"ep": "h2-00554", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9756, "status": "ok", "correct": true, "speedup": 0.9756, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 79.4, "calls": 1, "tokens_in": 7032, "tokens_out": 1339, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535282.9072704}
{"ep": "h2-00494", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6177, "status": "ok", "correct": true, "speedup": 0.6177, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 301.9, "calls": 3, "tokens_in": 18762, "tokens_out": 1537, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535288.4645872}
{"ep": "h2-00548", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'fused_lse_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_lse_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/t", "wall_s": 118.4, "calls": 1, "tokens_in": 1818, "tokens_out": 8671, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535291.8342736}
{"ep": "h2-00532", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9488, "status": "ok", "correct": true, "speedup": 0.9488, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 189.6, "calls": 2, "tokens_in": 13865, "tokens_out": 12659, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535298.755108}
{"ep": "h2-00518", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.717, "status": "ok", "correct": true, "speedup": 2.717, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 238.8, "calls": 2, "tokens_in": 7886, "tokens_out": 10400, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535306.0813184}
{"ep": "h2-00385", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0624, "status": "ok", "correct": true, "speedup": 1.0624, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 676.0, "calls": 2, "tokens_in": 4781, "tokens_out": 3090, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535309.4415274}
{"ep": "h2-00531", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0107, "status": "ok", "correct": true, "speedup": 1.0107, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 205.2, "calls": 2, "tokens_in": 6287, "tokens_out": 7241, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535313.1466198}
{"ep": "h2-00521", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.003, "status": "ok", "correct": true, "speedup": 1.003, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 242.5, "calls": 5, "tokens_in": 25202, "tokens_out": 3949, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535313.1741154}
{"ep": "h2-00486", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0681, "status": "ok", "correct": true, "speedup": 1.0681, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 343.3, "calls": 2, "tokens_in": 13853, "tokens_out": 3289, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535314.1781096}
{"ep": "h2-00582", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8015, "status": "ok", "correct": true, "speedup": 0.8015, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 33.8, "calls": 1, "tokens_in": 1984, "tokens_out": 736, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535322.2619615}
{"ep": "h2-00539", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3204, "status": "ok", "correct": true, "speedup": 2.3204, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 171.7, "calls": 3, "tokens_in": 16220, "tokens_out": 12499, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535322.5864847}
{"ep": "h2-00557", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0287, "status": "ok", "correct": true, "speedup": 1.0287, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 110.2, "calls": 1, "tokens_in": 5832, "tokens_out": 524, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791535323.2964118}
{"ep": "h2-00559", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0115, "status": "ok", "correct": true, "speedup": 1.0115, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 93.6, "calls": 3, "tokens_in": 19805, "tokens_out": 2073, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535325.2331603}
{"ep": "h2-00481", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6643, "status": "ok", "correct": true, "speedup": 2.6643, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 369.4, "calls": 2, "tokens_in": 13006, "tokens_out": 4188, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535326.4333868}
{"ep": "h2-00533", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.0042, "status": "ok", "correct": true, "speedup": 3.0042, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 218.2, "calls": 2, "tokens_in": 15405, "tokens_out": 5539, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535329.2568898}
{"ep": "h2-00508", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0064, "status": "ok", "correct": true, "speedup": 1.0064, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 313.8, "calls": 2, "tokens_in": 4043, "tokens_out": 2190, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535329.9649053}
{"ep": "h2-00561", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9982, "status": "ok", "correct": true, "speedup": 0.9982, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 97.8, "calls": 2, "tokens_in": 4160, "tokens_out": 1946, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535331.106959}
{"ep": "h2-00574", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'resnet_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=resnet_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/tor", "wall_s": 69.1, "calls": 1, "tokens_in": 2743, "tokens_out": 2470, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535332.351947}
{"ep": "h2-00433", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7777, "status": "ok", "correct": true, "speedup": 2.7777, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 526.6, "calls": 3, "tokens_in": 13714, "tokens_out": 9957, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535334.5845096}
{"ep": "h2-00564", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0594, "status": "ok", "correct": true, "speedup": 1.0594, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 91.9, "calls": 3, "tokens_in": 25400, "tokens_out": 4290, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535336.4823318}
{"ep": "h2-00511", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0091, "status": "ok", "correct": true, "speedup": 1.0091, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 318.7, "calls": 2, "tokens_in": 11624, "tokens_out": 1328, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535337.3311472}
{"ep": "h2-00585", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8496, "status": "ok", "correct": true, "speedup": 0.8496, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 35.8, "calls": 1, "tokens_in": 7030, "tokens_out": 1203, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535341.8677433}
{"ep": "h2-00540", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0125, "status": "ok", "correct": true, "speedup": 0.0125, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 200.5, "calls": 2, "tokens_in": 16690, "tokens_out": 5757, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535353.775985}
{"ep": "h2-00414", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7089, "status": "ok", "correct": true, "speedup": 2.7089, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 651.4, "calls": 2, "tokens_in": 15505, "tokens_out": 38578, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535354.8388596}
{"ep": "h2-00589", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7829, "status": "ok", "correct": true, "speedup": 0.7829, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 42.8, "calls": 3, "tokens_in": 18948, "tokens_out": 1612, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535357.011875}
{"ep": "h2-00556", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0556, "status": "ok", "correct": true, "speedup": 1.0556, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 147.2, "calls": 2, "tokens_in": 8387, "tokens_out": 6481, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535358.154074}
{"ep": "h2-00538", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9509, "status": "ok", "correct": true, "speedup": 0.9509, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 225.5, "calls": 2, "tokens_in": 14039, "tokens_out": 11914, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535361.906559}
{"ep": "h2-00573", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0183, "status": "ok", "correct": true, "speedup": 1.0183, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 100.1, "calls": 1, "tokens_in": 1750, "tokens_out": 2385, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535362.2168067}
{"ep": "h2-00578", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8143, "status": "ok", "correct": true, "speedup": 0.8143, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 91.2, "calls": 1, "tokens_in": 1984, "tokens_out": 817, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535362.76161}
{"ep": "h2-00560", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0142, "status": "ok", "correct": true, "speedup": 1.0142, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 132.2, "calls": 2, "tokens_in": 11422, "tokens_out": 4410, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791535363.9340377}
{"ep": "h2-00499", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.2788, "status": "ok", "correct": true, "speedup": 3.2788, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 368.4, "calls": 2, "tokens_in": 15469, "tokens_out": 5616, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535366.9304185}
{"ep": "h2-00562", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0705, "status": "ok", "correct": true, "speedup": 1.0705, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 129.2, "calls": 2, "tokens_in": 4643, "tokens_out": 2300, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535367.5694556}
{"ep": "h2-00572", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2009, "status": "ok", "correct": true, "speedup": 0.2009, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 113.7, "calls": 2, "tokens_in": 15362, "tokens_out": 6430, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535372.7209737}
{"ep": "h2-00488", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8452, "status": "ok", "correct": true, "speedup": 0.8452, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 394.2, "calls": 2, "tokens_in": 15814, "tokens_out": 3203, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535372.790493}
{"ep": "h2-00595", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9995, "status": "ok", "correct": true, "speedup": 0.9995, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 43.9, "calls": 1, "tokens_in": 2181, "tokens_out": 983, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535373.1429718}
{"ep": "h2-00555", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.646, "status": "ok", "correct": true, "speedup": 2.646, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 169.8, "calls": 2, "tokens_in": 13048, "tokens_out": 4195, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535375.3658655}
{"ep": "h2-00584", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0085, "status": "ok", "correct": true, "speedup": 1.0085, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 77.1, "calls": 2, "tokens_in": 12742, "tokens_out": 2077, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535375.8372095}
{"ep": "h2-00507", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0049, "status": "ok", "correct": true, "speedup": 1.0049, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 368.7, "calls": 3, "tokens_in": 19849, "tokens_out": 2071, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535379.4355102}
{"ep": "h2-00558", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.199, "status": "ok", "correct": true, "speedup": 1.199, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 157.2, "calls": 3, "tokens_in": 9728, "tokens_out": 3855, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535382.4719286}
{"ep": "h2-00594", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.634, "status": "ok", "correct": true, "speedup": 0.634, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 58.8, "calls": 1, "tokens_in": 1647, "tokens_out": 449, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535385.2475488}
{"ep": "h2-00475", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0657, "status": "ok", "correct": true, "speedup": 1.0657, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 442.6, "calls": 2, "tokens_in": 10501, "tokens_out": 2302, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535385.2922564}
{"ep": "h2-00576", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0631, "status": "ok", "correct": true, "speedup": 1.0631, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 119.2, "calls": 2, "tokens_in": 9154, "tokens_out": 8327, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535387.2687507}
{"ep": "h2-00597", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0003, "status": "ok", "correct": true, "speedup": 1.0003, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 61.3, "calls": 2, "tokens_in": 13440, "tokens_out": 1112, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791535392.383671}
{"ep": "h2-00504", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8445, "status": "ok", "correct": true, "speedup": 0.8445, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 392.8, "calls": 1, "tokens_in": 7030, "tokens_out": 1203, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535398.6022785}
{"ep": "h2-00496", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0001, "status": "ok", "correct": true, "speedup": 1.0001, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 404.1, "calls": 1, "tokens_in": 5369, "tokens_out": 564, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535399.7527075}
{"ep": "h2-00468", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4119, "status": "ok", "correct": true, "speedup": 1.4119, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 478.1, "calls": 2, "tokens_in": 5201, "tokens_out": 5042, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535401.724528}
{"ep": "h2-00583", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9913, "status": "ok", "correct": true, "speedup": 0.9913, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 110.6, "calls": 2, "tokens_in": 15575, "tokens_out": 2157, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535402.4063604}
{"ep": "h2-00493", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0141, "status": "ok", "correct": true, "speedup": 1.0141, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 421.3, "calls": 3, "tokens_in": 24633, "tokens_out": 2103, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791535405.5281608}
{"ep": "h2-00571", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8476, "status": "ok", "correct": true, "speedup": 0.8476, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 153.1, "calls": 1, "tokens_in": 7030, "tokens_out": 1207, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535411.5119667}
{"ep": "h2-00566", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.02, "status": "ok", "correct": true, "speedup": 1.02, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 165.9, "calls": 2, "tokens_in": 10190, "tokens_out": 3172, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791535415.7056272}
{"ep": "h2-00474", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.4153, "status": "ok", "correct": true, "speedup": 3.4153, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 473.6, "calls": 3, "tokens_in": 15908, "tokens_out": 13485, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535415.8530035}
{"ep": "h2-00553", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0263, "status": "ok", "correct": true, "speedup": 1.0263, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 216.9, "calls": 2, "tokens_in": 4392, "tokens_out": 2205, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535416.9790416}
{"ep": "h2-00602", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'mbconv_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=mbconv_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/tor", "wall_s": 78.4, "calls": 1, "tokens_in": 2159, "tokens_out": 2077, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535420.251513}
{"ep": "h2-00603", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5542, "status": "ok", "correct": true, "speedup": 0.5542, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 85.5, "calls": 1, "tokens_in": 1565, "tokens_out": 1862, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535439.2675173}
{"ep": "h2-00575", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3791, "status": "ok", "correct": true, "speedup": 1.3791, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 179.9, "calls": 2, "tokens_in": 5277, "tokens_out": 4345, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535444.8749382}
{"ep": "h2-00472", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4618, "status": "ok", "correct": true, "speedup": 1.4618, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 508.8, "calls": 2, "tokens_in": 11313, "tokens_out": 5636, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535447.8736002}
{"ep": "h2-00623", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7153, "status": "ok", "correct": true, "speedup": 0.7153, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 60.3, "calls": 2, "tokens_in": 16667, "tokens_out": 4635, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535452.7240715}
{"ep": "h2-00626", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.018, "status": "ok", "correct": true, "speedup": 1.018, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 53.9, "calls": 3, "tokens_in": 23780, "tokens_out": 2501, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791535455.6238441}
{"ep": "h2-00629", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0177, "status": "ok", "correct": true, "speedup": 1.0177, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 56.2, "calls": 2, "tokens_in": 9146, "tokens_out": 1795, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791535467.6864295}
{"ep": "h2-00565", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7822, "status": "ok", "correct": true, "speedup": 0.7822, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 226.2, "calls": 2, "tokens_in": 16880, "tokens_out": 7577, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535472.7501998}
{"ep": "h2-00592", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0167, "status": "ok", "correct": true, "speedup": 1.0167, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 150.1, "calls": 3, "tokens_in": 24697, "tokens_out": 2223, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535473.4079666}
{"ep": "h2-00500", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0062, "status": "ok", "correct": true, "speedup": 1.0062, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 474.8, "calls": 3, "tokens_in": 19941, "tokens_out": 2710, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791535475.5032516}
{"ep": "h2-00577", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4071, "status": "ok", "correct": true, "speedup": 1.4071, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 208.0, "calls": 2, "tokens_in": 30845, "tokens_out": 18025, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535479.5204756}
{"ep": "h2-00618", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0065, "status": "ok", "correct": true, "speedup": 1.0065, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 100.3, "calls": 3, "tokens_in": 19871, "tokens_out": 2148, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535479.728046}
{"ep": "h2-00598", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9766, "status": "ok", "correct": true, "speedup": 0.9766, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 149.1, "calls": 1, "tokens_in": 7032, "tokens_out": 1135, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535481.44699}
{"ep": "h2-00599", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5507, "status": "ok", "correct": true, "speedup": 0.5507, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 148.2, "calls": 3, "tokens_in": 20425, "tokens_out": 3558, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535482.7542841}
{"ep": "h2-00550", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0699, "status": "ok", "correct": true, "speedup": 1.0699, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 298.8, "calls": 2, "tokens_in": 14429, "tokens_out": 19471, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535487.8410602}
{"ep": "h2-00633", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8398, "status": "ok", "correct": true, "speedup": 0.8398, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 68.6, "calls": 2, "tokens_in": 15382, "tokens_out": 2374, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535488.8293548}
{"ep": "h2-00635", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0041, "status": "ok", "correct": true, "speedup": 1.0041, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 45.4, "calls": 3, "tokens_in": 17460, "tokens_out": 1107, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535490.3142052}
{"ep": "h2-00591", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.6155, "status": "ok", "correct": true, "speedup": 1.6155, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 167.8, "calls": 2, "tokens_in": 5795, "tokens_out": 5126, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535490.3962004}
{"ep": "h2-00605", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0519, "status": "ok", "correct": true, "speedup": 1.0519, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 133.4, "calls": 2, "tokens_in": 11788, "tokens_out": 3853, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535490.4044478}
{"ep": "h2-00495", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0179, "status": "ok", "correct": true, "speedup": 1.0179, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 501.8, "calls": 2, "tokens_in": 15507, "tokens_out": 3406, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791535492.5087903}
{"ep": "h2-00612", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0009, "status": "ok", "correct": true, "speedup": 1.0009, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 125.2, "calls": 3, "tokens_in": 17520, "tokens_out": 1167, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535492.8026493}
{"ep": "h2-00630", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0129, "status": "ok", "correct": true, "speedup": 1.0129, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 78.0, "calls": 3, "tokens_in": 25004, "tokens_out": 2405, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535493.6900778}
{"ep": "h2-00579", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0827, "status": "ok", "correct": true, "speedup": 1.0827, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 233.9, "calls": 4, "tokens_in": 14356, "tokens_out": 3630, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535507.6105063}
{"ep": "h2-00634", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0266, "status": "ok", "correct": true, "speedup": 1.0266, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.7, "calls": 1, "tokens_in": 5832, "tokens_out": 524, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791535508.0043163}
{"ep": "h2-00588", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0119, "status": "ok", "correct": true, "speedup": 1.0119, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 195.0, "calls": 2, "tokens_in": 15162, "tokens_out": 5309, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791535508.1715333}
{"ep": "h2-00639", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8024, "status": "ok", "correct": true, "speedup": 0.8024, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 49.0, "calls": 3, "tokens_in": 19213, "tokens_out": 1736, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535516.7265742}
{"ep": "h2-00647", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "forbidden", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "static check failed: line 57: getattr needs a literal, non-private attribute name; line 58: getattr needs a literal, non-private attribute name; line 59: getattr needs a literal, non-private attribute name; line 60: getattr needs a literal, non-private attribute name", "wall_s": 29.1, "calls": 1, "tokens_in": 1964, "tokens_out": 2636, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535516.9570427}
{"ep": "h2-00615", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7721, "status": "ok", "correct": true, "speedup": 0.7721, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 149.5, "calls": 3, "tokens_in": 49911, "tokens_out": 14884, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535522.6442163}
{"ep": "h2-00607", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3219, "status": "ok", "correct": true, "speedup": 0.3219, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 162.2, "calls": 3, "tokens_in": 23036, "tokens_out": 6385, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535524.1000128}
{"ep": "h2-00631", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1615, "status": "ok", "correct": true, "speedup": 1.1615, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 108.7, "calls": 3, "tokens_in": 30477, "tokens_out": 6562, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535524.5364742}
{"ep": "h2-00609", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1178, "status": "ok", "correct": true, "speedup": 1.1178, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 162.9, "calls": 2, "tokens_in": 15559, "tokens_out": 3652, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535525.7116005}
{"ep": "h2-00601", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9623, "status": "ok", "correct": true, "speedup": 0.9623, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 190.4, "calls": 2, "tokens_in": 8356, "tokens_out": 6467, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535527.7207317}
{"ep": "h2-00625", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4264, "status": "ok", "correct": true, "speedup": 1.4264, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 132.9, "calls": 2, "tokens_in": 12999, "tokens_out": 6059, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535532.6173007}
{"ep": "h2-00638", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0179, "status": "ok", "correct": true, "speedup": 1.0179, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 80.1, "calls": 2, "tokens_in": 16861, "tokens_out": 4465, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535535.6931472}
{"ep": "h2-00610", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9229, "status": "ok", "correct": true, "speedup": 0.9229, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 179.8, "calls": 3, "tokens_in": 24329, "tokens_out": 2436, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535543.7020316}
{"ep": "h2-00586", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0262, "status": "ok", "correct": true, "speedup": 1.0262, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 234.6, "calls": 2, "tokens_in": 5486, "tokens_out": 5679, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535544.0076826}
{"ep": "h2-00632", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9938, "status": "ok", "correct": true, "speedup": 0.9938, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 127.3, "calls": 3, "tokens_in": 22620, "tokens_out": 3139, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791535544.230095}
{"ep": "h2-00590", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3246, "status": "ok", "correct": true, "speedup": 0.3246, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 245.0, "calls": 3, "tokens_in": 22476, "tokens_out": 5834, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535567.2956357}
{"ep": "h2-00645", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0354, "status": "ok", "correct": true, "speedup": 1.0354, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 87.5, "calls": 2, "tokens_in": 12924, "tokens_out": 2168, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535568.9718146}
{"ep": "h2-00652", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0171, "status": "ok", "correct": true, "speedup": 1.0171, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 76.9, "calls": 2, "tokens_in": 9712, "tokens_out": 2389, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791535569.3785212}
{"ep": "h2-00620", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0086, "status": "ok", "correct": true, "speedup": 1.0086, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 190.1, "calls": 1, "tokens_in": 6367, "tokens_out": 532, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791535575.396112}
{"ep": "h2-00485", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6277, "status": "ok", "correct": true, "speedup": 0.6277, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 606.8, "calls": 5, "tokens_in": 57166, "tokens_out": 12081, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535577.5179837}
{"ep": "h2-00637", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4123, "status": "ok", "correct": true, "speedup": 1.4123, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 125.5, "calls": 2, "tokens_in": 4997, "tokens_out": 4921, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535578.2522025}
{"ep": "h2-00663", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'bias_relu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bias_relu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/t", "wall_s": 58.8, "calls": 1, "tokens_in": 1622, "tokens_out": 827, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535584.5489776}
{"ep": "h2-00643", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0069, "status": "ok", "correct": true, "speedup": 1.0069, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 105.8, "calls": 2, "tokens_in": 16257, "tokens_out": 2870, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791535585.2824945}
{"ep": "h2-00604", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4725, "status": "ok", "correct": true, "speedup": 1.4725, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 233.4, "calls": 2, "tokens_in": 11228, "tokens_out": 4891, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535588.257242}
{"ep": "h2-00606", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4651, "status": "ok", "correct": true, "speedup": 1.4651, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 235.1, "calls": 2, "tokens_in": 11221, "tokens_out": 5550, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535593.2728002}
{"ep": "h2-00656", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.011, "status": "ok", "correct": true, "speedup": 1.011, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 85.9, "calls": 2, "tokens_in": 16212, "tokens_out": 2479, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791535593.920363}
{"ep": "h2-00650", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0496, "status": "ok", "correct": true, "speedup": 1.0496, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 110.2, "calls": 2, "tokens_in": 5555, "tokens_out": 4790, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535600.6174877}
{"ep": "h2-00513", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0129, "status": "ok", "correct": true, "speedup": 1.0129, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 579.7, "calls": 2, "tokens_in": 16189, "tokens_out": 2549, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791535602.3406649}
{"ep": "h2-00666", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0527, "status": "ok", "correct": true, "speedup": 1.0527, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 71.1, "calls": 3, "tokens_in": 18633, "tokens_out": 3761, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535606.7911365}
{"ep": "h2-00667", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.849, "status": "ok", "correct": true, "speedup": 0.849, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 63.8, "calls": 2, "tokens_in": 15402, "tokens_out": 2415, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535607.5420637}
{"ep": "h2-00654", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0514, "status": "ok", "correct": true, "speedup": 1.0514, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 121.0, "calls": 3, "tokens_in": 22858, "tokens_out": 2415, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791535614.6544175}
{"ep": "h2-00642", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9945, "status": "ok", "correct": true, "speedup": 0.9945, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 141.0, "calls": 2, "tokens_in": 14697, "tokens_out": 2917, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535616.5500748}
{"ep": "h2-00498", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.019, "status": "ok", "correct": true, "speedup": 1.019, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 621.3, "calls": 2, "tokens_in": 15356, "tokens_out": 3046, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791535619.08359}
{"ep": "h2-00653", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4763, "status": "ok", "correct": true, "speedup": 1.4763, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 139.2, "calls": 2, "tokens_in": 11287, "tokens_out": 5316, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535631.9629161}
{"ep": "h2-00646", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.9405, "status": "ok", "correct": true, "speedup": 2.9405, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 149.6, "calls": 2, "tokens_in": 13988, "tokens_out": 4621, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791535632.3947186}
{"ep": "h2-00648", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0063, "status": "ok", "correct": true, "speedup": 1.0063, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 143.7, "calls": 2, "tokens_in": 6137, "tokens_out": 6673, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535632.5587835}
{"ep": "h2-00655", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0149, "status": "ok", "correct": true, "speedup": 1.0149, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 125.4, "calls": 2, "tokens_in": 5468, "tokens_out": 4678, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535632.9654047}
{"ep": "h2-00675", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'diag_mul_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=diag_mul_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/tor", "wall_s": 56.2, "calls": 1, "tokens_in": 1647, "tokens_out": 901, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535634.4514859}
{"ep": "h2-00672", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0068, "status": "ok", "correct": true, "speedup": 1.0068, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.0, "calls": 1, "tokens_in": 6477, "tokens_out": 502, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791535637.4192464}
{"ep": "h2-00668", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0025, "status": "ok", "correct": true, "speedup": 1.0025, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 96.9, "calls": 2, "tokens_in": 11412, "tokens_out": 1126, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535640.8832645}
{"ep": "h2-00657", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3046, "status": "ok", "correct": true, "speedup": 0.3046, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 138.7, "calls": 4, "tokens_in": 43097, "tokens_out": 10944, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535646.8834982}
{"ep": "h2-00627", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3301, "status": "ok", "correct": true, "speedup": 1.3301, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 245.5, "calls": 1, "tokens_in": 5998, "tokens_out": 768, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791535647.9051323}
{"ep": "h2-00674", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0, "status": "ok", "correct": true, "speedup": 1.0, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 75.0, "calls": 2, "tokens_in": 13375, "tokens_out": 972, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791535652.5007832}
{"ep": "h2-00658", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.338, "status": "ok", "correct": true, "speedup": 2.338, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 136.0, "calls": 2, "tokens_in": 15275, "tokens_out": 5959, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535652.758623}
{"ep": "h2-00671", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0295, "status": "ok", "correct": true, "speedup": 1.0295, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 85.8, "calls": 3, "tokens_in": 27326, "tokens_out": 4562, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535654.745314}
{"ep": "h2-00669", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9778, "status": "ok", "correct": true, "speedup": 0.9778, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 111.1, "calls": 1, "tokens_in": 7032, "tokens_out": 1137, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535655.3318667}
{"ep": "h2-00664", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0633, "status": "ok", "correct": true, "speedup": 1.0633, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 128.5, "calls": 3, "tokens_in": 24344, "tokens_out": 3134, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791535656.2704463}
{"ep": "h2-00682", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0027, "status": "ok", "correct": true, "speedup": 1.0027, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 54.3, "calls": 2, "tokens_in": 11412, "tokens_out": 1126, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535656.6572394}
{"ep": "h2-00617", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.009, "status": "ok", "correct": true, "speedup": 2.009, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 282.6, "calls": 2, "tokens_in": 32661, "tokens_out": 24841, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535658.465866}
{"ep": "h2-00570", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0559, "status": "ok", "correct": true, "speedup": 1.0559, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 403.2, "calls": 3, "tokens_in": 23159, "tokens_out": 2546, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791535659.239602}
{"ep": "h2-00568", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.065, "status": "ok", "correct": true, "speedup": 1.065, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 410.6, "calls": 2, "tokens_in": 14733, "tokens_out": 2464, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791535662.5512686}
{"ep": "h2-00613", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3852, "status": "ok", "correct": true, "speedup": 1.3852, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 292.1, "calls": 2, "tokens_in": 15882, "tokens_out": 27019, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535664.8156211}
{"ep": "h2-00621", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8032, "status": "ok", "correct": true, "speedup": 0.8032, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 284.4, "calls": 2, "tokens_in": 4940, "tokens_out": 1580, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535669.6482494}
{"ep": "h2-00611", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0279, "status": "ok", "correct": true, "speedup": 1.0279, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 303.7, "calls": 2, "tokens_in": 12716, "tokens_out": 1585, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791535670.6232016}
{"ep": "h2-00651", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.02, "status": "ok", "correct": true, "speedup": 1.02, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 188.0, "calls": 3, "tokens_in": 9512, "tokens_out": 3587, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535678.446877}
{"ep": "h2-00541", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.0927, "status": "ok", "correct": true, "speedup": 3.0927, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 526.6, "calls": 3, "tokens_in": 16862, "tokens_out": 13790, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535682.6105728}
{"ep": "h2-00581", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.994, "status": "ok", "correct": true, "speedup": 1.994, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 400.8, "calls": 2, "tokens_in": 30797, "tokens_out": 22266, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535683.7178314}
{"ep": "h2-00563", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4609, "status": "ok", "correct": true, "speedup": 0.4609, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 440.5, "calls": 2, "tokens_in": 6716, "tokens_out": 10949, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535683.965662}
{"ep": "h2-00487", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7169, "status": "ok", "correct": true, "speedup": 0.7169, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 709.4, "calls": 2, "tokens_in": 16277, "tokens_out": 4297, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535684.3583384}
{"ep": "h2-00685", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'touch_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=touch_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csr", "wall_s": 72.6, "calls": 1, "tokens_in": 2157, "tokens_out": 1009, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535687.2827353}
{"ep": "h2-00705", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0044, "status": "ok", "correct": true, "speedup": 1.0044, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 24.8, "calls": 1, "tokens_in": 6477, "tokens_out": 489, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791535687.3161535}
{"ep": "h2-00628", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0068, "status": "ok", "correct": true, "speedup": 1.0068, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 285.8, "calls": 1, "tokens_in": 6367, "tokens_out": 543, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791535691.3461368}
{"ep": "h2-00640", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9618, "status": "ok", "correct": true, "speedup": 0.9618, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 219.2, "calls": 2, "tokens_in": 14285, "tokens_out": 12774, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535691.9473197}
{"ep": "h2-00662", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9999, "status": "ok", "correct": true, "speedup": 0.9999, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 167.6, "calls": 4, "tokens_in": 27228, "tokens_out": 2340, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535692.1694417}
{"ep": "h2-00580", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.3477, "status": "ok", "correct": true, "speedup": 4.3477, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 427.4, "calls": 3, "tokens_in": 14494, "tokens_out": 11434, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535702.2674534}
{"ep": "h2-00684", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9813, "status": "ok", "correct": true, "speedup": 0.9813, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 98.5, "calls": 3, "tokens_in": 18701, "tokens_out": 1538, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535706.024162}
{"ep": "h2-00505", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4971, "status": "ok", "correct": true, "speedup": 0.4971, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 703.9, "calls": 5, "tokens_in": 57562, "tokens_out": 12031, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535711.0863194}
{"ep": "h2-00596", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7675, "status": "ok", "correct": true, "speedup": 0.7675, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 381.4, "calls": 3, "tokens_in": 50029, "tokens_out": 14741, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791535711.375026}
{"ep": "h2-00676", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0062, "status": "ok", "correct": true, "speedup": 1.0062, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 128.3, "calls": 2, "tokens_in": 13637, "tokens_out": 1094, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791535712.8031743}
{"ep": "h2-00696", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0118, "status": "ok", "correct": true, "speedup": 1.0118, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 66.5, "calls": 1, "tokens_in": 1744, "tokens_out": 3601, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535714.447973}
{"ep": "h2-00689", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.995, "status": "ok", "correct": true, "speedup": 1.995, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 89.3, "calls": 1, "tokens_in": 1818, "tokens_out": 2522, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535721.7405446}
{"ep": "h2-00649", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0609, "status": "ok", "correct": true, "speedup": 1.0609, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 232.3, "calls": 2, "tokens_in": 12887, "tokens_out": 4533, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535722.635861}
{"ep": "h2-00688", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0053, "status": "ok", "correct": true, "speedup": 1.0053, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 92.0, "calls": 2, "tokens_in": 4070, "tokens_out": 2131, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535723.939908}
{"ep": "h2-00665", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1954, "status": "ok", "correct": true, "speedup": 1.1954, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 195.4, "calls": 2, "tokens_in": 4944, "tokens_out": 5029, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535728.0312488}
{"ep": "h2-00690", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0507, "status": "ok", "correct": true, "speedup": 1.0507, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 95.6, "calls": 3, "tokens_in": 25846, "tokens_out": 4484, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535728.1642537}
{"ep": "h2-00644", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6004, "status": "ok", "correct": true, "speedup": 0.6004, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 249.2, "calls": 2, "tokens_in": 7188, "tokens_out": 10701, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535728.9616039}
{"ep": "h2-00587", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9907, "status": "ok", "correct": true, "speedup": 0.9907, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 417.8, "calls": 3, "tokens_in": 24788, "tokens_out": 4038, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535730.927632}
{"ep": "h2-00659", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0411, "status": "ok", "correct": true, "speedup": 0.0411, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 215.0, "calls": 2, "tokens_in": 16723, "tokens_out": 6492, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535731.9966047}
{"ep": "h2-00701", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3346, "status": "ok", "correct": true, "speedup": 1.3346, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 76.9, "calls": 1, "tokens_in": 5998, "tokens_out": 761, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791535733.1578074}
{"ep": "h2-00670", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1432, "status": "ok", "correct": true, "speedup": 1.1432, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 166.8, "calls": 2, "tokens_in": 13986, "tokens_out": 11915, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535734.1151493}
{"ep": "h2-00692", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0053, "status": "ok", "correct": true, "speedup": 1.0053, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 102.1, "calls": 2, "tokens_in": 14943, "tokens_out": 5210, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791535736.5570495}
{"ep": "h2-00695", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.5573, "status": "ok", "correct": true, "speedup": 3.5573, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 96.8, "calls": 2, "tokens_in": 5562, "tokens_out": 6191, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535743.6842256}
{"ep": "h2-00660", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.2326, "status": "ok", "correct": true, "speedup": 4.2326, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 222.4, "calls": 3, "tokens_in": 12304, "tokens_out": 8512, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535744.9994268}
{"ep": "h2-00600", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.003, "status": "ok", "correct": true, "speedup": 1.003, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 410.1, "calls": 2, "tokens_in": 4174, "tokens_out": 2134, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535746.5459678}
{"ep": "h2-00567", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.0568, "status": "ok", "correct": true, "speedup": 3.0568, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 497.7, "calls": 3, "tokens_in": 15533, "tokens_out": 11855, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535747.8674073}
{"ep": "h2-00681", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.059, "status": "ok", "correct": true, "speedup": 1.059, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 147.5, "calls": 4, "tokens_in": 18863, "tokens_out": 4118, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535748.155144}
{"ep": "h2-00719", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0074, "status": "ok", "correct": true, "speedup": 1.0074, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 47.4, "calls": 1, "tokens_in": 6367, "tokens_out": 540, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791535749.6588688}
{"ep": "h2-00614", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7892, "status": "ok", "correct": true, "speedup": 0.7892, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 378.1, "calls": 4, "tokens_in": 26416, "tokens_out": 1970, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535750.8677442}
{"ep": "h2-00622", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3305, "status": "ok", "correct": true, "speedup": 1.3305, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 363.7, "calls": 1, "tokens_in": 5998, "tokens_out": 704, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791535750.9928946}
{"ep": "h2-00619", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8025, "status": "ok", "correct": true, "speedup": 0.8025, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 369.1, "calls": 3, "tokens_in": 19059, "tokens_out": 1768, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535751.6108224}
{"ep": "h2-00697", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0239, "status": "ok", "correct": true, "speedup": 1.0239, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 104.1, "calls": 2, "tokens_in": 4851, "tokens_out": 3697, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535756.6472566}
{"ep": "h2-00636", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 8.3972, "status": "ok", "correct": true, "speedup": 8.3972, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 328.6, "calls": 3, "tokens_in": 15889, "tokens_out": 23561, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535776.4342391}
{"ep": "h2-00724", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7883, "status": "ok", "correct": true, "speedup": 0.7883, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 66.1, "calls": 2, "tokens_in": 13821, "tokens_out": 862, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535780.582702}
{"ep": "h2-00728", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0082, "status": "ok", "correct": true, "speedup": 1.0082, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 54.1, "calls": 3, "tokens_in": 19801, "tokens_out": 2117, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535782.1632528}
{"ep": "h2-00698", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9494, "status": "ok", "correct": true, "speedup": 0.9494, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 129.7, "calls": 2, "tokens_in": 13877, "tokens_out": 6980, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535782.4750519}
{"ep": "h2-00721", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.841, "status": "ok", "correct": true, "speedup": 0.841, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 72.9, "calls": 1, "tokens_in": 10632, "tokens_out": 7195, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535783.9955597}
{"ep": "h2-00714", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1166, "status": "ok", "correct": true, "speedup": 1.1166, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 98.2, "calls": 2, "tokens_in": 19228, "tokens_out": 7408, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535785.5139387}
{"ep": "h2-00707", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7323, "status": "ok", "correct": true, "speedup": 0.7323, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 117.9, "calls": 2, "tokens_in": 14223, "tokens_out": 1893, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535787.5051413}
{"ep": "h2-00717", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0142, "status": "ok", "correct": true, "speedup": 1.0142, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 97.8, "calls": 1, "tokens_in": 1750, "tokens_out": 2652, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535789.7681372}
{"ep": "h2-00678", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7589, "status": "ok", "correct": true, "speedup": 0.7589, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 207.2, "calls": 2, "tokens_in": 14129, "tokens_out": 1521, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791535795.4231112}
{"ep": "h2-00686", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 36.7163, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 180.3, "calls": 2, "tokens_in": 6825, "tokens_out": 7142, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535796.8279521}
{"ep": "h2-00735", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'fused_gemm_act_gn': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_gemm_act_gn -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/i", "wall_s": 64.3, "calls": 1, "tokens_in": 1764, "tokens_out": 2000, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535800.9012468}
{"ep": "h2-00726", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6198, "status": "ok", "correct": true, "speedup": 0.6198, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 81.8, "calls": 3, "tokens_in": 18737, "tokens_out": 1545, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535804.3994527}
{"ep": "h2-00729", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0611, "status": "ok", "correct": true, "speedup": 1.0611, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 78.7, "calls": 2, "tokens_in": 13860, "tokens_out": 3351, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535806.9113648}
{"ep": "h2-00624", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9938, "status": "ok", "correct": true, "speedup": 0.9938, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 408.9, "calls": 3, "tokens_in": 22550, "tokens_out": 3024, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791535807.465932}
{"ep": "h2-00691", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0082, "status": "ok", "correct": true, "speedup": 1.0082, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 176.3, "calls": 2, "tokens_in": 16760, "tokens_out": 4388, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535809.2461956}
{"ep": "h2-00616", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0614, "status": "ok", "correct": true, "speedup": 1.0614, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 438.5, "calls": 3, "tokens_in": 22860, "tokens_out": 2471, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791535813.8564584}
{"ep": "h2-00608", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3388, "status": "ok", "correct": true, "speedup": 1.3388, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 456.7, "calls": 2, "tokens_in": 16662, "tokens_out": 7040, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535818.9113245}
{"ep": "h2-00641", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.8013, "status": "ok", "correct": true, "speedup": 1.8013, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 346.9, "calls": 3, "tokens_in": 16305, "tokens_out": 12855, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535820.336627}
{"ep": "h2-00751", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8464, "status": "ok", "correct": true, "speedup": 0.8464, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 34.8, "calls": 1, "tokens_in": 7030, "tokens_out": 1221, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535820.349994}
{"ep": "h2-00743", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0053, "status": "ok", "correct": true, "speedup": 1.0053, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 74.2, "calls": 3, "tokens_in": 19765, "tokens_out": 2054, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535825.1430755}
{"ep": "h2-00683", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0592, "status": "ok", "correct": true, "speedup": 1.0592, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 228.6, "calls": 4, "tokens_in": 18754, "tokens_out": 4113, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535835.4251428}
{"ep": "h2-00710", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0295, "status": "ok", "correct": true, "speedup": 1.0295, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 156.7, "calls": 2, "tokens_in": 4442, "tokens_out": 2191, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535839.3110712}
{"ep": "h2-00722", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5577, "status": "ok", "correct": true, "speedup": 0.5577, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 129.2, "calls": 2, "tokens_in": 12730, "tokens_out": 3183, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535840.563195}
{"ep": "h2-00742", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0507, "status": "ok", "correct": true, "speedup": 1.0507, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 91.2, "calls": 1, "tokens_in": 4862, "tokens_out": 1887, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535842.093834}
{"ep": "h2-00680", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0107, "status": "ok", "correct": true, "speedup": 0.0107, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 249.4, "calls": 2, "tokens_in": 16559, "tokens_out": 6094, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535843.3130202}
{"ep": "h2-00706", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5925, "status": "ok", "correct": true, "speedup": 0.5925, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 184.6, "calls": 2, "tokens_in": 15357, "tokens_out": 11809, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535849.4427214}
{"ep": "h2-00718", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0643, "status": "ok", "correct": true, "speedup": 1.0643, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 161.1, "calls": 3, "tokens_in": 25394, "tokens_out": 4457, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535853.2763414}
{"ep": "h2-00704", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.056, "status": "ok", "correct": true, "speedup": 1.056, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 197.3, "calls": 2, "tokens_in": 6051, "tokens_out": 6040, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535856.5115628}
{"ep": "h2-00687", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4939, "status": "ok", "correct": true, "speedup": 1.4939, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 238.5, "calls": 2, "tokens_in": 9595, "tokens_out": 18197, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535857.608932}
{"ep": "h2-00744", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0161, "status": "ok", "correct": true, "speedup": 1.0161, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 109.1, "calls": 2, "tokens_in": 10577, "tokens_out": 3566, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791535860.683137}
{"ep": "h2-00741", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0036, "status": "ok", "correct": true, "speedup": 1.0036, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 112.1, "calls": 1, "tokens_in": 6477, "tokens_out": 540, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791535861.7976873}
{"ep": "h2-00661", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5713, "status": "ok", "correct": true, "speedup": 1.5713, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 339.8, "calls": 3, "tokens_in": 16255, "tokens_out": 12361, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535863.8689356}
{"ep": "h2-00752", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0004, "status": "ok", "correct": true, "speedup": 1.0004, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 77.8, "calls": 3, "tokens_in": 19907, "tokens_out": 2169, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535865.2905388}
{"ep": "h2-00739", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0058, "status": "ok", "correct": true, "speedup": 1.0058, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 120.9, "calls": 3, "tokens_in": 20139, "tokens_out": 2747, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791535868.7335174}
{"ep": "h2-00736", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9898, "status": "ok", "correct": true, "speedup": 0.9898, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 130.7, "calls": 3, "tokens_in": 19785, "tokens_out": 2600, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791535874.3617084}
{"ep": "h2-00727", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0125, "status": "ok", "correct": true, "speedup": 1.0125, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 154.7, "calls": 3, "tokens_in": 24743, "tokens_out": 2241, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791535878.612882}
{"ep": "h2-00679", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7768, "status": "ok", "correct": true, "speedup": 0.7768, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 293.4, "calls": 5, "tokens_in": 58786, "tokens_out": 13124, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535886.6936944}
{"ep": "h2-00715", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0062, "status": "ok", "correct": true, "speedup": 1.0062, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 199.4, "calls": 3, "tokens_in": 19930, "tokens_out": 2188, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791535886.7303932}
{"ep": "h2-00732", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9789, "status": "ok", "correct": true, "speedup": 0.9789, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 159.7, "calls": 3, "tokens_in": 24111, "tokens_out": 2286, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791535891.7264795}
{"ep": "h2-00677", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0579, "status": "ok", "correct": true, "speedup": 1.0579, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 308.8, "calls": 3, "tokens_in": 22948, "tokens_out": 2478, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791535894.0355906}
{"ep": "h2-00734", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8429, "status": "ok", "correct": true, "speedup": 0.8429, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 161.6, "calls": 2, "tokens_in": 15697, "tokens_out": 2985, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791535895.7385776}
{"ep": "h2-00709", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3566, "status": "ok", "correct": true, "speedup": 2.3566, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 218.8, "calls": 3, "tokens_in": 23611, "tokens_out": 5267, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535897.2083187}
{"ep": "h2-00764", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0037, "status": "ok", "correct": true, "speedup": 1.0037, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 77.3, "calls": 2, "tokens_in": 11409, "tokens_out": 1107, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791535897.6405172}
{"ep": "h2-00693", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4724, "status": "ok", "correct": true, "speedup": 1.4724, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 261.0, "calls": 2, "tokens_in": 11230, "tokens_out": 4876, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535898.3777857}
{"ep": "h2-00759", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0143, "status": "ok", "correct": true, "speedup": 1.0143, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 94.6, "calls": 2, "tokens_in": 16644, "tokens_out": 4349, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791535902.032302}
{"ep": "h2-00712", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9959, "status": "ok", "correct": true, "speedup": 0.9959, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 218.5, "calls": 3, "tokens_in": 22618, "tokens_out": 3088, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791535902.451035}
{"ep": "h2-00569", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.0045, "status": "ok", "correct": true, "speedup": 2.0045, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 654.5, "calls": 2, "tokens_in": 30691, "tokens_out": 22528, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535906.553085}
{"ep": "h2-00754", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0436, "status": "ok", "correct": true, "speedup": 1.0436, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 114.0, "calls": 2, "tokens_in": 5113, "tokens_out": 4249, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535909.451536}
{"ep": "h2-00673", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.4506, "status": "ok", "correct": true, "speedup": 2.4506, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 334.4, "calls": 2, "tokens_in": 12147, "tokens_out": 20410, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535909.7663481}
{"ep": "h2-00694", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.6024, "status": "ok", "correct": true, "speedup": 7.6024, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 270.2, "calls": 3, "tokens_in": 16696, "tokens_out": 17448, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535911.0952544}
{"ep": "h2-00699", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0647, "status": "ok", "correct": true, "speedup": 1.0647, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 257.6, "calls": 2, "tokens_in": 10501, "tokens_out": 2302, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535912.3695428}
{"ep": "h2-00749", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.551, "status": "ok", "correct": true, "speedup": 0.551, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 130.5, "calls": 3, "tokens_in": 20641, "tokens_out": 3455, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535912.9594216}
{"ep": "h2-00773", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'bias_relu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=bias_relu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/t", "wall_s": 57.0, "calls": 1, "tokens_in": 1622, "tokens_out": 878, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535913.5050404}
{"ep": "h2-00746", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1345, "status": "ok", "correct": true, "speedup": 1.1345, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 137.7, "calls": 2, "tokens_in": 4814, "tokens_out": 4111, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535914.1473594}
{"ep": "h2-00740", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 36.5348, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 166.1, "calls": 2, "tokens_in": 7254, "tokens_out": 7596, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535914.304282}
{"ep": "h2-00593", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.573, "status": "ok", "correct": true, "speedup": 1.573, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 594.3, "calls": 3, "tokens_in": 16144, "tokens_out": 15177, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535919.4930227}
{"ep": "h2-00748", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7167, "status": "ok", "correct": true, "speedup": 0.7167, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 137.4, "calls": 2, "tokens_in": 16356, "tokens_out": 3811, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535919.5781841}
{"ep": "h2-00763", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0044, "status": "ok", "correct": true, "speedup": 1.0044, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 101.3, "calls": 3, "tokens_in": 23842, "tokens_out": 2572, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791535921.660719}
{"ep": "h2-00755", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0007, "status": "ok", "correct": true, "speedup": 1.0007, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 125.4, "calls": 2, "tokens_in": 16252, "tokens_out": 2599, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791535922.2102692}
{"ep": "h2-00758", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9837, "status": "ok", "correct": true, "speedup": 0.9837, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 118.6, "calls": 2, "tokens_in": 11793, "tokens_out": 1494, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791535925.5023324}
{"ep": "h2-00730", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0095, "status": "ok", "correct": true, "speedup": 1.0095, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 204.5, "calls": 2, "tokens_in": 15075, "tokens_out": 5277, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791535933.4999893}
{"ep": "h2-00731", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9783, "status": "ok", "correct": true, "speedup": 0.9783, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 204.0, "calls": 2, "tokens_in": 14828, "tokens_out": 9127, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535934.975741}
{"ep": "h2-00700", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.2483, "status": "ok", "correct": true, "speedup": 2.2483, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 280.2, "calls": 3, "tokens_in": 16659, "tokens_out": 13247, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535935.508596}
{"ep": "h2-00713", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 37.1256, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 252.2, "calls": 2, "tokens_in": 6938, "tokens_out": 6862, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535936.5500157}
{"ep": "h2-00716", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6384, "status": "ok", "correct": true, "speedup": 0.6384, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 245.6, "calls": 2, "tokens_in": 15438, "tokens_out": 14228, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535936.9802504}
{"ep": "h2-00723", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5541, "status": "ok", "correct": true, "speedup": 1.5541, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 224.5, "calls": 2, "tokens_in": 6577, "tokens_out": 6812, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535937.2978582}
{"ep": "h2-00737", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2934, "status": "ok", "correct": true, "speedup": 1.2934, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 194.4, "calls": 2, "tokens_in": 14194, "tokens_out": 6766, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535939.4194615}
{"ep": "h2-00772", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0637, "status": "ok", "correct": true, "speedup": 1.0637, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 87.3, "calls": 2, "tokens_in": 13788, "tokens_out": 3120, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535940.6218405}
{"ep": "h2-00766", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7831, "status": "ok", "correct": true, "speedup": 2.7831, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 106.4, "calls": 1, "tokens_in": 1818, "tokens_out": 6268, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535941.8113754}
{"ep": "h2-00702", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.7235, "status": "ok", "correct": true, "speedup": 6.7235, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 285.3, "calls": 3, "tokens_in": 30499, "tokens_out": 26825, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535941.990279}
{"ep": "h2-00767", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5495, "status": "ok", "correct": true, "speedup": 0.5495, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 106.1, "calls": 2, "tokens_in": 5046, "tokens_out": 4591, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535945.4372556}
{"ep": "h2-00778", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0094, "status": "ok", "correct": true, "speedup": 1.0094, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.3, "calls": 2, "tokens_in": 4137, "tokens_out": 2025, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535946.613557}
{"ep": "h2-00769", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0278, "status": "ok", "correct": true, "speedup": 1.0278, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 109.4, "calls": 1, "tokens_in": 5832, "tokens_out": 539, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791535951.463079}
{"ep": "h2-00703", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 16.9719, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 295.5, "calls": 2, "tokens_in": 7675, "tokens_out": 24351, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535953.9488976}
{"ep": "h2-00761", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3333, "status": "ok", "correct": true, "speedup": 2.3333, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 141.7, "calls": 2, "tokens_in": 14555, "tokens_out": 5222, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535955.592386}
{"ep": "h2-00708", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.5937, "status": "ok", "correct": true, "speedup": 3.5937, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 285.1, "calls": 3, "tokens_in": 19683, "tokens_out": 19679, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535955.7728043}
{"ep": "h2-00796", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8037, "status": "ok", "correct": true, "speedup": 0.8037, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 45.0, "calls": 3, "tokens_in": 18765, "tokens_out": 1539, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791535957.4184136}
{"ep": "h2-00782", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0103, "status": "ok", "correct": true, "speedup": 1.0103, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 72.4, "calls": 3, "tokens_in": 24006, "tokens_out": 3667, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791535959.0572038}
{"ep": "h2-00787", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.007, "status": "ok", "correct": true, "speedup": 1.007, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 62.7, "calls": 2, "tokens_in": 16347, "tokens_out": 3573, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791535959.9102201}
{"ep": "h2-00756", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0115, "status": "ok", "correct": true, "speedup": 1.0115, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 159.8, "calls": 3, "tokens_in": 24816, "tokens_out": 2268, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535960.7219334}
{"ep": "h2-00771", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0058, "status": "ok", "correct": true, "speedup": 1.0058, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 112.2, "calls": 2, "tokens_in": 4192, "tokens_out": 2110, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535961.6715584}
{"ep": "h2-00768", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.019, "status": "ok", "correct": true, "speedup": 1.019, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 122.4, "calls": 2, "tokens_in": 5429, "tokens_out": 4434, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535962.9783046}
{"ep": "h2-00725", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.9152, "status": "ok", "correct": true, "speedup": 2.9152, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 241.7, "calls": 2, "tokens_in": 14009, "tokens_out": 4865, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791535963.4694269}
{"ep": "h2-00753", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5637, "status": "ok", "correct": true, "speedup": 0.5637, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 182.2, "calls": 2, "tokens_in": 15766, "tokens_out": 11279, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535972.0002375}
{"ep": "h2-00779", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0173, "status": "ok", "correct": true, "speedup": 1.0173, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 106.4, "calls": 3, "tokens_in": 24912, "tokens_out": 2291, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535975.1233847}
{"ep": "h2-00765", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0128, "status": "ok", "correct": true, "speedup": 1.0128, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 153.8, "calls": 2, "tokens_in": 16440, "tokens_out": 2706, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791535978.896565}
{"ep": "h2-00760", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0211, "status": "ok", "correct": true, "speedup": 1.0211, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 173.3, "calls": 2, "tokens_in": 13424, "tokens_out": 4670, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791535982.5524223}
{"ep": "h2-00747", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.7002, "status": "ok", "correct": true, "speedup": 1.7002, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 210.0, "calls": 2, "tokens_in": 9095, "tokens_out": 8918, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535990.5526943}
{"ep": "h2-00824", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0042, "status": "ok", "correct": true, "speedup": 1.0042, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 31.0, "calls": 1, "tokens_in": 6367, "tokens_out": 539, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791535990.959695}
{"ep": "h2-00792", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3275, "status": "ok", "correct": true, "speedup": 2.3275, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 90.2, "calls": 2, "tokens_in": 13176, "tokens_out": 3922, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791535996.7567832}
{"ep": "h2-00738", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.0582, "status": "ok", "correct": true, "speedup": 4.0582, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 252.2, "calls": 3, "tokens_in": 15889, "tokens_out": 13990, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791535998.708745}
{"ep": "h2-00797", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3213, "status": "ok", "correct": true, "speedup": 0.3213, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 86.7, "calls": 3, "tokens_in": 21758, "tokens_out": 5116, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791535999.6112351}
{"ep": "h2-00770", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0066, "status": "ok", "correct": true, "speedup": 1.0066, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 160.2, "calls": 3, "tokens_in": 19895, "tokens_out": 2128, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791536003.5414693}
{"ep": "h2-00711", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0191, "status": "ok", "correct": true, "speedup": 1.0191, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 320.3, "calls": 4, "tokens_in": 35102, "tokens_out": 3731, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536004.0100913}
{"ep": "h2-00774", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 37.3773, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 147.3, "calls": 2, "tokens_in": 7321, "tokens_out": 7914, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536004.9459517}
{"ep": "h2-00775", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8512, "status": "ok", "correct": true, "speedup": 0.8512, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 146.7, "calls": 3, "tokens_in": 19625, "tokens_out": 2785, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791536007.3758814}
{"ep": "h2-00806", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3313, "status": "ok", "correct": true, "speedup": 1.3313, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 76.5, "calls": 1, "tokens_in": 5998, "tokens_out": 743, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536009.959371}
{"ep": "h2-00776", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0199, "status": "ok", "correct": true, "speedup": 1.0199, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 151.5, "calls": 2, "tokens_in": 5831, "tokens_out": 5380, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536013.274533}
{"ep": "h2-00745", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8714, "status": "ok", "correct": true, "speedup": 0.8714, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 259.7, "calls": 3, "tokens_in": 8282, "tokens_out": 2606, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536016.3952384}
{"ep": "h2-00793", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0248, "status": "ok", "correct": true, "speedup": 1.0248, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 109.1, "calls": 2, "tokens_in": 13344, "tokens_out": 4368, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791536018.5172489}
{"ep": "h2-00818", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'ct3d_copy': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=ct3d_copy -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csr", "wall_s": 68.1, "calls": 1, "tokens_in": 2181, "tokens_out": 1046, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536019.536599}
{"ep": "h2-00813", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0269, "status": "ok", "correct": true, "speedup": 1.0269, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.9, "calls": 1, "tokens_in": 1668, "tokens_out": 1637, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536022.567274}
{"ep": "h2-00791", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0166, "status": "ok", "correct": true, "speedup": 1.0166, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 122.7, "calls": 3, "tokens_in": 25234, "tokens_out": 2533, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791536025.1719265}
{"ep": "h2-00809", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8462, "status": "ok", "correct": true, "speedup": 0.8462, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 88.7, "calls": 2, "tokens_in": 15676, "tokens_out": 2885, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791536025.230001}
{"ep": "h2-00808", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0016, "status": "ok", "correct": true, "speedup": 1.0016, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 100.9, "calls": 1, "tokens_in": 1596, "tokens_out": 2426, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536036.4179344}
{"ep": "h2-00822", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0596, "status": "ok", "correct": true, "speedup": 1.0596, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 82.4, "calls": 2, "tokens_in": 13786, "tokens_out": 3034, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791536039.8523867}
{"ep": "h2-00803", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0179, "status": "ok", "correct": true, "speedup": 1.0179, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 125.3, "calls": 2, "tokens_in": 16602, "tokens_out": 3766, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536046.970852}
{"ep": "h2-00827", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0061, "status": "ok", "correct": true, "speedup": 1.0061, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 89.7, "calls": 2, "tokens_in": 13692, "tokens_out": 1128, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536052.680706}
{"ep": "h2-00780", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.027, "status": "ok", "correct": true, "speedup": 1.027, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 180.4, "calls": 2, "tokens_in": 13526, "tokens_out": 4833, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791536054.7525256}
{"ep": "h2-00777", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7813, "status": "ok", "correct": true, "speedup": 0.7813, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 191.0, "calls": 2, "tokens_in": 8440, "tokens_out": 13423, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536054.846621}
{"ep": "h2-00733", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.4513, "status": "ok", "correct": true, "speedup": 3.4513, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 324.7, "calls": 3, "tokens_in": 26920, "tokens_out": 17686, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536057.8628178}
{"ep": "h2-00810", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0296, "status": "ok", "correct": true, "speedup": 1.0296, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 124.6, "calls": 2, "tokens_in": 9293, "tokens_out": 2835, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536061.5653884}
{"ep": "h2-00832", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'mbconv_ops': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=mbconv_ops -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/c", "wall_s": 80.7, "calls": 1, "tokens_in": 2159, "tokens_out": 1961, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536063.2519054}
{"ep": "h2-00795", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.782, "status": "ok", "correct": true, "speedup": 0.782, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 153.8, "calls": 3, "tokens_in": 47130, "tokens_out": 14718, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536064.9194539}
{"ep": "h2-00840", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0186, "status": "ok", "correct": true, "speedup": 1.0186, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 65.5, "calls": 2, "tokens_in": 10564, "tokens_out": 3521, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536070.4575121}
{"ep": "h2-00802", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4375, "status": "ok", "correct": true, "speedup": 1.4375, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 154.9, "calls": 2, "tokens_in": 5042, "tokens_out": 4518, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536074.4572241}
{"ep": "h2-00762", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3799, "status": "ok", "correct": true, "speedup": 1.3799, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 257.3, "calls": 2, "tokens_in": 16853, "tokens_out": 8018, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536076.2448542}
{"ep": "h2-00834", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0053, "status": "ok", "correct": true, "speedup": 1.0053, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 87.4, "calls": 2, "tokens_in": 11765, "tokens_out": 1497, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536078.3350036}
{"ep": "h2-00757", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9994, "status": "ok", "correct": true, "speedup": 0.9994, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 274.4, "calls": 4, "tokens_in": 23377, "tokens_out": 6476, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536078.7823627}
{"ep": "h2-00849", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0071, "status": "ok", "correct": true, "speedup": 1.0071, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 58.5, "calls": 1, "tokens_in": 6367, "tokens_out": 538, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791536083.7526143}
{"ep": "h2-00836", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6706, "status": "ok", "correct": true, "speedup": 2.6706, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 92.0, "calls": 2, "tokens_in": 14488, "tokens_out": 5028, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791536090.7162595}
{"ep": "h2-00781", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0058, "status": "ok", "correct": true, "speedup": 1.0058, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 212.6, "calls": 2, "tokens_in": 11680, "tokens_out": 1363, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536091.234955}
{"ep": "h2-00799", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7911, "status": "ok", "correct": true, "speedup": 0.7911, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 178.0, "calls": 3, "tokens_in": 50114, "tokens_out": 15034, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791536092.1507127}
{"ep": "h2-00847", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0063, "status": "ok", "correct": true, "speedup": 1.0063, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 70.6, "calls": 1, "tokens_in": 6477, "tokens_out": 517, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536093.1481848}
{"ep": "h2-00839", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.4348, "status": "ok", "correct": true, "speedup": 2.4348, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 90.1, "calls": 2, "tokens_in": 13087, "tokens_out": 4277, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791536094.0660734}
{"ep": "h2-00783", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3114, "status": "ok", "correct": true, "speedup": 1.3114, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 208.1, "calls": 2, "tokens_in": 30597, "tokens_out": 15794, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791536094.7921157}
{"ep": "h2-00852", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0012, "status": "ok", "correct": true, "speedup": 1.0012, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 51.0, "calls": 2, "tokens_in": 11415, "tokens_out": 1119, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536097.978221}
{"ep": "h2-00817", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0073, "status": "ok", "correct": true, "speedup": 1.0073, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 153.5, "calls": 2, "tokens_in": 15137, "tokens_out": 5604, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536100.076615}
{"ep": "h2-00820", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0024, "status": "ok", "correct": true, "speedup": 1.0024, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 151.4, "calls": 2, "tokens_in": 11396, "tokens_out": 1094, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536106.9675782}
{"ep": "h2-00804", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.399, "status": "ok", "correct": true, "speedup": 1.399, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 185.0, "calls": 2, "tokens_in": 6632, "tokens_out": 6816, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536107.1912353}
{"ep": "h2-00811", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0205, "status": "ok", "correct": true, "speedup": 1.0205, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 171.2, "calls": 4, "tokens_in": 34968, "tokens_out": 3687, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536108.5117986}
{"ep": "h2-00845", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0106, "status": "ok", "correct": true, "speedup": 1.0106, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 92.2, "calls": 1, "tokens_in": 1599, "tokens_out": 628, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536110.706602}
{"ep": "h2-00823", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0109, "status": "ok", "correct": true, "speedup": 1.0109, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 154.1, "calls": 2, "tokens_in": 13647, "tokens_out": 1115, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536113.1926591}
{"ep": "h2-00750", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.688, "status": "ok", "correct": true, "speedup": 7.688, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 334.6, "calls": 3, "tokens_in": 29570, "tokens_out": 21965, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536118.5483227}
{"ep": "h2-00805", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0292, "status": "ok", "correct": true, "speedup": 1.0292, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 199.4, "calls": 2, "tokens_in": 16123, "tokens_out": 13483, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536124.890582}
{"ep": "h2-00851", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0334, "status": "ok", "correct": true, "speedup": 1.0334, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 87.1, "calls": 2, "tokens_in": 4968, "tokens_out": 2857, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536126.9650755}
{"ep": "h2-00838", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8441, "status": "ok", "correct": true, "speedup": 0.8441, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 123.7, "calls": 2, "tokens_in": 15651, "tokens_out": 2905, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791536127.218215}
{"ep": "h2-00784", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.4489, "status": "ok", "correct": true, "speedup": 2.4489, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 236.1, "calls": 2, "tokens_in": 29248, "tokens_out": 18802, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536127.7778938}
{"ep": "h2-00854", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9954, "status": "ok", "correct": true, "speedup": 0.9954, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 76.4, "calls": 2, "tokens_in": 14436, "tokens_out": 3021, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536131.1143737}
{"ep": "h2-00814", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6288, "status": "ok", "correct": true, "speedup": 0.6288, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 196.4, "calls": 2, "tokens_in": 15286, "tokens_out": 12531, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536138.2503088}
{"ep": "h2-00864", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0026, "status": "ok", "correct": true, "speedup": 1.0026, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 62.7, "calls": 1, "tokens_in": 6367, "tokens_out": 546, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791536141.501417}
{"ep": "h2-00786", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7003, "status": "ok", "correct": true, "speedup": 0.7003, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 250.3, "calls": 2, "tokens_in": 13774, "tokens_out": 13841, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536146.0544655}
{"ep": "h2-00788", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3179, "status": "ok", "correct": true, "speedup": 0.3179, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 248.4, "calls": 5, "tokens_in": 56572, "tokens_out": 11744, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536146.0579655}
{"ep": "h2-00869", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0011, "status": "ok", "correct": true, "speedup": 1.0011, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 53.6, "calls": 3, "tokens_in": 17512, "tokens_out": 1124, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536146.7787971}
{"ep": "h2-00790", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5373, "status": "ok", "correct": true, "speedup": 1.5373, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 244.8, "calls": 3, "tokens_in": 15931, "tokens_out": 12766, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536146.8780797}
{"ep": "h2-00848", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0134, "status": "ok", "correct": true, "speedup": 1.0134, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 123.9, "calls": 3, "tokens_in": 9157, "tokens_out": 3010, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536149.0950367}
{"ep": "h2-00826", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5464, "status": "ok", "correct": true, "speedup": 1.5464, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 188.6, "calls": 2, "tokens_in": 5192, "tokens_out": 4217, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536150.2544696}
{"ep": "h2-00720", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2575, "status": "ok", "correct": true, "speedup": 0.2575, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 444.5, "calls": 3, "tokens_in": 16284, "tokens_out": 14756, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536150.553573}
{"ep": "h2-00819", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0045, "status": "ok", "correct": true, "speedup": 1.0045, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 199.7, "calls": 3, "tokens_in": 24058, "tokens_out": 2760, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536153.6768746}
{"ep": "h2-00785", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5181, "status": "ok", "correct": true, "speedup": 0.5181, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 260.7, "calls": 3, "tokens_in": 13248, "tokens_out": 6405, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536154.7676828}
{"ep": "h2-00856", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0563, "status": "ok", "correct": true, "speedup": 1.0563, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 101.6, "calls": 2, "tokens_in": 12974, "tokens_out": 2280, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791536159.5095217}
{"ep": "h2-00862", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8483, "status": "ok", "correct": true, "speedup": 0.8483, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 84.8, "calls": 1, "tokens_in": 7030, "tokens_out": 1207, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791536161.01058}
{"ep": "h2-00867", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0278, "status": "ok", "correct": true, "speedup": 1.0278, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 77.9, "calls": 1, "tokens_in": 5832, "tokens_out": 526, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536169.1410143}
{"ep": "h2-00858", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0667, "status": "ok", "correct": true, "speedup": 1.0667, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 106.1, "calls": 2, "tokens_in": 10493, "tokens_out": 2282, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536169.3790946}
{"ep": "h2-00855", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0152, "status": "ok", "correct": true, "speedup": 1.0152, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 126.5, "calls": 2, "tokens_in": 16181, "tokens_out": 2585, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536181.338926}
{"ep": "h2-00830", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9898, "status": "ok", "correct": true, "speedup": 0.9898, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 212.3, "calls": 3, "tokens_in": 11764, "tokens_out": 3019, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536187.3830721}
{"ep": "h2-00875", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8201, "status": "ok", "correct": true, "speedup": 0.8201, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 81.1, "calls": 2, "tokens_in": 12029, "tokens_out": 1448, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536188.2691314}
{"ep": "h2-00843", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9776, "status": "ok", "correct": true, "speedup": 0.9776, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 175.5, "calls": 2, "tokens_in": 15210, "tokens_out": 1836, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536188.756122}
{"ep": "h2-00846", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.03, "status": "ok", "correct": true, "speedup": 1.03, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 170.3, "calls": 2, "tokens_in": 8884, "tokens_out": 7891, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536189.8129241}
{"ep": "h2-00844", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0239, "status": "ok", "correct": true, "speedup": 1.0239, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 180.7, "calls": 4, "tokens_in": 19353, "tokens_out": 4784, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536197.131787}
{"ep": "h2-00833", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0062, "status": "ok", "correct": true, "speedup": 1.0062, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 209.2, "calls": 2, "tokens_in": 5860, "tokens_out": 5947, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536199.7063959}
{"ep": "h2-00860", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8495, "status": "ok", "correct": true, "speedup": 0.8495, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 130.1, "calls": 2, "tokens_in": 15732, "tokens_out": 3041, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791536200.5249517}
{"ep": "h2-00831", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6182, "status": "ok", "correct": true, "speedup": 2.6182, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 222.5, "calls": 3, "tokens_in": 15148, "tokens_out": 12275, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536201.4452565}
{"ep": "h2-00800", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1705, "status": "ok", "correct": true, "speedup": 1.1705, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 289.7, "calls": 2, "tokens_in": 7205, "tokens_out": 8534, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536204.0229182}
{"ep": "h2-00837", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8702, "status": "ok", "correct": true, "speedup": 0.8702, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 212.0, "calls": 2, "tokens_in": 4765, "tokens_out": 2177, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536211.581051}
{"ep": "h2-00807", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0033, "status": "ok", "correct": true, "speedup": 1.0033, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 280.8, "calls": 3, "tokens_in": 24687, "tokens_out": 2154, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536215.824195}
{"ep": "h2-00789", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0208, "status": "ok", "correct": true, "speedup": 1.0208, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 320.7, "calls": 3, "tokens_in": 16344, "tokens_out": 2826, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536219.1142695}
{"ep": "h2-00801", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0214, "status": "ok", "correct": true, "speedup": 1.0214, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 300.6, "calls": 3, "tokens_in": 12338, "tokens_out": 8435, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536220.082642}
{"ep": "h2-00821", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.028, "status": "ok", "correct": true, "speedup": 1.028, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 269.5, "calls": 2, "tokens_in": 12722, "tokens_out": 1977, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536225.2844958}
{"ep": "h2-00897", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0051, "status": "ok", "correct": true, "speedup": 1.0051, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 75.6, "calls": 2, "tokens_in": 14091, "tokens_out": 1481, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536236.6504548}
{"ep": "h2-00868", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0651, "status": "ok", "correct": true, "speedup": 1.0651, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 155.9, "calls": 2, "tokens_in": 10519, "tokens_out": 2332, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536248.0692613}
{"ep": "h2-00895", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.712, "status": "ok", "correct": true, "speedup": 0.712, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 93.4, "calls": 2, "tokens_in": 14872, "tokens_out": 9052, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536248.1451926}
{"ep": "h2-00815", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5011, "status": "ok", "correct": true, "speedup": 0.5011, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 308.7, "calls": 4, "tokens_in": 19995, "tokens_out": 6363, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536250.686511}
{"ep": "h2-00886", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3289, "status": "ok", "correct": true, "speedup": 0.3289, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 116.2, "calls": 3, "tokens_in": 22629, "tokens_out": 5955, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536257.6515367}
{"ep": "h2-00859", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.323, "status": "ok", "correct": true, "speedup": 0.323, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 193.4, "calls": 4, "tokens_in": 35337, "tokens_out": 7541, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536258.3316047}
{"ep": "h2-00885", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3464, "status": "ok", "correct": true, "speedup": 2.3464, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 123.3, "calls": 3, "tokens_in": 23560, "tokens_out": 5180, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791536261.5347896}
{"ep": "h2-00894", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.316, "status": "ok", "correct": true, "speedup": 0.316, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 111.0, "calls": 3, "tokens_in": 22429, "tokens_out": 5801, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536264.6689131}
{"ep": "h2-00879", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.067, "status": "ok", "correct": true, "speedup": 1.067, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 151.6, "calls": 1, "tokens_in": 4605, "tokens_out": 1150, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536270.142812}
{"ep": "h2-00907", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0198, "status": "ok", "correct": true, "speedup": 1.0198, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 77.5, "calls": 2, "tokens_in": 15640, "tokens_out": 3640, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536278.0028481}
{"ep": "h2-00825", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4324, "status": "ok", "correct": true, "speedup": 1.4324, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 323.1, "calls": 2, "tokens_in": 16620, "tokens_out": 14176, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536283.864276}
{"ep": "h2-00892", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0302, "status": "ok", "correct": true, "speedup": 1.0302, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 134.0, "calls": 2, "tokens_in": 9235, "tokens_out": 2587, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536284.3006232}
{"ep": "h2-00905", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0272, "status": "ok", "correct": true, "speedup": 1.0272, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 88.3, "calls": 2, "tokens_in": 12339, "tokens_out": 1087, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536285.3931308}
{"ep": "h2-00899", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0544, "status": "ok", "correct": true, "speedup": 1.0544, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 117.1, "calls": 2, "tokens_in": 4618, "tokens_out": 2790, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536286.4961584}
{"ep": "h2-00906", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0264, "status": "ok", "correct": true, "speedup": 1.0264, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 90.3, "calls": 2, "tokens_in": 12320, "tokens_out": 1068, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536289.9987795}
{"ep": "h2-00883", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0107, "status": "ok", "correct": true, "speedup": 1.0107, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 167.9, "calls": 2, "tokens_in": 6805, "tokens_out": 8326, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536295.6722782}
{"ep": "h2-00891", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0115, "status": "ok", "correct": true, "speedup": 1.0115, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 148.1, "calls": 2, "tokens_in": 16066, "tokens_out": 2245, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536297.2031114}
{"ep": "h2-00816", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.9559, "status": "ok", "correct": true, "speedup": 6.9559, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 367.0, "calls": 3, "tokens_in": 20443, "tokens_out": 24451, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536312.4548416}
{"ep": "h2-00908", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9756, "status": "ok", "correct": true, "speedup": 0.9756, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 111.2, "calls": 3, "tokens_in": 23601, "tokens_out": 1970, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536312.6375778}
{"ep": "h2-00835", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2381, "status": "ok", "correct": true, "speedup": 1.2381, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 317.4, "calls": 2, "tokens_in": 12577, "tokens_out": 22296, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536314.1893456}
{"ep": "h2-00925", "task": "L1_012", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7527, "status": "ok", "correct": true, "speedup": 0.7527, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 32.7, "calls": 1, "tokens_in": 6622, "tokens_out": 521, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791536316.5969787}
{"ep": "h2-00890", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.8917, "status": "ok", "correct": true, "speedup": 2.8917, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 171.6, "calls": 3, "tokens_in": 12529, "tokens_out": 7994, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536318.4985116}
{"ep": "h2-00922", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0123, "status": "ok", "correct": true, "speedup": 1.0123, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 54.4, "calls": 2, "tokens_in": 11902, "tokens_out": 1619, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536319.031445}
{"ep": "h2-00884", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.585, "status": "ok", "correct": true, "speedup": 2.585, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 188.7, "calls": 2, "tokens_in": 7769, "tokens_out": 9440, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536319.840083}
{"ep": "h2-00916", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0092, "status": "ok", "correct": true, "speedup": 1.0092, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 72.4, "calls": 1, "tokens_in": 6367, "tokens_out": 536, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791536320.4213102}
{"ep": "h2-00910", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3992, "status": "ok", "correct": true, "speedup": 1.3992, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 111.1, "calls": 2, "tokens_in": 4926, "tokens_out": 4722, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536322.6675773}
{"ep": "h2-00914", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0019, "status": "ok", "correct": true, "speedup": 1.0019, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 98.0, "calls": 2, "tokens_in": 4116, "tokens_out": 1922, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536323.240034}
{"ep": "h2-00930", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "incorrect", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 29.8, "calls": 1, "tokens_in": 1902, "tokens_out": 1110, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536325.4598901}
{"ep": "h2-00828", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.4956, "status": "ok", "correct": true, "speedup": 5.4956, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 364.5, "calls": 2, "tokens_in": 6355, "tokens_out": 8334, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536327.967623}
{"ep": "h2-00912", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7935, "status": "ok", "correct": true, "speedup": 0.7935, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 119.1, "calls": 4, "tokens_in": 26350, "tokens_out": 1961, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536338.1994846}
{"ep": "h2-00911", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.6548, "status": "ok", "correct": true, "speedup": 3.6548, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 126.1, "calls": 2, "tokens_in": 6574, "tokens_out": 6515, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536341.918368}
{"ep": "h2-00928", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0009, "status": "ok", "correct": true, "speedup": 1.0009, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 57.4, "calls": 1, "tokens_in": 6477, "tokens_out": 492, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536343.852973}
{"ep": "h2-00913", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2893, "status": "ok", "correct": true, "speedup": 0.2893, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 124.3, "calls": 4, "tokens_in": 37516, "tokens_out": 8109, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536344.3400855}
{"ep": "h2-00898", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9474, "status": "ok", "correct": true, "speedup": 0.9474, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 176.8, "calls": 2, "tokens_in": 15494, "tokens_out": 11785, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536345.9155505}
{"ep": "h2-00915", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3319, "status": "ok", "correct": true, "speedup": 0.3319, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 110.7, "calls": 3, "tokens_in": 22567, "tokens_out": 5914, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536347.3639157}
{"ep": "h2-00798", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0056, "status": "ok", "correct": true, "speedup": 1.0056, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 438.9, "calls": 4, "tokens_in": 21012, "tokens_out": 6127, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536352.4277256}
{"ep": "h2-00926", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0156, "status": "ok", "correct": true, "speedup": 1.0156, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 72.7, "calls": 2, "tokens_in": 15998, "tokens_out": 3568, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791536357.00084}
{"ep": "h2-00893", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3159, "status": "ok", "correct": true, "speedup": 1.3159, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 206.6, "calls": 2, "tokens_in": 10207, "tokens_out": 16856, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536357.1512072}
{"ep": "h2-00920", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0016, "status": "ok", "correct": true, "speedup": 1.0016, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 99.5, "calls": 2, "tokens_in": 4155, "tokens_out": 1824, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536357.8155758}
{"ep": "h2-00841", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6524, "status": "ok", "correct": true, "speedup": 0.6524, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 351.3, "calls": 2, "tokens_in": 12479, "tokens_out": 20027, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536358.7236955}
{"ep": "h2-00870", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.497, "status": "ok", "correct": true, "speedup": 1.497, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 265.5, "calls": 2, "tokens_in": 5174, "tokens_out": 4287, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536359.6018755}
{"ep": "h2-00829", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.9706, "status": "ok", "correct": true, "speedup": 4.9706, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 392.8, "calls": 3, "tokens_in": 13449, "tokens_out": 9732, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536364.7964063}
{"ep": "h2-00909", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8788, "status": "ok", "correct": true, "speedup": 0.8788, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 163.1, "calls": 2, "tokens_in": 5822, "tokens_out": 5197, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536367.0749385}
{"ep": "h2-00863", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1697, "status": "ok", "correct": true, "speedup": 1.1697, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 294.1, "calls": 1, "tokens_in": 1757, "tokens_out": 3981, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536372.4361997}
{"ep": "h2-00902", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4814, "status": "ok", "correct": true, "speedup": 1.4814, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 184.6, "calls": 2, "tokens_in": 6829, "tokens_out": 7044, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536372.9026377}
{"ep": "h2-00866", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8559, "status": "ok", "correct": true, "speedup": 0.8559, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 286.5, "calls": 3, "tokens_in": 15775, "tokens_out": 13182, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536377.1710742}
{"ep": "h2-00881", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3317, "status": "ok", "correct": true, "speedup": 2.3317, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 251.4, "calls": 3, "tokens_in": 21009, "tokens_out": 3951, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791536378.3481576}
{"ep": "h2-00931", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3338, "status": "ok", "correct": true, "speedup": 1.3338, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 83.7, "calls": 1, "tokens_in": 5998, "tokens_out": 732, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536380.8935091}
{"ep": "h2-00874", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4543, "status": "ok", "correct": true, "speedup": 1.4543, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 280.4, "calls": 2, "tokens_in": 11177, "tokens_out": 4959, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536387.4153666}
{"ep": "h2-00901", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5465, "status": "ok", "correct": true, "speedup": 1.5465, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 201.5, "calls": 2, "tokens_in": 6440, "tokens_out": 5776, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536388.9020283}
{"ep": "h2-00921", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0023, "status": "ok", "correct": true, "speedup": 1.0023, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 137.5, "calls": 2, "tokens_in": 4168, "tokens_out": 2255, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536399.044929}
{"ep": "h2-00871", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9162, "status": "ok", "correct": true, "speedup": 0.9162, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 305.0, "calls": 3, "tokens_in": 24026, "tokens_out": 2071, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536399.749599}
{"ep": "h2-00943", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0059, "status": "ok", "correct": true, "speedup": 1.0059, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 72.4, "calls": 2, "tokens_in": 13740, "tokens_out": 1264, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536400.338859}
{"ep": "h2-00794", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.8847, "status": "ok", "correct": true, "speedup": 1.8847, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 492.4, "calls": 3, "tokens_in": 17424, "tokens_out": 14458, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536402.124009}
{"ep": "h2-00932", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.535, "status": "ok", "correct": true, "speedup": 0.535, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 93.0, "calls": 1, "tokens_in": 1565, "tokens_out": 1697, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536405.468461}
{"ep": "h2-00865", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0664, "status": "ok", "correct": true, "speedup": 1.0664, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 322.7, "calls": 2, "tokens_in": 14483, "tokens_out": 8255, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536406.408163}
{"ep": "h2-00924", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9961, "status": "ok", "correct": true, "speedup": 0.9961, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 129.1, "calls": 2, "tokens_in": 13389, "tokens_out": 981, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791536407.092943}
{"ep": "h2-00948", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0058, "status": "ok", "correct": true, "speedup": 1.0058, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 61.3, "calls": 1, "tokens_in": 6477, "tokens_out": 522, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536407.2371945}
{"ep": "h2-00900", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5316, "status": "ok", "correct": true, "speedup": 1.5316, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 227.3, "calls": 3, "tokens_in": 10773, "tokens_out": 4072, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536408.6300154}
{"ep": "h2-00853", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0541, "status": "ok", "correct": true, "speedup": 1.0541, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 358.8, "calls": 2, "tokens_in": 4687, "tokens_out": 2852, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536411.503396}
{"ep": "h2-00812", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.4665, "status": "ok", "correct": true, "speedup": 2.4665, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 472.8, "calls": 3, "tokens_in": 16380, "tokens_out": 12493, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536412.2231455}
{"ep": "h2-00882", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9249, "status": "ok", "correct": true, "speedup": 0.9249, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 288.9, "calls": 3, "tokens_in": 24136, "tokens_out": 2449, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536416.0893297}
{"ep": "h2-00938", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0038, "status": "ok", "correct": true, "speedup": 1.0038, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 97.9, "calls": 2, "tokens_in": 11726, "tokens_out": 1461, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536417.7850947}
{"ep": "h2-00878", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0083, "status": "ok", "correct": true, "speedup": 1.0083, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 305.4, "calls": 2, "tokens_in": 15091, "tokens_out": 4960, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536418.6386993}
{"ep": "h2-00903", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0246, "status": "ok", "correct": true, "speedup": 1.0246, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 230.3, "calls": 2, "tokens_in": 6830, "tokens_out": 7992, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536419.014412}
{"ep": "h2-00935", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9765, "status": "ok", "correct": true, "speedup": 0.9765, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 110.5, "calls": 1, "tokens_in": 7032, "tokens_out": 1137, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536427.1294603}
{"ep": "h2-00880", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0044, "status": "ok", "correct": true, "speedup": 1.0044, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 307.2, "calls": 3, "tokens_in": 20017, "tokens_out": 2708, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791536432.0610619}
{"ep": "h2-00877", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0064, "status": "ok", "correct": true, "speedup": 1.0064, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 327.9, "calls": 2, "tokens_in": 16314, "tokens_out": 2720, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536438.6497784}
{"ep": "h2-00929", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.03, "status": "ok", "correct": true, "speedup": 1.03, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 149.1, "calls": 2, "tokens_in": 12677, "tokens_out": 1489, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536439.1382542}
{"ep": "h2-00873", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.5663, "status": "ok", "correct": true, "speedup": 6.5663, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 343.7, "calls": 3, "tokens_in": 18062, "tokens_out": 20413, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536443.7927988}
{"ep": "h2-00872", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0085, "status": "ok", "correct": true, "speedup": 1.0085, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 356.0, "calls": 2, "tokens_in": 15306, "tokens_out": 6222, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536453.982662}
{"ep": "h2-00939", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4325, "status": "ok", "correct": true, "speedup": 0.4325, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 136.3, "calls": 3, "tokens_in": 22561, "tokens_out": 5884, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536456.7693167}
{"ep": "h2-00979", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8085, "status": "ok", "correct": true, "speedup": 0.8085, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 38.0, "calls": 3, "tokens_in": 18532, "tokens_out": 1432, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536457.059384}
{"ep": "h2-00919", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0475, "status": "ok", "correct": true, "speedup": 1.0475, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 202.2, "calls": 2, "tokens_in": 5542, "tokens_out": 4945, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536459.8099961}
{"ep": "h2-00941", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0433, "status": "ok", "correct": true, "speedup": 1.0433, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 140.9, "calls": 3, "tokens_in": 18614, "tokens_out": 3742, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536464.0913177}
{"ep": "h2-00960", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.002, "status": "ok", "correct": true, "speedup": 1.002, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 88.9, "calls": 1, "tokens_in": 6477, "tokens_out": 521, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536466.1126935}
{"ep": "h2-00974", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'div_gelu_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=div_gelu_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/tor", "wall_s": 55.4, "calls": 1, "tokens_in": 1599, "tokens_out": 936, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536466.8696136}
{"ep": "h2-00965", "task": "L2_094", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0034, "status": "ok", "correct": true, "speedup": 1.0034, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.1, "calls": 2, "tokens_in": 6145, "tokens_out": 3516, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536467.1178868}
{"ep": "h2-00947", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0068, "status": "ok", "correct": true, "speedup": 1.0068, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 123.1, "calls": 2, "tokens_in": 12812, "tokens_out": 2683, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791536467.4841025}
{"ep": "h2-00983", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8479, "status": "ok", "correct": true, "speedup": 0.8479, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 30.0, "calls": 1, "tokens_in": 7030, "tokens_out": 1219, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791536469.1848364}
{"ep": "h2-00969", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0199, "status": "ok", "correct": true, "speedup": 1.0199, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 66.4, "calls": 3, "tokens_in": 18307, "tokens_out": 4129, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536471.9157481}
{"ep": "h2-00963", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'resnet_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=resnet_fused -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/tor", "wall_s": 93.7, "calls": 1, "tokens_in": 2743, "tokens_out": 3035, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536481.163785}
{"ep": "h2-00888", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5523, "status": "ok", "correct": true, "speedup": 0.5523, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 335.4, "calls": 3, "tokens_in": 20119, "tokens_out": 3191, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791536481.5079257}
{"ep": "h2-00977", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0168, "status": "ok", "correct": true, "speedup": 1.0168, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 64.5, "calls": 2, "tokens_in": 15472, "tokens_out": 3601, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536482.2925982}
{"ep": "h2-00946", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0049, "status": "ok", "correct": true, "speedup": 1.0049, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 154.4, "calls": 2, "tokens_in": 16178, "tokens_out": 2514, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536498.285288}
{"ep": "h2-00850", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1709, "status": "ok", "correct": true, "speedup": 1.1709, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 462.5, "calls": 2, "tokens_in": 30997, "tokens_out": 19083, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791536498.881726}
{"ep": "h2-00985", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0062, "status": "ok", "correct": true, "speedup": 1.0062, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 48.0, "calls": 2, "tokens_in": 13713, "tokens_out": 1160, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536502.0112834}
{"ep": "h2-00980", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0055, "status": "ok", "correct": true, "speedup": 1.0055, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 76.9, "calls": 2, "tokens_in": 4024, "tokens_out": 2138, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536504.0605974}
{"ep": "h2-00973", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0662, "status": "ok", "correct": true, "speedup": 1.0662, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 102.5, "calls": 3, "tokens_in": 16423, "tokens_out": 2313, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536511.1724458}
{"ep": "h2-00934", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0046, "status": "ok", "correct": true, "speedup": 1.0046, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 197.5, "calls": 2, "tokens_in": 4065, "tokens_out": 2115, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536511.6867976}
{"ep": "h2-00918", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 24.8376, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 261.0, "calls": 2, "tokens_in": 16304, "tokens_out": 8752, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791536511.7062762}
{"ep": "h2-00987", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'mt_fuse': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=mt_fuse -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/ap", "wall_s": 57.4, "calls": 1, "tokens_in": 1666, "tokens_out": 658, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536514.4202754}
{"ep": "h2-00857", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8358, "status": "ok", "correct": true, "speedup": 0.8358, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 453.9, "calls": 4, "tokens_in": 83187, "tokens_out": 21062, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791536515.4705224}
{"ep": "h2-00975", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9935, "status": "ok", "correct": true, "speedup": 0.9935, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 105.5, "calls": 3, "tokens_in": 22602, "tokens_out": 3066, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536517.766346}
{"ep": "h2-00971", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0276, "status": "ok", "correct": true, "speedup": 1.0276, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 113.6, "calls": 2, "tokens_in": 4480, "tokens_out": 2303, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536520.7061307}
{"ep": "h2-00998", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "incorrect", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "output shape (1024, 8192, 1, 1) != expected (1, 8192, 1024, 1)", "wall_s": 40.4, "calls": 1, "tokens_in": 1633, "tokens_out": 3160, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536522.700005}
{"ep": "h2-00957", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.028, "status": "ok", "correct": true, "speedup": 1.028, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 159.3, "calls": 2, "tokens_in": 13798, "tokens_out": 11713, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536526.398282}
{"ep": "h2-00991", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0189, "status": "ok", "correct": true, "speedup": 1.0189, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 59.8, "calls": 1, "tokens_in": 1750, "tokens_out": 1879, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536526.6456625}
{"ep": "h2-00944", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.0238, "status": "ok", "correct": true, "speedup": 2.0238, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 192.7, "calls": 2, "tokens_in": 7818, "tokens_out": 9323, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536530.8537288}
{"ep": "h2-00923", "task": "L3_014", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0633, "status": "ok", "correct": true, "speedup": 1.0633, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 262.5, "calls": 2, "tokens_in": 10519, "tokens_out": 2320, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536532.659196}
{"ep": "h2-00978", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9218, "status": "ok", "correct": true, "speedup": 0.9218, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 114.4, "calls": 2, "tokens_in": 15372, "tokens_out": 1891, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536532.989535}
{"ep": "h2-00933", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7771, "status": "ok", "correct": true, "speedup": 0.7771, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 232.3, "calls": 3, "tokens_in": 23488, "tokens_out": 2801, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791536544.9531527}
{"ep": "h2-00936", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3614, "status": "ok", "correct": true, "speedup": 2.3614, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 230.9, "calls": 3, "tokens_in": 20927, "tokens_out": 3895, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791536549.4025679}
{"ep": "h2-00917", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.6906, "status": "ok", "correct": true, "speedup": 6.6906, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 310.5, "calls": 3, "tokens_in": 18154, "tokens_out": 19177, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536558.6936967}
{"ep": "h2-00950", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7574, "status": "ok", "correct": true, "speedup": 0.7574, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 218.2, "calls": 2, "tokens_in": 12049, "tokens_out": 18637, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536570.6475563}
{"ep": "h2-01011", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0518, "status": "ok", "correct": true, "speedup": 1.0518, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 46.5, "calls": 1, "tokens_in": 4862, "tokens_out": 1878, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536572.8696196}
{"ep": "h2-00988", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.922, "status": "ok", "correct": true, "speedup": 0.922, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 124.7, "calls": 3, "tokens_in": 24184, "tokens_out": 2235, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536584.4633646}
{"ep": "h2-00972", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3818, "status": "ok", "correct": true, "speedup": 1.3818, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 180.2, "calls": 2, "tokens_in": 16679, "tokens_out": 7882, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536587.3873727}
{"ep": "h2-01005", "task": "L2_029", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0017, "status": "ok", "correct": true, "speedup": 1.0017, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 79.3, "calls": 2, "tokens_in": 11938, "tokens_out": 1730, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791536591.054482}
{"ep": "h2-00937", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8739, "status": "ok", "correct": true, "speedup": 0.8739, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 273.2, "calls": 3, "tokens_in": 46311, "tokens_out": 13999, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536592.1856794}
{"ep": "h2-00959", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4453, "status": "ok", "correct": true, "speedup": 1.4453, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 222.2, "calls": 2, "tokens_in": 11188, "tokens_out": 5053, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536595.1454837}
{"ep": "h2-00889", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0009, "status": "ok", "correct": true, "speedup": 1.0009, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 448.6, "calls": 2, "tokens_in": 4235, "tokens_out": 1981, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536595.3961794}
{"ep": "h2-00976", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3683, "status": "ok", "correct": true, "speedup": 1.3683, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 180.2, "calls": 2, "tokens_in": 17501, "tokens_out": 8265, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536596.2545054}
{"ep": "h2-00986", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0485, "status": "ok", "correct": true, "speedup": 1.0485, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 141.4, "calls": 3, "tokens_in": 18846, "tokens_out": 3947, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536598.2059743}
{"ep": "h2-00994", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0065, "status": "ok", "correct": true, "speedup": 1.0065, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 135.7, "calls": 3, "tokens_in": 25023, "tokens_out": 4526, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791536604.8514318}
{"ep": "h2-00876", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0494, "status": "ok", "correct": true, "speedup": 1.0494, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 498.9, "calls": 2, "tokens_in": 4915, "tokens_out": 3558, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536607.380071}
{"ep": "h2-01017", "task": "L2_076", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0039, "status": "ok", "correct": true, "speedup": 1.0039, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 61.9, "calls": 1, "tokens_in": 6367, "tokens_out": 541, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791536611.292141}
{"ep": "h2-00842", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.6704, "status": "ok", "correct": true, "speedup": 7.6704, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 601.6, "calls": 3, "tokens_in": 19259, "tokens_out": 24381, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536611.6016695}
{"ep": "h2-00982", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.9575, "status": "ok", "correct": true, "speedup": 3.9575, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 175.4, "calls": 2, "tokens_in": 6108, "tokens_out": 6715, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536614.0613604}
{"ep": "h2-00990", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0618, "status": "ok", "correct": true, "speedup": 1.0618, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 150.6, "calls": 2, "tokens_in": 16032, "tokens_out": 4778, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791536616.6763966}
{"ep": "h2-00940", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0038, "status": "ok", "correct": true, "speedup": 1.0038, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 303.3, "calls": 3, "tokens_in": 20299, "tokens_out": 2872, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791536625.9832902}
{"ep": "h2-01014", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0914, "status": "ok", "correct": true, "speedup": 1.0914, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 95.5, "calls": 2, "tokens_in": 15457, "tokens_out": 4367, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791536628.136523}
{"ep": "h2-00953", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9941, "status": "ok", "correct": true, "speedup": 0.9941, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 270.9, "calls": 3, "tokens_in": 22403, "tokens_out": 2967, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536628.6769109}
{"ep": "h2-00927", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4253, "status": "ok", "correct": true, "speedup": 1.4253, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 344.0, "calls": 2, "tokens_in": 16864, "tokens_out": 7999, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536629.4101443}
{"ep": "h2-00961", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7823, "status": "ok", "correct": true, "speedup": 0.7823, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 252.1, "calls": 3, "tokens_in": 49842, "tokens_out": 14679, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791536630.490414}
{"ep": "h2-00952", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.3057, "status": "ok", "correct": true, "speedup": 3.3057, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 274.0, "calls": 3, "tokens_in": 15884, "tokens_out": 17555, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536631.1134963}
{"ep": "h2-00993", "task": "L2_028", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0163, "status": "ok", "correct": true, "speedup": 1.0163, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 164.2, "calls": 2, "tokens_in": 11393, "tokens_out": 4383, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536631.6789975}
{"ep": "h2-01000", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0111, "status": "ok", "correct": true, "speedup": 1.0111, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 134.4, "calls": 2, "tokens_in": 16179, "tokens_out": 2495, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536633.2553666}
{"ep": "h2-01007", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9199, "status": "ok", "correct": true, "speedup": 0.9199, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 121.0, "calls": 3, "tokens_in": 23744, "tokens_out": 1900, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536636.4695349}
{"ep": "h2-00992", "task": "L2_047", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.057, "status": "ok", "correct": true, "speedup": 1.057, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 170.8, "calls": 2, "tokens_in": 4721, "tokens_out": 2977, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536637.888007}
{"ep": "h2-00942", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.2325, "status": "ok", "correct": true, "speedup": 2.2325, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 312.9, "calls": 2, "tokens_in": 6674, "tokens_out": 8215, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536638.3226576}
{"ep": "h2-00958", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.1236, "status": "ok", "correct": true, "speedup": 2.1236, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 267.8, "calls": 3, "tokens_in": 16122, "tokens_out": 14761, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536640.2450917}
{"ep": "h2-00945", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.196, "status": "ok", "correct": true, "speedup": 1.196, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 301.9, "calls": 2, "tokens_in": 16693, "tokens_out": 17751, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536643.814276}
{"ep": "h2-00981", "task": "L1_056", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5176, "status": "ok", "correct": true, "speedup": 1.5176, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 213.1, "calls": 2, "tokens_in": 6753, "tokens_out": 7121, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536645.146297}
{"ep": "h2-01004", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0034, "status": "ok", "correct": true, "speedup": 1.0034, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 133.7, "calls": 3, "tokens_in": 24738, "tokens_out": 2201, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536645.3449893}
{"ep": "h2-01008", "task": "L2_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0039, "status": "ok", "correct": true, "speedup": 1.0039, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 144.5, "calls": 3, "tokens_in": 20338, "tokens_out": 2983, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791536662.2248077}
{"ep": "h2-01015", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1996, "status": "ok", "correct": true, "speedup": 1.1996, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 134.1, "calls": 2, "tokens_in": 5107, "tokens_out": 3957, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536667.1115582}
{"ep": "h2-00887", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3696, "status": "ok", "correct": true, "speedup": 1.3696, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 523.1, "calls": 2, "tokens_in": 15858, "tokens_out": 20255, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536669.1121998}
{"ep": "h2-01031", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0005, "status": "ok", "correct": true, "speedup": 1.0005, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 77.3, "calls": 1, "tokens_in": 6477, "tokens_out": 520, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536688.5461974}
{"ep": "h2-00951", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7878, "status": "ok", "correct": true, "speedup": 0.7878, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 333.5, "calls": 3, "tokens_in": 50147, "tokens_out": 15047, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791536690.4649932}
{"ep": "h2-01009", "task": "L3_021", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0497, "status": "ok", "correct": true, "speedup": 1.0497, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 170.3, "calls": 3, "tokens_in": 18748, "tokens_out": 3859, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536691.0448403}
{"ep": "h2-00964", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0268, "status": "ok", "correct": true, "speedup": 1.0268, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 302.4, "calls": 1, "tokens_in": 5832, "tokens_out": 524, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536691.3068764}
{"ep": "h2-01006", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9931, "status": "ok", "correct": true, "speedup": 0.9931, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 182.1, "calls": 3, "tokens_in": 22384, "tokens_out": 2950, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536696.5115995}
{"ep": "h2-01032", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'conv3d_bias_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=conv3d_bias_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/inclu", "wall_s": 86.3, "calls": 1, "tokens_in": 2157, "tokens_out": 1384, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536697.9044447}
{"ep": "h2-01012", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9937, "status": "ok", "correct": true, "speedup": 0.9937, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 178.9, "calls": 3, "tokens_in": 22378, "tokens_out": 2934, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536705.574305}
{"ep": "h2-00949", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0637, "status": "ok", "correct": true, "speedup": 1.0637, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 359.2, "calls": 2, "tokens_in": 4933, "tokens_out": 3559, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536706.5258548}
{"ep": "h2-00968", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8736, "status": "ok", "correct": true, "speedup": 0.8736, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 304.9, "calls": 3, "tokens_in": 8116, "tokens_out": 2467, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536707.0261188}
{"ep": "h2-00962", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.165, "status": "ok", "correct": true, "speedup": 1.165, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 328.1, "calls": 3, "tokens_in": 16524, "tokens_out": 12290, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536708.9675758}
{"ep": "h2-01050", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7707, "status": "ok", "correct": true, "speedup": 0.7707, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 54.1, "calls": 3, "tokens_in": 18402, "tokens_out": 1371, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536716.3279436}
{"ep": "h2-00861", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3213, "status": "ok", "correct": true, "speedup": 2.3213, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 646.2, "calls": 2, "tokens_in": 7586, "tokens_out": 11628, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536720.6286602}
{"ep": "h2-01024", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3013, "status": "ok", "correct": true, "speedup": 1.3013, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 129.6, "calls": 2, "tokens_in": 14899, "tokens_out": 3818, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791536721.7651637}
{"ep": "h2-01019", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0102, "status": "ok", "correct": true, "speedup": 1.0102, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 158.5, "calls": 3, "tokens_in": 24428, "tokens_out": 3817, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791536729.1130602}
{"ep": "h2-00966", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0596, "status": "ok", "correct": true, "speedup": 1.0596, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 329.9, "calls": 2, "tokens_in": 14729, "tokens_out": 2427, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791536729.658368}
{"ep": "h2-01026", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.857, "status": "ok", "correct": true, "speedup": 0.857, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 149.1, "calls": 2, "tokens_in": 14113, "tokens_out": 12657, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536744.5461733}
{"ep": "h2-01013", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6187, "status": "ok", "correct": true, "speedup": 2.6187, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 214.5, "calls": 3, "tokens_in": 16948, "tokens_out": 15387, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536745.3365264}
{"ep": "h2-01053", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7475, "status": "ok", "correct": true, "speedup": 0.7475, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 63.1, "calls": 2, "tokens_in": 14161, "tokens_out": 1798, "ctx_chars": 10850, "ctx_sha": "daebc65ff56f9d20", "t_end": 1791536751.66107}
{"ep": "h2-00967", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0098, "status": "ok", "correct": true, "speedup": 1.0098, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 351.4, "calls": 2, "tokens_in": 16036, "tokens_out": 2176, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536751.747902}
{"ep": "h2-01023", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.018, "status": "ok", "correct": true, "speedup": 1.018, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 163.3, "calls": 3, "tokens_in": 24800, "tokens_out": 2241, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536754.3963068}
{"ep": "h2-01027", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0033, "status": "ok", "correct": true, "speedup": 1.0033, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 159.1, "calls": 3, "tokens_in": 24680, "tokens_out": 2184, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536755.344268}
{"ep": "h2-01060", "task": "L3_037", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8042, "status": "ok", "correct": true, "speedup": 0.8042, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 53.1, "calls": 3, "tokens_in": 18724, "tokens_out": 1518, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536759.6751497}
{"ep": "h2-00999", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4885, "status": "ok", "correct": true, "speedup": 1.4885, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 263.4, "calls": 2, "tokens_in": 15273, "tokens_out": 10162, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536761.64302}
{"ep": "h2-01064", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0583, "status": "ok", "correct": true, "speedup": 1.0583, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 43.0, "calls": 3, "tokens_in": 22693, "tokens_out": 2344, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791536763.6591609}
{"ep": "h2-01048", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0433, "status": "ok", "correct": true, "speedup": 1.0433, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 118.9, "calls": 2, "tokens_in": 13012, "tokens_out": 2272, "ctx_chars": 9274, "ctx_sha": "2120d7398ea70d7e", "t_end": 1791536764.0350463}
{"ep": "h2-00970", "task": "L3_020", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3824, "status": "ok", "correct": true, "speedup": 1.3824, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 364.9, "calls": 2, "tokens_in": 12201, "tokens_out": 20432, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536771.3070529}
{"ep": "h2-01058", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.043, "status": "ok", "correct": true, "speedup": 1.043, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 78.8, "calls": 2, "tokens_in": 5111, "tokens_out": 3055, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536776.7531028}
{"ep": "h2-01061", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3338, "status": "ok", "correct": true, "speedup": 1.3338, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 72.5, "calls": 1, "tokens_in": 5998, "tokens_out": 721, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536779.5375066}
{"ep": "h2-01054", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0178, "status": "ok", "correct": true, "speedup": 1.0178, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 91.3, "calls": 2, "tokens_in": 18019, "tokens_out": 5632, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791536781.7872584}
{"ep": "h2-01029", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.696, "status": "ok", "correct": true, "speedup": 3.696, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 177.5, "calls": 3, "tokens_in": 15822, "tokens_out": 13711, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536782.3413045}
{"ep": "h2-01018", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0105, "status": "ok", "correct": true, "speedup": 1.0105, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 225.2, "calls": 2, "tokens_in": 6377, "tokens_out": 7605, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536783.936564}
{"ep": "h2-01059", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0601, "status": "ok", "correct": true, "speedup": 1.0601, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.8, "calls": 3, "tokens_in": 25683, "tokens_out": 4551, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791536787.3435004}
{"ep": "h2-01071", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.847, "status": "ok", "correct": true, "speedup": 0.847, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 36.8, "calls": 1, "tokens_in": 7030, "tokens_out": 1232, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791536788.4986482}
{"ep": "h2-01056", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0188, "status": "ok", "correct": true, "speedup": 1.0188, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 97.6, "calls": 2, "tokens_in": 5108, "tokens_out": 4344, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536788.8571823}
{"ep": "h2-01028", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0282, "status": "ok", "correct": true, "speedup": 1.0282, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 191.5, "calls": 2, "tokens_in": 9175, "tokens_out": 2417, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536789.7546446}
{"ep": "h2-01055", "task": "L3_009", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3239, "status": "ok", "correct": true, "speedup": 0.3239, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 121.1, "calls": 4, "tokens_in": 37495, "tokens_out": 9033, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536812.1336586}
{"ep": "h2-01022", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.5893, "status": "ok", "correct": true, "speedup": 4.5893, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 226.1, "calls": 3, "tokens_in": 16578, "tokens_out": 16527, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536813.5169983}
{"ep": "h2-01052", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0166, "status": "ok", "correct": true, "speedup": 1.0166, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 145.8, "calls": 5, "tokens_in": 50062, "tokens_out": 5716, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536814.8650744}
{"ep": "h2-01049", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3361, "status": "ok", "correct": true, "speedup": 1.3361, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 171.6, "calls": 1, "tokens_in": 5998, "tokens_out": 718, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536816.9429781}
{"ep": "h2-01075", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5537, "status": "ok", "correct": true, "speedup": 0.5537, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 56.7, "calls": 1, "tokens_in": 1565, "tokens_out": 1779, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536818.3511734}
{"ep": "h2-01079", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0234, "status": "ok", "correct": true, "speedup": 1.0234, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 48.8, "calls": 2, "tokens_in": 9161, "tokens_out": 2271, "ctx_chars": 5026, "ctx_sha": "9bd1380e13dcea35", "t_end": 1791536825.6002285}
{"ep": "h2-00955", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0624, "status": "ok", "correct": true, "speedup": 1.0624, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 471.3, "calls": 3, "tokens_in": 8409, "tokens_out": 2176, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536830.8797078}
{"ep": "h2-00989", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 8.8909, "status": "ok", "correct": true, "speedup": 8.8909, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 369.8, "calls": 4, "tokens_in": 25683, "tokens_out": 19751, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536833.8623111}
{"ep": "h2-01066", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3217, "status": "ok", "correct": true, "speedup": 1.3217, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 107.4, "calls": 2, "tokens_in": 13178, "tokens_out": 2601, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536836.5625432}
{"ep": "h2-01062", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.1269, "status": "ok", "correct": true, "speedup": 2.1269, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 131.7, "calls": 2, "tokens_in": 7600, "tokens_out": 8579, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536840.67944}
{"ep": "h2-01035", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7163, "status": "ok", "correct": true, "speedup": 0.7163, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 219.2, "calls": 2, "tokens_in": 16477, "tokens_out": 4150, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791536845.18182}
{"ep": "h2-01083", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "incorrect", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "output mismatch beyond atol=rtol=0.0001", "wall_s": 63.1, "calls": 1, "tokens_in": 2942, "tokens_out": 4654, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536847.0748346}
{"ep": "h2-01030", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4837, "status": "ok", "correct": true, "speedup": 1.4837, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 246.4, "calls": 2, "tokens_in": 10544, "tokens_out": 20380, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536853.804217}
{"ep": "h2-01038", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3345, "status": "ok", "correct": true, "speedup": 1.3345, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 235.5, "calls": 1, "tokens_in": 5998, "tokens_out": 745, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536864.8626719}
{"ep": "h2-01084", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0277, "status": "ok", "correct": true, "speedup": 1.0277, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 88.1, "calls": 1, "tokens_in": 5832, "tokens_out": 524, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536875.4621215}
{"ep": "h2-01051", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8062, "status": "ok", "correct": true, "speedup": 0.8062, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 208.5, "calls": 5, "tokens_in": 58243, "tokens_out": 13129, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536875.652286}
{"ep": "h2-01067", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0257, "status": "ok", "correct": true, "speedup": 1.0257, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 151.3, "calls": 2, "tokens_in": 4654, "tokens_out": 2508, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536880.9763033}
{"ep": "h2-01039", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.798, "status": "ok", "correct": true, "speedup": 2.798, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 252.0, "calls": 2, "tokens_in": 13979, "tokens_out": 4238, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536882.5321996}
{"ep": "h2-01087", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.057, "status": "ok", "correct": true, "speedup": 1.057, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 95.2, "calls": 3, "tokens_in": 22730, "tokens_out": 2371, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791536885.0015204}
{"ep": "h2-00896", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7488, "status": "ok", "correct": true, "speedup": 0.7488, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 729.1, "calls": 5, "tokens_in": 53635, "tokens_out": 15514, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536888.6180358}
{"ep": "h2-01091", "task": "L2_086", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0089, "status": "ok", "correct": true, "speedup": 1.0089, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 73.4, "calls": 2, "tokens_in": 4283, "tokens_out": 2699, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536890.365608}
{"ep": "h2-01089", "task": "L2_077", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0176, "status": "ok", "correct": true, "speedup": 1.0176, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 77.4, "calls": 2, "tokens_in": 16305, "tokens_out": 2551, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791536890.885682}
{"ep": "h2-01069", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7951, "status": "ok", "correct": true, "speedup": 0.7951, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 146.0, "calls": 3, "tokens_in": 18888, "tokens_out": 1691, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536891.3704097}
{"ep": "h2-01044", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.2663, "status": "ok", "correct": true, "speedup": 6.2663, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 254.4, "calls": 3, "tokens_in": 17138, "tokens_out": 18207, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536892.2746387}
{"ep": "h2-01085", "task": "L1_061", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0087, "status": "ok", "correct": true, "speedup": 1.0087, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 109.4, "calls": 3, "tokens_in": 24630, "tokens_out": 2126, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536897.8880017}
{"ep": "h2-01072", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1435, "status": "ok", "correct": true, "speedup": 1.1435, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 146.1, "calls": 2, "tokens_in": 13786, "tokens_out": 11881, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536900.5324986}
{"ep": "h2-01047", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1065, "status": "ok", "correct": true, "speedup": 1.1065, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 258.6, "calls": 2, "tokens_in": 15481, "tokens_out": 3409, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791536902.4389129}
{"ep": "h2-01093", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0029, "status": "ok", "correct": true, "speedup": 1.0029, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 79.0, "calls": 3, "tokens_in": 24039, "tokens_out": 2796, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791536904.6129546}
{"ep": "h2-01041", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.1115, "status": "ok", "correct": true, "speedup": 2.1115, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 279.0, "calls": 3, "tokens_in": 14031, "tokens_out": 10436, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536910.7054443}
{"ep": "h2-00996", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0014, "status": "ok", "correct": true, "speedup": 1.0014, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 430.6, "calls": 3, "tokens_in": 9177, "tokens_out": 3992, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536911.8038933}
{"ep": "h2-01074", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.6924, "status": "ok", "correct": true, "speedup": 2.6924, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 154.2, "calls": 2, "tokens_in": 5620, "tokens_out": 5236, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536913.8763049}
{"ep": "h2-01034", "task": "L2_039", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9958, "status": "ok", "correct": true, "speedup": 0.9958, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 297.4, "calls": 3, "tokens_in": 22368, "tokens_out": 2929, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536914.1196458}
{"ep": "h2-01078", "task": "L2_089", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 34.4743, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 144.6, "calls": 2, "tokens_in": 6923, "tokens_out": 6792, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536915.8782003}
{"ep": "h2-01046", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0277, "status": "ok", "correct": true, "speedup": 1.0277, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 275.6, "calls": 1, "tokens_in": 5832, "tokens_out": 524, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536915.878872}
{"ep": "h2-01065", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4458, "status": "ok", "correct": true, "speedup": 1.4458, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 194.5, "calls": 2, "tokens_in": 11931, "tokens_out": 7040, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536916.256529}
{"ep": "h2-01002", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 9.2652, "status": "ok", "correct": true, "speedup": 9.2652, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 413.2, "calls": 2, "tokens_in": 6794, "tokens_out": 11381, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536917.2384512}
{"ep": "h2-01068", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9247, "status": "ok", "correct": true, "speedup": 0.9247, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 188.6, "calls": 3, "tokens_in": 23906, "tokens_out": 1991, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791536933.11607}
{"ep": "h2-00956", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9918, "status": "ok", "correct": true, "speedup": 0.9918, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 569.8, "calls": 2, "tokens_in": 16355, "tokens_out": 3969, "ctx_chars": 11065, "ctx_sha": "b967fe13455fdbd9", "t_end": 1791536934.5525415}
{"ep": "h2-01105", "task": "L2_048", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3305, "status": "ok", "correct": true, "speedup": 1.3305, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 59.9, "calls": 1, "tokens_in": 5998, "tokens_out": 764, "ctx_chars": 9970, "ctx_sha": "c573808a484b68ec", "t_end": 1791536942.4249368}
{"ep": "h2-01099", "task": "L2_086", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0039, "status": "ok", "correct": true, "speedup": 1.0039, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 97.3, "calls": 3, "tokens_in": 20676, "tokens_out": 976, "ctx_chars": 10909, "ctx_sha": "65e4e510dcc4381c", "t_end": 1791536944.3435464}
{"ep": "h2-01080", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0233, "status": "ok", "correct": true, "speedup": 1.0233, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 165.2, "calls": 1, "tokens_in": 5832, "tokens_out": 524, "ctx_chars": 9656, "ctx_sha": "797896dbdcfce662", "t_end": 1791536944.7475696}
{"ep": "h2-01042", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0238, "status": "ok", "correct": true, "speedup": 1.0238, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 322.4, "calls": 2, "tokens_in": 4750, "tokens_out": 2526, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536955.647258}
{"ep": "h2-01021", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0183, "status": "ok", "correct": true, "speedup": 1.0183, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 371.6, "calls": 2, "tokens_in": 5664, "tokens_out": 4616, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536956.017959}
{"ep": "h2-01102", "task": "L2_089", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0575, "status": "ok", "correct": true, "speedup": 1.0575, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.5, "calls": 2, "tokens_in": 14784, "tokens_out": 2545, "ctx_chars": 10527, "ctx_sha": "9d7b7603b9e7f31f", "t_end": 1791536956.9998312}
{"ep": "h2-01003", "task": "L3_030", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7654, "status": "ok", "correct": true, "speedup": 0.7654, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 447.1, "calls": 3, "tokens_in": 48325, "tokens_out": 15769, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536958.2885268}
{"ep": "h2-01077", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0598, "status": "ok", "correct": true, "speedup": 1.0598, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 195.7, "calls": 2, "tokens_in": 6330, "tokens_out": 6438, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536959.7231889}
{"ep": "h2-01101", "task": "L2_028", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0236, "status": "ok", "correct": true, "speedup": 1.0236, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 99.1, "calls": 2, "tokens_in": 4647, "tokens_out": 2364, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536963.9206383}
{"ep": "h2-01040", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0283, "status": "ok", "correct": true, "speedup": 1.0283, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 332.8, "calls": 1, "tokens_in": 1666, "tokens_out": 565, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536963.9539266}
{"ep": "h2-01098", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0165, "status": "ok", "correct": true, "speedup": 1.0165, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 123.5, "calls": 2, "tokens_in": 16228, "tokens_out": 2508, "ctx_chars": 12117, "ctx_sha": "5ee3def88dc5d5e6", "t_end": 1791536968.6750996}
{"ep": "h2-01036", "task": "L2_039", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0026, "status": "ok", "correct": true, "speedup": 1.0026, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 341.8, "calls": 2, "tokens_in": 15270, "tokens_out": 6113, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791536969.934022}
{"ep": "h2-01118", "task": "L2_076", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9981, "status": "ok", "correct": true, "speedup": 0.9981, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 57.2, "calls": 2, "tokens_in": 13358, "tokens_out": 981, "ctx_chars": 10847, "ctx_sha": "8373577b4232711a", "t_end": 1791536971.080351}
{"ep": "h2-01073", "task": "L3_014", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4671, "status": "ok", "correct": true, "speedup": 1.4671, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 217.9, "calls": 2, "tokens_in": 11279, "tokens_out": 4931, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791536973.2859595}
{"ep": "h2-01104", "task": "L2_092", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.8232, "status": "ok", "correct": true, "speedup": 2.8232, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 92.8, "calls": 2, "tokens_in": 5818, "tokens_out": 5740, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536973.7925117}
{"ep": "h2-00997", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.6846, "status": "ok", "correct": true, "speedup": 6.6846, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 493.9, "calls": 3, "tokens_in": 18624, "tokens_out": 20578, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536975.3885086}
{"ep": "h2-01119", "task": "L2_047", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "runtime_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "CompilationError: at 7:15:\ndef _mish_tanh_kernel(x_ptr, out_ptr, n, BLOCK: tl.constexpr):\n    pid = tl.program_id(0)\n    offs = pid * BLOCK + tl.arange(0, BLOCK)\n    mask = offs < n\n    x = tl.load(x_ptr + offs, mask=mask)\n    sp = tl.log(1.0 + tl.exp(x))\n    mish = x * tl.math.tanh(sp)\n            ", "wall_s": 61.7, "calls": 1, "tokens_in": 1666, "tokens_out": 553, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536975.8424635}
{"ep": "h2-01111", "task": "L2_092", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.3719, "status": "ok", "correct": true, "speedup": 2.3719, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 85.1, "calls": 2, "tokens_in": 14295, "tokens_out": 4955, "ctx_chars": 8529, "ctx_sha": "7e7b5a732e4def85", "t_end": 1791536977.3252966}
{"ep": "h2-01116", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.525, "status": "ok", "correct": true, "speedup": 0.525, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 67.7, "calls": 1, "tokens_in": 1565, "tokens_out": 1387, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536978.4323416}
{"ep": "h2-01057", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.8699, "status": "ok", "correct": true, "speedup": 2.8699, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 282.9, "calls": 3, "tokens_in": 17110, "tokens_out": 15461, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536979.4456935}
{"ep": "h2-01107", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "compile_error", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "RuntimeError: Error building extension 'dmish_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=dmish_ext -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csr", "wall_s": 94.4, "calls": 1, "tokens_in": 1501, "tokens_out": 864, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536983.0353336}
{"ep": "h2-01010", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.0105, "status": "ok", "correct": true, "speedup": 2.0105, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 462.5, "calls": 3, "tokens_in": 16784, "tokens_out": 12684, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536985.1966498}
{"ep": "h2-01108", "task": "L2_006", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1589, "status": "ok", "correct": true, "speedup": 1.1589, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 99.6, "calls": 1, "tokens_in": 1757, "tokens_out": 4021, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536990.0108202}
{"ep": "h2-01097", "task": "L1_012", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9422, "status": "ok", "correct": true, "speedup": 0.9422, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 150.1, "calls": 2, "tokens_in": 4643, "tokens_out": 2334, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536990.7926524}
{"ep": "h2-01115", "task": "L3_041", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8181, "status": "ok", "correct": true, "speedup": 0.8181, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 87.4, "calls": 2, "tokens_in": 12066, "tokens_out": 1489, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791536991.9875228}
{"ep": "h2-00995", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4074, "status": "ok", "correct": true, "speedup": 1.4074, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 522.2, "calls": 2, "tokens_in": 28940, "tokens_out": 18181, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536994.1169698}
{"ep": "h2-01001", "task": "L2_077", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5403, "status": "ok", "correct": true, "speedup": 1.5403, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 494.6, "calls": 2, "tokens_in": 6252, "tokens_out": 8931, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791536996.5619924}
{"ep": "h2-01016", "task": "L1_008", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9971, "status": "ok", "correct": true, "speedup": 0.9971, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 455.4, "calls": 4, "tokens_in": 25866, "tokens_out": 1601, "ctx_chars": 9033, "ctx_sha": "8b2060bfd7036bae", "t_end": 1791537000.3579988}
{"ep": "h2-01070", "task": "L2_048", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.2243, "status": "ok", "correct": true, "speedup": 4.2243, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 254.8, "calls": 3, "tokens_in": 14983, "tokens_out": 11055, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537006.4538488}
{"ep": "h2-01086", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.677, "status": "ok", "correct": true, "speedup": 1.677, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 220.4, "calls": 2, "tokens_in": 29288, "tokens_out": 19569, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537009.2139683}
{"ep": "h2-00904", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5816, "status": "ok", "correct": true, "speedup": 1.5816, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 831.4, "calls": 3, "tokens_in": 33329, "tokens_out": 17255, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791537021.2172875}
{"ep": "h2-01043", "task": "L1_058", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8426, "status": "ok", "correct": true, "speedup": 0.8426, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 389.3, "calls": 2, "tokens_in": 15411, "tokens_out": 2433, "ctx_chars": 11175, "ctx_sha": "5e031feda794c122", "t_end": 1791537025.7263796}
{"ep": "h2-01090", "task": "L1_058", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.411, "status": "ok", "correct": true, "speedup": 2.411, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 213.3, "calls": 2, "tokens_in": 7817, "tokens_out": 9831, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537028.1402931}
{"ep": "h2-00954", "task": "L2_094", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0404, "status": "ok", "correct": true, "speedup": 1.0404, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 674.2, "calls": 2, "tokens_in": 5104, "tokens_out": 3149, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537032.9711328}
{"ep": "h2-01110", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0261, "status": "ok", "correct": true, "speedup": 1.0261, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 142.2, "calls": 2, "tokens_in": 7206, "tokens_out": 9196, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537033.5864072}
{"ep": "h2-01094", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.2377, "status": "ok", "correct": true, "speedup": 4.2377, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 206.6, "calls": 3, "tokens_in": 13095, "tokens_out": 8913, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537037.4512165}
{"ep": "h2-01037", "task": "L2_029", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9979, "status": "ok", "correct": true, "speedup": 0.9979, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 410.7, "calls": 2, "tokens_in": 11396, "tokens_out": 1101, "ctx_chars": 9028, "ctx_sha": "2f70ede7a41b13f4", "t_end": 1791537039.3640568}
{"ep": "h2-00984", "task": "L2_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0215, "status": "ok", "correct": true, "speedup": 1.0215, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 596.4, "calls": 2, "tokens_in": 13573, "tokens_out": 5316, "ctx_chars": 9266, "ctx_sha": "9abf22a26a6d328a", "t_end": 1791537040.2181337}
{"ep": "h2-01082", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.0997, "status": "ok", "correct": true, "speedup": 3.0997, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 261.5, "calls": 3, "tokens_in": 26756, "tokens_out": 15939, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791537043.8796892}
{"ep": "h2-01076", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3821, "status": "ok", "correct": true, "speedup": 0.3821, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 281.7, "calls": 5, "tokens_in": 55891, "tokens_out": 13426, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791537045.3139796}
{"ep": "h2-01103", "task": "L1_061", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7504, "status": "ok", "correct": true, "speedup": 2.7504, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 175.2, "calls": 2, "tokens_in": 6747, "tokens_out": 7938, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537050.887413}
{"ep": "h2-01063", "task": "L3_037", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.917, "status": "ok", "correct": true, "speedup": 5.917, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 344.3, "calls": 3, "tokens_in": 18400, "tokens_out": 23026, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537060.578349}
{"ep": "h2-01045", "task": "L1_008", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4076, "status": "ok", "correct": true, "speedup": 1.4076, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 424.1, "calls": 2, "tokens_in": 5107, "tokens_out": 4537, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537062.3924298}
{"ep": "h2-01100", "task": "L3_009", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9452, "status": "ok", "correct": true, "speedup": 0.9452, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 209.4, "calls": 2, "tokens_in": 13905, "tokens_out": 7867, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791537063.2275295}
{"ep": "h2-01112", "task": "L2_006", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.0811, "status": "ok", "correct": true, "speedup": 4.0811, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 166.8, "calls": 2, "tokens_in": 6902, "tokens_out": 8116, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537064.654067}
{"ep": "h2-01114", "task": "L1_056", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9757, "status": "ok", "correct": true, "speedup": 0.9757, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 169.4, "calls": 3, "tokens_in": 24009, "tokens_out": 2178, "ctx_chars": 11539, "ctx_sha": "eb85e1c1c9a1056f", "t_end": 1791537071.8034472}
{"ep": "h2-01109", "task": "L3_030", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.7352, "status": "ok", "correct": true, "speedup": 1.7352, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 188.2, "calls": 2, "tokens_in": 30851, "tokens_out": 18954, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791537079.0872676}
{"ep": "h2-01092", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_self_gating", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.2126, "status": "ok", "correct": true, "speedup": 2.2126, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 263.6, "calls": 3, "tokens_in": 26376, "tokens_out": 14694, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791537081.9056973}
{"ep": "h2-01095", "task": "L2_043", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.005, "status": "ok", "correct": true, "speedup": 1.005, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 250.8, "calls": 4, "tokens_in": 23982, "tokens_out": 2714, "ctx_chars": 11823, "ctx_sha": "8cbf999f2b258061", "t_end": 1791537084.626335}
{"ep": "h2-01081", "task": "L1_066", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "none", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.993, "status": "ok", "correct": true, "speedup": 0.993, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 308.2, "calls": 4, "tokens_in": 17901, "tokens_out": 2951, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537089.9444938}
{"ep": "h2-01096", "task": "L2_075", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0083, "status": "ok", "correct": true, "speedup": 1.0083, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 254.0, "calls": 3, "tokens_in": 25937, "tokens_out": 5128, "ctx_chars": 10167, "ctx_sha": "bcbf9a06f3527d57", "t_end": 1791537090.554972}
{"ep": "h2-01033", "task": "L3_020", "split": "fresh", "reader": "claude-opus-4-8", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2927, "status": "ok", "correct": true, "speedup": 0.2927, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 478.8, "calls": 4, "tokens_in": 37066, "tokens_out": 8042, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791537092.811946}
{"ep": "h2-01020", "task": "L2_075", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5118, "status": "ok", "correct": true, "speedup": 1.5118, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 520.0, "calls": 2, "tokens_in": 6068, "tokens_out": 7155, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537092.8415585}
{"ep": "h2-01025", "task": "L2_043", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.2982, "status": "ok", "correct": true, "speedup": 2.2982, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 505.0, "calls": 2, "tokens_in": 5402, "tokens_out": 6572, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537100.1376066}
{"ep": "h2-01117", "task": "L3_021", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9768, "status": "ok", "correct": true, "speedup": 0.9768, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 191.6, "calls": 2, "tokens_in": 14138, "tokens_out": 12584, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791537103.4316213}
{"ep": "h2-01088", "task": "L1_066", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "predictor_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1923, "status": "ok", "correct": true, "speedup": 1.1923, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 292.6, "calls": 3, "tokens_in": 16632, "tokens_out": 12827, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537104.7084916}
{"ep": "h2-01106", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "opus_digest_calibrated", "groups": null, "store": false, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 2.7436, "status": "ok", "correct": true, "speedup": 2.7436, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 224.8, "calls": 3, "tokens_in": 16521, "tokens_out": 13989, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791537109.7925851}
{"ep": "h2-01113", "task": "L3_041", "split": "fresh", "reader": "claude-opus-5-5", "policy": "h2", "arm": "show_all", "groups": null, "store": true, "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.572, "status": "ok", "correct": true, "speedup": 3.572, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 252.2, "calls": 3, "tokens_in": 26518, "tokens_out": 15846, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791537152.711742}