{"ep": "ok-00014", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 16.8, "calls": 1, "tokens_in": 1814, "tokens_out": 725, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522500.106733} {"ep": "ok-00026", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "p_item": null, "p_policy": null, "success": true, "score": 1.0286, "status": "ok", "correct": true, "speedup": 1.0286, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 33.0, "calls": 1, "tokens_in": 2026, "tokens_out": 1537, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791522516.2904186} {"ep": "ok-00019", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0968, "status": "ok", "correct": true, "speedup": 1.0968, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 37.4, "calls": 1, "tokens_in": 7259, "tokens_out": 1129, "ctx_chars": 12103, "ctx_sha": "42cb8c90d2cfce7e", "t_end": 1791522520.7314322} {"ep": "ok-00055", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0299, "status": "ok", "correct": true, "speedup": 1.0299, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 46.6, "calls": 2, "tokens_in": 13671, "tokens_out": 1970, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791522529.8608897} {"ep": "ok-00021", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 1.1447, "status": "ok", "correct": true, "speedup": 1.1447, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 47.2, "calls": 3, "tokens_in": 21194, "tokens_out": 1425, "ctx_chars": 10587, "ctx_sha": "073757efd798c108", "t_end": 1791522530.4863293} {"ep": "ok-00003", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 48.9, "calls": 3, "tokens_in": 24679, "tokens_out": 1872, "ctx_chars": 13736, "ctx_sha": "f9598e6429f01c39", "t_end": 1791522532.2121572} {"ep": "ok-00047", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 49.3, "calls": 2, "tokens_in": 16294, "tokens_out": 2084, "ctx_chars": 13736, "ctx_sha": "1ff228bcf6371290", "t_end": 1791522532.5892687} {"ep": "ok-00018", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.036, "status": "ok", "correct": true, "speedup": 1.036, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 49.5, "calls": 3, "tokens_in": 23871, "tokens_out": 1889, "ctx_chars": 12848, "ctx_sha": "98fb6b45b82f188b", "t_end": 1791522532.7638211} {"ep": "ok-00043", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.8549, "status": "ok", "correct": true, "speedup": 0.8549, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 50.2, "calls": 1, "tokens_in": 2489, "tokens_out": 2877, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522533.5353718} {"ep": "ok-00059", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0369, "status": "ok", "correct": true, "speedup": 1.0369, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 63.5, "calls": 2, "tokens_in": 13179, "tokens_out": 2652, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791522546.8206828} {"ep": "ok-00005", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 72.1, "calls": 2, "tokens_in": 5451, "tokens_out": 4869, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522555.4106357} {"ep": "ok-00060", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8224, "status": "ok", "correct": true, "speedup": 0.8224, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 73.5, "calls": 3, "tokens_in": 11548, "tokens_out": 3872, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522556.7822351} {"ep": "ok-00036", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0349, "status": "ok", "correct": true, "speedup": 1.0349, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 79.5, "calls": 1, "tokens_in": 1933, "tokens_out": 1616, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522562.7600718} {"ep": "ok-00006", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0144, "status": "ok", "correct": true, "speedup": 1.0144, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.5, "calls": 3, "tokens_in": 24719, "tokens_out": 1891, "ctx_chars": 13736, "ctx_sha": "f9598e6429f01c39", "t_end": 1791522564.7713716} {"ep": "ok-00040", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 84.5, "calls": 2, "tokens_in": 5999, "tokens_out": 5578, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522567.799137} {"ep": "ok-00030", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7417, "status": "ok", "correct": true, "speedup": 0.7417, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 85.3, "calls": 2, "tokens_in": 10221, "tokens_out": 5148, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791522568.6350663} {"ep": "ok-00046", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5948, "status": "ok", "correct": true, "speedup": 1.5948, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 91.0, "calls": 2, "tokens_in": 5716, "tokens_out": 5113, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522574.3076105} {"ep": "ok-00058", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "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": 100.3, "calls": 3, "tokens_in": 28926, "tokens_out": 2880, "ctx_chars": 15603, "ctx_sha": "a415cc777520c780", "t_end": 1791522583.6062517} {"ep": "ok-00034", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9361, "status": "ok", "correct": true, "speedup": 0.9361, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 102.0, "calls": 2, "tokens_in": 16862, "tokens_out": 4883, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791522585.3082094} {"ep": "ok-00042", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 113.2, "calls": 5, "tokens_in": 42878, "tokens_out": 3820, "ctx_chars": 12555, "ctx_sha": "fb438aa3b57cd542", "t_end": 1791522596.5242388} {"ep": "ok-00038", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.996, "status": "ok", "correct": true, "speedup": 0.996, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 116.5, "calls": 3, "tokens_in": 8360, "tokens_out": 3020, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522599.7578523} {"ep": "ok-00069", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0329, "status": "ok", "correct": true, "speedup": 1.0329, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.9, "calls": 3, "tokens_in": 25445, "tokens_out": 2793, "ctx_chars": 12848, "ctx_sha": "98fb6b45b82f188b", "t_end": 1791522601.073693} {"ep": "ok-00007", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-d10f50ba0c", "pit-69809d3cb6", "rec-21ef38357b"], "p_item": null, "p_policy": null, "success": false, "score": 0.9395, "status": "ok", "correct": true, "speedup": 0.9395, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 128.0, "calls": 2, "tokens_in": 6846, "tokens_out": 5231, "ctx_chars": 1383, "ctx_sha": "680ebcf2a2f1ebf3", "t_end": 1791522611.2329173} {"ep": "ok-00065", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": true, "score": 1.0207, "status": "ok", "correct": true, "speedup": 1.0207, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 103.8, "calls": 3, "tokens_in": 28934, "tokens_out": 2927, "ctx_chars": 15603, "ctx_sha": "a415cc777520c780", "t_end": 1791522620.1396494} {"ep": "ok-00010", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 146.3, "calls": 1, "tokens_in": 1876, "tokens_out": 2072, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522629.5449462} {"ep": "ok-00041", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "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": 148.5, "calls": 3, "tokens_in": 9756, "tokens_out": 6295, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791522631.7567506} {"ep": "ok-00050", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 1.0917, "status": "ok", "correct": true, "speedup": 1.0917, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 156.8, "calls": 3, "tokens_in": 17132, "tokens_out": 5661, "ctx_chars": 2922, "ctx_sha": "3cb6e9a4694064be", "t_end": 1791522640.0748832} {"ep": "ok-00024", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 55.4127, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 157.5, "calls": 2, "tokens_in": 7908, "tokens_out": 7550, "ctx_chars": 2016, "ctx_sha": "a2bb82d0a90ca3de", "t_end": 1791522640.8244386} {"ep": "ok-00078", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0388, "status": "ok", "correct": true, "speedup": 1.0388, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 73.8, "calls": 2, "tokens_in": 5279, "tokens_out": 3199, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522641.5607755} {"ep": "ok-00009", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 35.1807, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 160.8, "calls": 2, "tokens_in": 6705, "tokens_out": 6586, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522644.1083026} {"ep": "ok-00051", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7685, "status": "ok", "correct": true, "speedup": 0.7685, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 179.8, "calls": 5, "tokens_in": 51261, "tokens_out": 9338, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791522663.0905032} {"ep": "ok-00013", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 86.1153, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 188.6, "calls": 2, "tokens_in": 8456, "tokens_out": 8258, "ctx_chars": 2016, "ctx_sha": "a2bb82d0a90ca3de", "t_end": 1791522671.8618617} {"ep": "ok-00075", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "p_item": null, "p_policy": null, "success": false, "score": 0.991, "status": "ok", "correct": true, "speedup": 0.991, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 124.1, "calls": 3, "tokens_in": 17718, "tokens_out": 3169, "ctx_chars": 7333, "ctx_sha": "42fc92cfe0f03f33", "t_end": 1791522680.8328228} {"ep": "ok-00011", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'lse_mish_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=lse_mish_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": 206.3, "calls": 1, "tokens_in": 1933, "tokens_out": 1684, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522689.5801542} {"ep": "ok-00020", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0739, "status": "ok", "correct": true, "speedup": 1.0739, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 209.8, "calls": 1, "tokens_in": 7684, "tokens_out": 1137, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791522693.0847788} {"ep": "ok-00049", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.035, "status": "ok", "correct": true, "speedup": 1.035, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 211.9, "calls": 2, "tokens_in": 7098, "tokens_out": 7724, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522695.1831071} {"ep": "ok-00084", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 97.4, "calls": 2, "tokens_in": 13589, "tokens_out": 1838, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791522697.1168} {"ep": "ok-00002", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8215, "status": "ok", "correct": true, "speedup": 0.8215, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 214.6, "calls": 2, "tokens_in": 162511, "tokens_out": 6717, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522697.9005919} {"ep": "ok-00082", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 23.7981, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 115.5, "calls": 2, "tokens_in": 14893, "tokens_out": 5763, "ctx_chars": 10255, "ctx_sha": "359838044746c0df", "t_end": 1791522700.8173614} {"ep": "ok-00029", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9351, "status": "ok", "correct": true, "speedup": 0.9351, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 217.6, "calls": 2, "tokens_in": 160423, "tokens_out": 4606, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522700.9219406} {"ep": "ok-00004", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 76.1003, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 220.8, "calls": 2, "tokens_in": 6942, "tokens_out": 8114, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522704.0354419} {"ep": "ok-00063", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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 'gn_hardtanh_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_hardtanh_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/inclu", "wall_s": 221.3, "calls": 1, "tokens_in": 1723, "tokens_out": 1780, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522704.6368701} {"ep": "ok-00017", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4589, "status": "ok", "correct": true, "speedup": 0.4589, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 231.5, "calls": 3, "tokens_in": 23927, "tokens_out": 20161, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522714.7605784} {"ep": "ok-00044", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9427, "status": "ok", "correct": true, "speedup": 0.9427, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 233.0, "calls": 5, "tokens_in": 60912, "tokens_out": 13536, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791522716.2842076} {"ep": "ok-00012", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.037, "status": "ok", "correct": true, "speedup": 1.037, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 237.2, "calls": 2, "tokens_in": 15548, "tokens_out": 2556, "ctx_chars": 12848, "ctx_sha": "c5005fba182a16d4", "t_end": 1791522720.5077996} {"ep": "ok-00045", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.4909, "status": "ok", "correct": true, "speedup": 0.4909, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 237.5, "calls": 2, "tokens_in": 11874, "tokens_out": 21051, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522720.8523319} {"ep": "ok-00081", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.035, "status": "ok", "correct": true, "speedup": 1.035, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 138.5, "calls": 3, "tokens_in": 21688, "tokens_out": 2739, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791522722.0662642} {"ep": "ok-00037", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 259.0, "calls": 2, "tokens_in": 163517, "tokens_out": 11977, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522742.3147037} {"ep": "ok-00027", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9826, "status": "ok", "correct": true, "speedup": 0.9826, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 260.6, "calls": 2, "tokens_in": 163376, "tokens_out": 11696, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522743.9129663} {"ep": "ok-00039", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.7661, "status": "ok", "correct": true, "speedup": 0.7661, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 261.5, "calls": 4, "tokens_in": 36018, "tokens_out": 20050, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522744.8177345} {"ep": "ok-00016", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0022, "status": "ok", "correct": true, "speedup": 1.0022, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 263.4, "calls": 5, "tokens_in": 405403, "tokens_out": 5861, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522746.64231} {"ep": "ok-00061", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 6.5371, "status": "ok", "correct": true, "speedup": 6.5371, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 263.9, "calls": 2, "tokens_in": 12557, "tokens_out": 20562, "ctx_chars": 2713, "ctx_sha": "d18291fca1598bb8", "t_end": 1791522747.2071915} {"ep": "ok-00062", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "p_item": null, "p_policy": null, "success": true, "score": 1.0286, "status": "ok", "correct": true, "speedup": 1.0286, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 288.2, "calls": 2, "tokens_in": 5430, "tokens_out": 2628, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791522771.5343864} {"ep": "ok-00102", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0232, "status": "ok", "correct": true, "speedup": 1.0232, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 71.0, "calls": 3, "tokens_in": 20053, "tokens_out": 1834, "ctx_chars": 9950, "ctx_sha": "cbff30e3b5d0d366", "t_end": 1791522771.8113716} {"ep": "ok-00073", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 1.005, "status": "ok", "correct": true, "speedup": 1.005, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 229.0, "calls": 2, "tokens_in": 15306, "tokens_out": 5540, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791522775.8172796} {"ep": "ok-00083", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.549, "status": "ok", "correct": true, "speedup": 0.549, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 199.1, "calls": 2, "tokens_in": 13575, "tokens_out": 9667, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791522795.584123} {"ep": "ok-00000", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2525, "status": "ok", "correct": true, "speedup": 1.2525, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 314.1, "calls": 2, "tokens_in": 12588, "tokens_out": 21942, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522797.3774645} {"ep": "ok-00028", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8989, "status": "ok", "correct": true, "speedup": 0.8989, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 323.8, "calls": 5, "tokens_in": 55478, "tokens_out": 12132, "ctx_chars": 5802, "ctx_sha": "c3f789aa6f5dcf18", "t_end": 1791522807.1079402} {"ep": "ok-00074", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0899, "status": "ok", "correct": true, "speedup": 1.0899, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 260.9, "calls": 3, "tokens_in": 25395, "tokens_out": 2057, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791522816.308095} {"ep": "ok-00086", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "p_item": null, "p_policy": null, "success": true, "score": 1.0242, "status": "ok", "correct": true, "speedup": 1.0242, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 208.6, "calls": 3, "tokens_in": 12634, "tokens_out": 1854, "ctx_chars": 4565, "ctx_sha": "77e8064d2cc468b9", "t_end": 1791522819.821208} {"ep": "ok-00080", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.7994, "status": "ok", "correct": true, "speedup": 0.7994, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 246.6, "calls": 2, "tokens_in": 11904, "tokens_out": 1344, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791522820.8988988} {"ep": "ok-00057", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 10.7045, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 363.1, "calls": 3, "tokens_in": 29485, "tokens_out": 22752, "ctx_chars": 7992, "ctx_sha": "03c04da8eac89804", "t_end": 1791522846.4371994} {"ep": "ok-00015", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4471, "status": "ok", "correct": true, "speedup": 1.4471, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 366.4, "calls": 2, "tokens_in": 12605, "tokens_out": 24687, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522849.707731} {"ep": "ok-00112", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "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": 107.1, "calls": 3, "tokens_in": 25357, "tokens_out": 2718, "ctx_chars": 12848, "ctx_sha": "98fb6b45b82f188b", "t_end": 1791522850.978513} {"ep": "ok-00093", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.1016, "status": "ok", "correct": true, "speedup": 1.1016, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 211.3, "calls": 3, "tokens_in": 22803, "tokens_out": 2119, "ctx_chars": 11064, "ctx_sha": "f8d570b75c61820c", "t_end": 1791522855.3646047} {"ep": "ok-00098", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 24.9015, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 164.7, "calls": 2, "tokens_in": 20564, "tokens_out": 7519, "ctx_chars": 16078, "ctx_sha": "7102bc51b235fd0f", "t_end": 1791522857.7811618} {"ep": "ok-00111", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'gn_ht_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-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": 124.3, "calls": 1, "tokens_in": 1856, "tokens_out": 1820, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522866.5712187} {"ep": "ok-00103", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0336, "status": "ok", "correct": true, "speedup": 1.0336, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 174.9, "calls": 3, "tokens_in": 17335, "tokens_out": 2665, "ctx_chars": 6481, "ctx_sha": "2281995c87ed0a4b", "t_end": 1791522875.7793238} {"ep": "ok-00107", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0265, "status": "ok", "correct": true, "speedup": 1.0265, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 164.5, "calls": 2, "tokens_in": 4712, "tokens_out": 2341, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522880.8128936} {"ep": "ok-00101", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 187.0, "calls": 3, "tokens_in": 26080, "tokens_out": 2925, "ctx_chars": 14186, "ctx_sha": "81f894fa6f6eba57", "t_end": 1791522884.8996856} {"ep": "ok-00113", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "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": 151.8, "calls": 2, "tokens_in": 7211, "tokens_out": 4954, "ctx_chars": 2175, "ctx_sha": "86963271ef726410", "t_end": 1791522896.6250224} {"ep": "ok-00095", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.7683, "status": "ok", "correct": true, "speedup": 0.7683, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 231.2, "calls": 3, "tokens_in": 10515, "tokens_out": 1761, "ctx_chars": 2270, "ctx_sha": "cbeec28bae225a7b", "t_end": 1791522903.0664494} {"ep": "ok-00123", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.025, "status": "ok", "correct": true, "speedup": 1.025, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 84.4, "calls": 3, "tokens_in": 20940, "tokens_out": 1844, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791522904.2459195} {"ep": "ok-00097", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.1575, "status": "ok", "correct": true, "speedup": 0.1575, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 217.9, "calls": 4, "tokens_in": 31254, "tokens_out": 4804, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791522907.4362538} {"ep": "ok-00109", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.2961, "status": "ok", "correct": true, "speedup": 0.2961, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 187.8, "calls": 3, "tokens_in": 20908, "tokens_out": 4210, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791522908.6228547} {"ep": "ok-00064", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 7.2251, "status": "ok", "correct": true, "speedup": 7.2251, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 413.9, "calls": 3, "tokens_in": 19730, "tokens_out": 20463, "ctx_chars": 696, "ctx_sha": "4047841f6f5065d2", "t_end": 1791522913.9848776} {"ep": "ok-00115", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.2954, "status": "ok", "correct": true, "speedup": 0.2954, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 169.8, "calls": 3, "tokens_in": 19883, "tokens_out": 4115, "ctx_chars": 6059, "ctx_sha": "fcbd714fceba4ac3", "t_end": 1791522916.9843318} {"ep": "ok-00056", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.9022, "status": "ok", "correct": true, "speedup": 5.9022, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 448.3, "calls": 3, "tokens_in": 30029, "tokens_out": 23860, "ctx_chars": 7644, "ctx_sha": "1bcf1308b5ca023c", "t_end": 1791522931.5927923} {"ep": "ok-00108", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4"], "p_item": null, "p_policy": null, "success": true, "score": 1.0341, "status": "ok", "correct": true, "speedup": 1.0341, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 213.3, "calls": 2, "tokens_in": 11758, "tokens_out": 4582, "ctx_chars": 7221, "ctx_sha": "c76ebe5823d3165a", "t_end": 1791522933.8262377} {"ep": "ok-00094", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7912, "status": "ok", "correct": true, "speedup": 0.7912, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 271.9, "calls": 3, "tokens_in": 16721, "tokens_out": 5295, "ctx_chars": 2169, "ctx_sha": "4663d45691d76c7e", "t_end": 1791522934.9558518} {"ep": "ok-00088", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.4971, "status": "ok", "correct": true, "speedup": 1.4971, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 308.5, "calls": 4, "tokens_in": 51070, "tokens_out": 12877, "ctx_chars": 16078, "ctx_sha": "7102bc51b235fd0f", "t_end": 1791522938.0846882} {"ep": "ok-00066", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 9.9371, "status": "ok", "correct": true, "speedup": 9.9371, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 418.5, "calls": 2, "tokens_in": 164618, "tokens_out": 22649, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522939.2285764} {"ep": "ok-00085", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.0375, "status": "ok", "correct": true, "speedup": 7.0375, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 340.3, "calls": 2, "tokens_in": 6730, "tokens_out": 9342, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522941.341395} {"ep": "ok-00067", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 417.6, "calls": 2, "tokens_in": 12097, "tokens_out": 4845, "ctx_chars": 7549, "ctx_sha": "f0881682a422c1e8", "t_end": 1791522947.4143362} {"ep": "ok-00054", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "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": 468.5, "calls": 4, "tokens_in": 17875, "tokens_out": 9878, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791522951.7802815} {"ep": "ok-00035", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 6.7208, "status": "ok", "correct": true, "speedup": 6.7208, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 469.8, "calls": 3, "tokens_in": 28517, "tokens_out": 31708, "ctx_chars": 2713, "ctx_sha": "d18291fca1598bb8", "t_end": 1791522953.0926604} {"ep": "ok-00033", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 472.4, "calls": 4, "tokens_in": 322583, "tokens_out": 10962, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522955.6919262} {"ep": "ok-00001", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 7.6973, "status": "ok", "correct": true, "speedup": 7.6973, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 474.4, "calls": 3, "tokens_in": 21415, "tokens_out": 27334, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522957.6962829} {"ep": "ok-00070", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": false, "score": 0.9988, "status": "ok", "correct": true, "speedup": 0.9988, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 435.4, "calls": 5, "tokens_in": 42825, "tokens_out": 3545, "ctx_chars": 12555, "ctx_sha": "fb438aa3b57cd542", "t_end": 1791522968.030196} {"ep": "ok-00140", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 54.4, "calls": 1, "tokens_in": 5935, "tokens_out": 3000, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791522971.3834198} {"ep": "ok-00134", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0928, "status": "ok", "correct": true, "speedup": 1.0928, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 75.9, "calls": 1, "tokens_in": 7259, "tokens_out": 1085, "ctx_chars": 12103, "ctx_sha": "42cb8c90d2cfce7e", "t_end": 1791522972.5072634} {"ep": "ok-00032", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9925, "status": "ok", "correct": true, "speedup": 0.9925, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 493.1, "calls": 4, "tokens_in": 335688, "tokens_out": 13649, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791522976.4149857} {"ep": "ok-00122", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9491, "status": "ok", "correct": true, "speedup": 0.9491, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 161.2, "calls": 1, "tokens_in": 2489, "tokens_out": 4195, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791522977.4952312} {"ep": "ok-00133", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff"], "p_item": null, "p_policy": null, "success": true, "score": 1.0359, "status": "ok", "correct": true, "speedup": 1.0359, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 93.3, "calls": 2, "tokens_in": 10088, "tokens_out": 2570, "ctx_chars": 5518, "ctx_sha": "7180f8dff0056426", "t_end": 1791522978.2448797} {"ep": "ok-00125", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9384, "status": "ok", "correct": true, "speedup": 0.9384, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 132.1, "calls": 2, "tokens_in": 19313, "tokens_out": 5357, "ctx_chars": 15603, "ctx_sha": "3f3a125c98fd04bf", "t_end": 1791522978.4902904} {"ep": "ok-00092", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "p_item": null, "p_policy": null, "success": true, "score": 1.0351, "status": "ok", "correct": true, "speedup": 1.0351, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 339.6, "calls": 4, "tokens_in": 19672, "tokens_out": 2852, "ctx_chars": 3968, "ctx_sha": "1e8d83b857da86fb", "t_end": 1791522981.1291213} {"ep": "ok-00099", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 286.4, "calls": 4, "tokens_in": 36052, "tokens_out": 9421, "ctx_chars": 12555, "ctx_sha": "bae97e8db7be5c58", "t_end": 1791522981.5669618} {"ep": "ok-00106", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.2954, "status": "ok", "correct": true, "speedup": 0.2954, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 268.5, "calls": 3, "tokens_in": 20075, "tokens_out": 4108, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791522983.2637372} {"ep": "ok-00072", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 451.2, "calls": 4, "tokens_in": 35812, "tokens_out": 8147, "ctx_chars": 12555, "ctx_sha": "bae97e8db7be5c58", "t_end": 1791522984.7466664} {"ep": "ok-00079", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8274c30657", "rec-4365468e5f", "ker-6558b83d05"], "p_item": null, "p_policy": null, "success": false, "score": 1.0002, "status": "ok", "correct": true, "speedup": 1.0002, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 431.1, "calls": 5, "tokens_in": 28095, "tokens_out": 3471, "ctx_chars": 5534, "ctx_sha": "3d72d551b52c403d", "t_end": 1791522999.7391472} {"ep": "ok-00104", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0395, "status": "ok", "correct": true, "speedup": 1.0395, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 299.0, "calls": 3, "tokens_in": 8309, "tokens_out": 2468, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523003.040992} {"ep": "ok-00128", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7745, "status": "ok", "correct": true, "speedup": 0.7745, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 149.1, "calls": 4, "tokens_in": 36194, "tokens_out": 7164, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523004.4703286} {"ep": "ok-00087", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1023, "status": "ok", "correct": true, "speedup": 1.1023, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 387.1, "calls": 4, "tokens_in": 20474, "tokens_out": 5448, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523007.2303874} {"ep": "ok-00130", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 84.1522, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 146.5, "calls": 2, "tokens_in": 6647, "tokens_out": 7073, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523013.0221066} {"ep": "ok-00090", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9598, "status": "ok", "correct": true, "speedup": 0.9598, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 377.7, "calls": 4, "tokens_in": 21049, "tokens_out": 5768, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523017.7976906} {"ep": "ok-00119", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0271, "status": "ok", "correct": true, "speedup": 1.0271, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 226.4, "calls": 2, "tokens_in": 10840, "tokens_out": 2494, "ctx_chars": 7159, "ctx_sha": "1ccf94064353eca4", "t_end": 1791523021.9854088} {"ep": "ok-00139", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0247, "status": "ok", "correct": true, "speedup": 1.0247, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 108.8, "calls": 1, "tokens_in": 6268, "tokens_out": 945, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791523022.737189} {"ep": "ok-00068", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.3374, "status": "ok", "correct": true, "speedup": 7.3374, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 495.3, "calls": 4, "tokens_in": 48753, "tokens_out": 36328, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523025.7809284} {"ep": "ok-00116", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.994, "status": "ok", "correct": true, "speedup": 0.994, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 256.9, "calls": 3, "tokens_in": 9874, "tokens_out": 4626, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523028.4595702} {"ep": "ok-00143", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 93.7, "calls": 3, "tokens_in": 21074, "tokens_out": 1940, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791523028.6628232} {"ep": "ok-00126", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0346, "status": "ok", "correct": true, "speedup": 1.0346, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 179.1, "calls": 4, "tokens_in": 11178, "tokens_out": 2398, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523028.8122659} {"ep": "ok-00142", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3038, "status": "ok", "correct": true, "speedup": 0.3038, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 97.7, "calls": 3, "tokens_in": 23361, "tokens_out": 4210, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791523031.5237832} {"ep": "ok-00031", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.9579, "status": "ok", "correct": true, "speedup": 5.9579, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 550.1, "calls": 3, "tokens_in": 31155, "tokens_out": 36193, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523033.4432817} {"ep": "ok-00144", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0285, "status": "ok", "correct": true, "speedup": 1.0285, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 95.4, "calls": 2, "tokens_in": 13807, "tokens_out": 2063, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791523033.4849708} {"ep": "ok-00096", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9787, "status": "ok", "correct": true, "speedup": 0.9787, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 353.0, "calls": 2, "tokens_in": 159076, "tokens_out": 4486, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523033.7887454} {"ep": "ok-00150", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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_pool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_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", "wall_s": 80.9, "calls": 1, "tokens_in": 1960, "tokens_out": 1730, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523036.555237} {"ep": "ok-00077", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 9.3504, "status": "ok", "correct": true, "speedup": 9.3504, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 476.8, "calls": 3, "tokens_in": 28101, "tokens_out": 21760, "ctx_chars": 7992, "ctx_sha": "03c04da8eac89804", "t_end": 1791523041.618948} {"ep": "ok-00138", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 139.5, "calls": 1, "tokens_in": 2759, "tokens_out": 5292, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523048.1433172} {"ep": "ok-00166", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 42.0, "calls": 1, "tokens_in": 2759, "tokens_out": 4107, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523049.2164626} {"ep": "ok-00153", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.009, "status": "ok", "correct": true, "speedup": 1.009, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 81.9, "calls": 2, "tokens_in": 5518, "tokens_out": 5797, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523053.2461011} {"ep": "ok-00105", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 9.8036, "status": "ok", "correct": true, "speedup": 9.8036, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 348.7, "calls": 3, "tokens_in": 18847, "tokens_out": 19996, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523053.3700314} {"ep": "ok-00048", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.007, "status": "ok", "correct": true, "speedup": 0.007, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 572.6, "calls": 3, "tokens_in": 250148, "tokens_out": 11729, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523055.8733585} {"ep": "ok-00114", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4889, "status": "ok", "correct": true, "speedup": 1.4889, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 309.3, "calls": 2, "tokens_in": 160303, "tokens_out": 13215, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523055.9335449} {"ep": "ok-00117", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 285.0, "calls": 2, "tokens_in": 158478, "tokens_out": 7265, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523056.846335} {"ep": "ok-00022", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "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": 574.8, "calls": 3, "tokens_in": 10228, "tokens_out": 6854, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791523058.1362948} {"ep": "ok-00089", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9032, "status": "ok", "correct": true, "speedup": 0.9032, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 427.9, "calls": 4, "tokens_in": 34090, "tokens_out": 16100, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523059.6730924} {"ep": "ok-00025", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7389, "status": "ok", "correct": true, "speedup": 0.7389, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 576.9, "calls": 3, "tokens_in": 28405, "tokens_out": 14270, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791523060.231266} {"ep": "ok-00091", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 6.3443, "status": "ok", "correct": true, "speedup": 6.3443, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 427.3, "calls": 2, "tokens_in": 13497, "tokens_out": 24213, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791523068.1160061} {"ep": "ok-00132", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7471, "status": "ok", "correct": true, "speedup": 0.7471, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 193.0, "calls": 4, "tokens_in": 37474, "tokens_out": 7089, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791523073.7756135} {"ep": "ok-00152", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "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": 105.8, "calls": 2, "tokens_in": 6090, "tokens_out": 4949, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791523073.8059404} {"ep": "ok-00127", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.6665, "status": "ok", "correct": true, "speedup": 0.6665, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 229.0, "calls": 2, "tokens_in": 13954, "tokens_out": 9598, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523079.9593163} {"ep": "ok-00110", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8087, "status": "ok", "correct": true, "speedup": 0.8087, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 367.3, "calls": 2, "tokens_in": 163375, "tokens_out": 15331, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523089.4103184} {"ep": "ok-00156", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 126.5, "calls": 2, "tokens_in": 12059, "tokens_out": 5338, "ctx_chars": 7549, "ctx_sha": "f0881682a422c1e8", "t_end": 1791523103.9782429} {"ep": "ok-00052", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 6.923, "status": "ok", "correct": true, "speedup": 6.923, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 621.2, "calls": 4, "tokens_in": 48322, "tokens_out": 37910, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523104.5045383} {"ep": "ok-00164", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 103.9, "calls": 3, "tokens_in": 25195, "tokens_out": 2849, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791523106.9004986} {"ep": "ok-00160", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9947, "status": "ok", "correct": true, "speedup": 0.9947, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 146.8, "calls": 3, "tokens_in": 22197, "tokens_out": 2755, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791523128.3339283} {"ep": "ok-00100", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7431, "status": "ok", "correct": true, "speedup": 0.7431, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 431.8, "calls": 4, "tokens_in": 41290, "tokens_out": 10400, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791523128.952004} {"ep": "ok-00175", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8177, "status": "ok", "correct": true, "speedup": 0.8177, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 98.3, "calls": 2, "tokens_in": 12647, "tokens_out": 4574, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523129.8552778} {"ep": "ok-00163", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.265, "status": "ok", "correct": true, "speedup": 0.265, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 131.5, "calls": 3, "tokens_in": 20968, "tokens_out": 4228, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791523131.2796504} {"ep": "ok-00076", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 5.6876, "status": "ok", "correct": true, "speedup": 5.6876, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 568.5, "calls": 3, "tokens_in": 28531, "tokens_out": 19612, "ctx_chars": 7992, "ctx_sha": "03c04da8eac89804", "t_end": 1791523131.2898655} {"ep": "ok-00023", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 7.5814, "status": "ok", "correct": true, "speedup": 7.5814, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 650.4, "calls": 3, "tokens_in": 28235, "tokens_out": 35531, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523133.6972919} {"ep": "ok-00179", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0307, "status": "ok", "correct": true, "speedup": 1.0307, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 98.7, "calls": 2, "tokens_in": 13204, "tokens_out": 2590, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791523135.2469788} {"ep": "ok-00188", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'gn_ht_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht_mod -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-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": 87.1, "calls": 1, "tokens_in": 1856, "tokens_out": 1824, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523145.1887238} {"ep": "ok-00176", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": true, "score": 1.0155, "status": "ok", "correct": true, "speedup": 1.0155, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 127.2, "calls": 3, "tokens_in": 22555, "tokens_out": 2919, "ctx_chars": 10528, "ctx_sha": "2d3203f47b184251", "t_end": 1791523160.6705284} {"ep": "ok-00193", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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_pool_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_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", "wall_s": 97.4, "calls": 1, "tokens_in": 1827, "tokens_out": 1673, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523171.1731732} {"ep": "ok-00177", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.426, "status": "ok", "correct": true, "speedup": 1.426, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 142.5, "calls": 2, "tokens_in": 6030, "tokens_out": 6218, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523176.02505} {"ep": "ok-00178", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.1279, "status": "ok", "correct": true, "speedup": 0.1279, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 143.2, "calls": 3, "tokens_in": 23828, "tokens_out": 5013, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791523177.0280128} {"ep": "ok-00196", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7446, "status": "ok", "correct": true, "speedup": 0.7446, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 73.2, "calls": 2, "tokens_in": 13401, "tokens_out": 4714, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523177.139953} {"ep": "ok-00203", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0369, "status": "ok", "correct": true, "speedup": 1.0369, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 47.9, "calls": 2, "tokens_in": 10043, "tokens_out": 2542, "ctx_chars": 5984, "ctx_sha": "f178e5e79419791a", "t_end": 1791523179.1592295} {"ep": "ok-00053", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285"], "p_item": null, "p_policy": null, "success": true, "score": 6.6474, "status": "ok", "correct": true, "speedup": 6.6474, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 698.0, "calls": 3, "tokens_in": 27614, "tokens_out": 33190, "ctx_chars": 369, "ctx_sha": "92409fabb91e61c8", "t_end": 1791523181.292775} {"ep": "ok-00131", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 73.0958, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 307.8, "calls": 2, "tokens_in": 7133, "tokens_out": 7944, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523183.5434299} {"ep": "ok-00135", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 298.7, "calls": 3, "tokens_in": 242271, "tokens_out": 6826, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523201.8110013} {"ep": "ok-00172", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "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": 187.1, "calls": 2, "tokens_in": 16334, "tokens_out": 2939, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791523215.577902} {"ep": "ok-00157", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.4197, "status": "ok", "correct": true, "speedup": 1.4197, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 240.0, "calls": 2, "tokens_in": 6229, "tokens_out": 6330, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523218.247179} {"ep": "ok-00149", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 268.7, "calls": 5, "tokens_in": 36500, "tokens_out": 3779, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791523221.8165202} {"ep": "ok-00190", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0346, "status": "ok", "correct": true, "speedup": 1.0346, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 170.4, "calls": 2, "tokens_in": 10960, "tokens_out": 2720, "ctx_chars": 6481, "ctx_sha": "2281995c87ed0a4b", "t_end": 1791523230.6049516} {"ep": "ok-00118", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 1.0026, "status": "ok", "correct": true, "speedup": 1.0026, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 457.3, "calls": 4, "tokens_in": 16587, "tokens_out": 8429, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523233.1640453} {"ep": "ok-00120", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.9082, "status": "ok", "correct": true, "speedup": 7.9082, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 446.7, "calls": 3, "tokens_in": 250903, "tokens_out": 26858, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523244.1212616} {"ep": "ok-00186", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.9846, "status": "ok", "correct": true, "speedup": 0.9846, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 192.2, "calls": 2, "tokens_in": 11646, "tokens_out": 3106, "ctx_chars": 7758, "ctx_sha": "ae9fa76cd68a90a1", "t_end": 1791523248.1240866} {"ep": "ok-00187", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.946, "status": "ok", "correct": true, "speedup": 0.946, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 194.5, "calls": 4, "tokens_in": 35004, "tokens_out": 6627, "ctx_chars": 5802, "ctx_sha": "c3f789aa6f5dcf18", "t_end": 1791523251.3033795} {"ep": "ok-00171", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0329, "status": "ok", "correct": true, "speedup": 1.0329, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 230.8, "calls": 2, "tokens_in": 13614, "tokens_out": 4475, "ctx_chars": 8788, "ctx_sha": "796f186ac3130710", "t_end": 1791523256.6291919} {"ep": "ok-00169", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 41.4114, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 242.6, "calls": 2, "tokens_in": 15085, "tokens_out": 6122, "ctx_chars": 10255, "ctx_sha": "359838044746c0df", "t_end": 1791523264.5830202} {"ep": "ok-00198", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 1.0386, "status": "ok", "correct": true, "speedup": 1.0386, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 158.2, "calls": 2, "tokens_in": 7323, "tokens_out": 4812, "ctx_chars": 2175, "ctx_sha": "86963271ef726410", "t_end": 1791523265.1355445} {"ep": "ok-00173", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0293, "status": "ok", "correct": true, "speedup": 1.0293, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 244.1, "calls": 2, "tokens_in": 13655, "tokens_out": 4349, "ctx_chars": 8788, "ctx_sha": "796f186ac3130710", "t_end": 1791523272.7233534} {"ep": "ok-00008", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0842, "status": "ok", "correct": true, "speedup": 1.0842, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 808.6, "calls": 4, "tokens_in": 43727, "tokens_out": 25783, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523291.8509932} {"ep": "ok-00124", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.569, "status": "ok", "correct": true, "speedup": 1.569, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 477.0, "calls": 4, "tokens_in": 329930, "tokens_out": 15544, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523297.8715723} {"ep": "ok-00162", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "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": 313.3, "calls": 2, "tokens_in": 6581, "tokens_out": 6026, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791523298.0796454} {"ep": "ok-00167", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 297.3, "calls": 2, "tokens_in": 159198, "tokens_out": 4786, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523310.3204117} {"ep": "ok-00185", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "no_custom_kernel", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "none of the candidate's kernels ['relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "wall_s": 254.5, "calls": 1, "tokens_in": 2626, "tokens_out": 4228, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523310.3492928} {"ep": "ok-00206", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-e75be99f9e", "ker-071e045dd4"], "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": 172.2, "calls": 3, "tokens_in": 18316, "tokens_out": 2926, "ctx_chars": 7245, "ctx_sha": "5c9cac21cf11798f", "t_end": 1791523317.4335222} {"ep": "ok-00148", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.0777, "status": "ok", "correct": true, "speedup": 0.0777, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 366.8, "calls": 4, "tokens_in": 20066, "tokens_out": 6904, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523318.6084933} {"ep": "ok-00071", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8607, "status": "ok", "correct": true, "speedup": 0.8607, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 789.9, "calls": 4, "tokens_in": 59539, "tokens_out": 29197, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791523322.691258} {"ep": "ok-00210", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.2283, "status": "ok", "correct": true, "speedup": 0.2283, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 154.9, "calls": 3, "tokens_in": 20224, "tokens_out": 4232, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791523331.9547932} {"ep": "ok-00211", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 155.1, "calls": 3, "tokens_in": 22410, "tokens_out": 2950, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791523332.2331507} {"ep": "ok-00207", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7664, "status": "ok", "correct": true, "speedup": 0.7664, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 173.1, "calls": 2, "tokens_in": 13581, "tokens_out": 5820, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523333.7692404} {"ep": "ok-00194", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0319, "status": "ok", "correct": true, "speedup": 1.0319, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 255.4, "calls": 2, "tokens_in": 5663, "tokens_out": 4899, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523335.4049542} {"ep": "ok-00136", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.009, "status": "ok", "correct": true, "speedup": 1.009, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 443.4, "calls": 4, "tokens_in": 26426, "tokens_out": 8995, "ctx_chars": 5630, "ctx_sha": "1d3288f4ac875b68", "t_end": 1791523347.596343} {"ep": "ok-00168", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 335.8, "calls": 2, "tokens_in": 10035, "tokens_out": 2702, "ctx_chars": 5984, "ctx_sha": "f178e5e79419791a", "t_end": 1791523353.5884755} {"ep": "ok-00151", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0008, "status": "ok", "correct": true, "speedup": 1.0008, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 396.9, "calls": 5, "tokens_in": 42402, "tokens_out": 5568, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791523354.5776508} {"ep": "ok-00145", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8424, "status": "ok", "correct": true, "speedup": 0.8424, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 416.6, "calls": 2, "tokens_in": 13203, "tokens_out": 6168, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791523355.8713827} {"ep": "ok-00208", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.7923, "status": "ok", "correct": true, "speedup": 0.7923, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 185.4, "calls": 2, "tokens_in": 6379, "tokens_out": 1618, "ctx_chars": 1993, "ctx_sha": "e81d6bc04df8963f", "t_end": 1791523356.601385} {"ep": "ok-00195", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.0942, "status": "ok", "correct": true, "speedup": 0.0942, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 268.7, "calls": 3, "tokens_in": 21093, "tokens_out": 3977, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791523358.1396544} {"ep": "ok-00129", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "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": 503.3, "calls": 5, "tokens_in": 22763, "tokens_out": 8571, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791523361.0741527} {"ep": "ok-00121", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 11.3442, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 556.4, "calls": 3, "tokens_in": 261535, "tokens_out": 41449, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523363.4586294} {"ep": "ok-00174", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.936, "status": "ok", "correct": true, "speedup": 0.936, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 343.6, "calls": 2, "tokens_in": 19451, "tokens_out": 5761, "ctx_chars": 15603, "ctx_sha": "3f3a125c98fd04bf", "t_end": 1791523372.419432} {"ep": "ok-00225", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-4cfeee51c1", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 1.1666, "status": "ok", "correct": true, "speedup": 1.1666, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 110.7, "calls": 3, "tokens_in": 13686, "tokens_out": 3854, "ctx_chars": 1884, "ctx_sha": "a37a18ff81bf7ac3", "t_end": 1791523375.325506} {"ep": "ok-00233", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 65.5, "calls": 1, "tokens_in": 1814, "tokens_out": 756, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523382.9582646} {"ep": "ok-00199", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 8.057, "status": "ok", "correct": true, "speedup": 8.057, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 258.3, "calls": 2, "tokens_in": 12093, "tokens_out": 21450, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523386.6458397} {"ep": "ok-00183", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5701, "status": "ok", "correct": true, "speedup": 1.5701, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 333.5, "calls": 2, "tokens_in": 159252, "tokens_out": 10271, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523386.6969836} {"ep": "ok-00234", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2988, "status": "ok", "correct": true, "speedup": 0.2988, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 69.9, "calls": 1, "tokens_in": 5329, "tokens_out": 2119, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523388.509498} {"ep": "ok-00158", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.8996, "status": "ok", "correct": true, "speedup": 0.8996, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 410.5, "calls": 3, "tokens_in": 16674, "tokens_out": 5611, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791523388.995004} {"ep": "ok-00180", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0273, "status": "ok", "correct": true, "speedup": 1.0273, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 351.5, "calls": 2, "tokens_in": 6048, "tokens_out": 5598, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523393.1516442} {"ep": "ok-00155", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 7.6699, "status": "ok", "correct": true, "speedup": 7.6699, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 423.4, "calls": 3, "tokens_in": 33451, "tokens_out": 28392, "ctx_chars": 10587, "ctx_sha": "bc692baaaeca6a2f", "t_end": 1791523399.796201} {"ep": "ok-00227", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9878, "status": "ok", "correct": true, "speedup": 0.9878, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 128.1, "calls": 1, "tokens_in": 1743, "tokens_out": 1603, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523400.811481} {"ep": "ok-00231", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "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": 93.8, "calls": 2, "tokens_in": 13109, "tokens_out": 5977, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523404.1633108} {"ep": "ok-00146", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 462.9, "calls": 4, "tokens_in": 27594, "tokens_out": 9438, "ctx_chars": 5630, "ctx_sha": "1d3288f4ac875b68", "t_end": 1791523404.2004766} {"ep": "ok-00209", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0332, "status": "ok", "correct": true, "speedup": 1.0332, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 228.2, "calls": 2, "tokens_in": 5118, "tokens_out": 2994, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523404.2517445} {"ep": "ok-00147", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "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": 457.9, "calls": 3, "tokens_in": 25433, "tokens_out": 2996, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791523405.3343008} {"ep": "ok-00220", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7625, "status": "ok", "correct": true, "speedup": 0.7625, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 178.6, "calls": 3, "tokens_in": 250628, "tokens_out": 10151, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523411.7702777} {"ep": "ok-00241", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.1015, "status": "ok", "correct": true, "speedup": 1.1015, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 62.8, "calls": 1, "tokens_in": 6776, "tokens_out": 1049, "ctx_chars": 11064, "ctx_sha": "f8d570b75c61820c", "t_end": 1791523416.3626657} {"ep": "ok-00232", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0366, "status": "ok", "correct": true, "speedup": 1.0366, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 110.3, "calls": 2, "tokens_in": 10253, "tokens_out": 2972, "ctx_chars": 5984, "ctx_sha": "f178e5e79419791a", "t_end": 1791523420.6576595} {"ep": "ok-00141", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 3.6763, "status": "ok", "correct": true, "speedup": 3.6763, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 491.4, "calls": 3, "tokens_in": 21451, "tokens_out": 26445, "ctx_chars": 696, "ctx_sha": "4047841f6f5065d2", "t_end": 1791523423.006627} {"ep": "ok-00244", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'relu_gn_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_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", "wall_s": 69.8, "calls": 1, "tokens_in": 1876, "tokens_out": 1876, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523426.441384} {"ep": "ok-00217", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": true, "score": 1.0004, "status": "ok", "correct": true, "speedup": 1.0004, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 210.1, "calls": 3, "tokens_in": 18408, "tokens_out": 3219, "ctx_chars": 7758, "ctx_sha": "ae9fa76cd68a90a1", "t_end": 1791523428.3122525} {"ep": "ok-00137", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3"], "p_item": null, "p_policy": null, "success": false, "score": 0.9997, "status": "ok", "correct": true, "speedup": 0.9997, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 521.9, "calls": 5, "tokens_in": 25167, "tokens_out": 4516, "ctx_chars": 3492, "ctx_sha": "8e815cc7e524fc7b", "t_end": 1791523429.333555} {"ep": "ok-00216", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.3609, "status": "ok", "correct": true, "speedup": 4.3609, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 215.9, "calls": 2, "tokens_in": 11616, "tokens_out": 16059, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791523431.435272} {"ep": "ok-00191", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0379, "status": "ok", "correct": true, "speedup": 1.0379, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 366.4, "calls": 2, "tokens_in": 10394, "tokens_out": 2958, "ctx_chars": 6332, "ctx_sha": "985655908be45697", "t_end": 1791523434.476925} {"ep": "ok-00235", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4024, "status": "ok", "correct": true, "speedup": 1.4024, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 114.8, "calls": 2, "tokens_in": 6123, "tokens_out": 6495, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523437.5083618} {"ep": "ok-00226", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 65.5399, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 173.5, "calls": 2, "tokens_in": 7064, "tokens_out": 7951, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523438.6261792} {"ep": "ok-00229", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4"], "p_item": null, "p_policy": null, "success": true, "score": 1.0197, "status": "ok", "correct": true, "speedup": 1.0197, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 141.1, "calls": 1, "tokens_in": 5681, "tokens_out": 4200, "ctx_chars": 9128, "ctx_sha": "055c3b32ed6a1efe", "t_end": 1791523438.9255524} {"ep": "ok-00236", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 110.5, "calls": 2, "tokens_in": 11990, "tokens_out": 5224, "ctx_chars": 7261, "ctx_sha": "dbcfd75c6a2698c6", "t_end": 1791523442.4291422} {"ep": "ok-00170", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.109, "status": "ok", "correct": true, "speedup": 0.109, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 419.9, "calls": 4, "tokens_in": 19516, "tokens_out": 6147, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523442.6841068} {"ep": "ok-00240", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0383, "status": "ok", "correct": true, "speedup": 1.0383, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 96.8, "calls": 2, "tokens_in": 10021, "tokens_out": 2708, "ctx_chars": 5984, "ctx_sha": "f178e5e79419791a", "t_end": 1791523444.392109} {"ep": "ok-00165", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8048, "status": "ok", "correct": true, "speedup": 0.8048, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 444.1, "calls": 3, "tokens_in": 260197, "tokens_out": 15495, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523448.5672631} {"ep": "ok-00230", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7887, "status": "ok", "correct": true, "speedup": 0.7887, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 172.9, "calls": 3, "tokens_in": 18724, "tokens_out": 12929, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523470.9571586} {"ep": "ok-00246", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.7831, "status": "ok", "correct": true, "speedup": 0.7831, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 113.1, "calls": 2, "tokens_in": 6354, "tokens_out": 1606, "ctx_chars": 1993, "ctx_sha": "e81d6bc04df8963f", "t_end": 1791523474.1909304} {"ep": "ok-00189", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 7.4183, "status": "ok", "correct": true, "speedup": 7.4183, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 419.9, "calls": 2, "tokens_in": 8936, "tokens_out": 18903, "ctx_chars": 696, "ctx_sha": "4047841f6f5065d2", "t_end": 1791523479.6190288} {"ep": "ok-00219", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.7936, "status": "ok", "correct": true, "speedup": 0.7936, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 267.2, "calls": 4, "tokens_in": 35385, "tokens_out": 20132, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523497.7725852} {"ep": "ok-00192", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.345, "status": "ok", "correct": true, "speedup": 0.345, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 440.0, "calls": 2, "tokens_in": 12092, "tokens_out": 22668, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523513.811524} {"ep": "ok-00181", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7079, "status": "ok", "correct": true, "speedup": 0.7079, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 471.1, "calls": 5, "tokens_in": 53841, "tokens_out": 9405, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791523519.2296584} {"ep": "ok-00222", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "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": 271.2, "calls": 3, "tokens_in": 17313, "tokens_out": 2898, "ctx_chars": 7333, "ctx_sha": "42fc92cfe0f03f33", "t_end": 1791523519.3521426} {"ep": "ok-00159", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 545.8, "calls": 4, "tokens_in": 29340, "tokens_out": 7086, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791523526.974588} {"ep": "ok-00212", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0338, "status": "ok", "correct": true, "speedup": 1.0338, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 348.0, "calls": 2, "tokens_in": 14400, "tokens_out": 3228, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791523527.1494594} {"ep": "ok-00218", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "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": 306.1, "calls": 2, "tokens_in": 13623, "tokens_out": 1339, "ctx_chars": 10587, "ctx_sha": "073757efd798c108", "t_end": 1791523527.8849561} {"ep": "ok-00239", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0931, "status": "ok", "correct": true, "speedup": 0.0931, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 215.4, "calls": 5, "tokens_in": 24991, "tokens_out": 5852, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523550.8243237} {"ep": "ok-00197", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6333, "status": "ok", "correct": true, "speedup": 0.6333, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 449.1, "calls": 3, "tokens_in": 19322, "tokens_out": 12222, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523553.6109896} {"ep": "ok-00238", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9968, "status": "ok", "correct": true, "speedup": 0.9968, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 224.7, "calls": 3, "tokens_in": 22431, "tokens_out": 2947, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791523558.432356} {"ep": "ok-00263", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 145.5, "calls": 2, "tokens_in": 12057, "tokens_out": 5096, "ctx_chars": 7549, "ctx_sha": "f0881682a422c1e8", "t_end": 1791523561.8485203} {"ep": "ok-00260", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 161.0, "calls": 2, "tokens_in": 15029, "tokens_out": 4863, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791523565.2653437} {"ep": "ok-00205", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "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": 440.4, "calls": 4, "tokens_in": 16905, "tokens_out": 8480, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791523575.6605968} {"ep": "ok-00201", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.6197, "status": "ok", "correct": true, "speedup": 0.6197, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 448.2, "calls": 5, "tokens_in": 58056, "tokens_out": 9848, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791523578.0336003} {"ep": "ok-00182", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.99, "status": "ok", "correct": true, "speedup": 0.99, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 530.8, "calls": 3, "tokens_in": 8914, "tokens_out": 3285, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523579.9691079} {"ep": "ok-00202", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9361, "status": "ok", "correct": true, "speedup": 0.9361, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 452.4, "calls": 2, "tokens_in": 16615, "tokens_out": 4294, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791523583.703432} {"ep": "ok-00259", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0316, "status": "ok", "correct": true, "speedup": 1.0316, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 186.6, "calls": 2, "tokens_in": 4769, "tokens_out": 2608, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523590.7697282} {"ep": "ok-00245", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7539, "status": "ok", "correct": true, "speedup": 0.7539, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 233.2, "calls": 3, "tokens_in": 17811, "tokens_out": 6354, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791523591.323904} {"ep": "ok-00266", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.8019, "status": "ok", "correct": true, "speedup": 0.8019, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 167.5, "calls": 2, "tokens_in": 13792, "tokens_out": 1493, "ctx_chars": 10587, "ctx_sha": "073757efd798c108", "t_end": 1791523593.9711185} {"ep": "ok-00204", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.2861, "status": "ok", "correct": true, "speedup": 7.2861, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 460.6, "calls": 3, "tokens_in": 18778, "tokens_out": 23012, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523594.304637} {"ep": "ok-00161", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7583, "status": "ok", "correct": true, "speedup": 0.7583, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 613.4, "calls": 5, "tokens_in": 56533, "tokens_out": 11028, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791523596.667747} {"ep": "ok-00262", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5378, "status": "ok", "correct": true, "speedup": 0.5378, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 185.6, "calls": 2, "tokens_in": 13702, "tokens_out": 10331, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791523597.3779156} {"ep": "ok-00213", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.7319, "status": "ok", "correct": true, "speedup": 1.7319, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 416.9, "calls": 3, "tokens_in": 245548, "tokens_out": 16753, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523598.1815896} {"ep": "ok-00214", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7164, "status": "ok", "correct": true, "speedup": 0.7164, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 417.8, "calls": 3, "tokens_in": 17491, "tokens_out": 4848, "ctx_chars": 2922, "ctx_sha": "3cb6e9a4694064be", "t_end": 1791523601.3713338} {"ep": "ok-00271", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7612, "status": "ok", "correct": true, "speedup": 0.7612, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 173.5, "calls": 3, "tokens_in": 26819, "tokens_out": 11543, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791523611.0281396} {"ep": "ok-00280", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "p_item": null, "p_policy": null, "success": true, "score": 1.0347, "status": "ok", "correct": true, "speedup": 1.0347, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 137.7, "calls": 3, "tokens_in": 14972, "tokens_out": 3206, "ctx_chars": 3968, "ctx_sha": "1e8d83b857da86fb", "t_end": 1791523617.3581371} {"ep": "ok-00253", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.295, "status": "ok", "correct": true, "speedup": 0.295, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 231.0, "calls": 3, "tokens_in": 21030, "tokens_out": 4325, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791523619.5507984} {"ep": "ok-00264", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657", "ker-f5807f0030"], "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": 199.7, "calls": 2, "tokens_in": 8609, "tokens_out": 4192, "ctx_chars": 3636, "ctx_sha": "c4e20fc881ca2568", "t_end": 1791523620.3970876} {"ep": "ok-00250", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8342, "status": "ok", "correct": true, "speedup": 0.8342, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 238.5, "calls": 2, "tokens_in": 15412, "tokens_out": 7195, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791523621.4512205} {"ep": "ok-00215", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7504, "status": "ok", "correct": true, "speedup": 0.7504, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 420.3, "calls": 2, "tokens_in": 9604, "tokens_out": 4404, "ctx_chars": 2922, "ctx_sha": "3cb6e9a4694064be", "t_end": 1791523622.1250296} {"ep": "ok-00268", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3036, "status": "ok", "correct": true, "speedup": 0.3036, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 204.3, "calls": 3, "tokens_in": 20376, "tokens_out": 4094, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523633.6237955} {"ep": "ok-00272", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-4cfeee51c1", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.8263, "status": "ok", "correct": true, "speedup": 0.8263, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 197.1, "calls": 4, "tokens_in": 23007, "tokens_out": 5156, "ctx_chars": 1884, "ctx_sha": "a37a18ff81bf7ac3", "t_end": 1791523635.71782} {"ep": "ok-00276", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 195.6, "calls": 2, "tokens_in": 16373, "tokens_out": 2490, "ctx_chars": 13736, "ctx_sha": "1ff228bcf6371290", "t_end": 1791523640.032609} {"ep": "ok-00296", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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": 58.9, "calls": 1, "tokens_in": 2917, "tokens_out": 5180, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523642.6181307} {"ep": "ok-00228", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "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": 356.0, "calls": 2, "tokens_in": 5684, "tokens_out": 5092, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523647.8840601} {"ep": "ok-00275", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 205.9, "calls": 1, "tokens_in": 2759, "tokens_out": 3903, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523648.5532286} {"ep": "ok-00270", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 68.9751, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 217.3, "calls": 2, "tokens_in": 15274, "tokens_out": 7932, "ctx_chars": 9324, "ctx_sha": "60d2d3bd3cb4a50b", "t_end": 1791523651.7318203} {"ep": "ok-00237", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-e75be99f9e", "ker-071e045dd4"], "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": 320.4, "calls": 3, "tokens_in": 18126, "tokens_out": 2841, "ctx_chars": 7245, "ctx_sha": "5c9cac21cf11798f", "t_end": 1791523652.6789663} {"ep": "ok-00267", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0367, "status": "ok", "correct": true, "speedup": 1.0367, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 229.6, "calls": 2, "tokens_in": 15660, "tokens_out": 2867, "ctx_chars": 12848, "ctx_sha": "c5005fba182a16d4", "t_end": 1791523657.8689332} {"ep": "ok-00255", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0972, "status": "ok", "correct": true, "speedup": 1.0972, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 266.1, "calls": 3, "tokens_in": 24335, "tokens_out": 2169, "ctx_chars": 12121, "ctx_sha": "03e0667a95c5bdd5", "t_end": 1791523659.2639272} {"ep": "ok-00223", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 7.766, "status": "ok", "correct": true, "speedup": 7.766, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 408.1, "calls": 2, "tokens_in": 14520, "tokens_out": 28600, "ctx_chars": 4637, "ctx_sha": "e562c22c78d786c2", "t_end": 1791523659.374505} {"ep": "ok-00200", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": false, "score": 0.9978, "status": "ok", "correct": true, "speedup": 0.9978, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 530.5, "calls": 5, "tokens_in": 44333, "tokens_out": 9332, "ctx_chars": 6127, "ctx_sha": "6d5266a306356454", "t_end": 1791523659.4877014} {"ep": "ok-00282", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.2971, "status": "ok", "correct": true, "speedup": 0.2971, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 147.6, "calls": 3, "tokens_in": 20129, "tokens_out": 4393, "ctx_chars": 6059, "ctx_sha": "fcbd714fceba4ac3", "t_end": 1791523661.4056728} {"ep": "ok-00258", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.792, "status": "ok", "correct": true, "speedup": 0.792, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 257.5, "calls": 2, "tokens_in": 12785, "tokens_out": 4174, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791523661.7016683} {"ep": "ok-00254", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 31.8385, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 274.0, "calls": 2, "tokens_in": 14383, "tokens_out": 5593, "ctx_chars": 9324, "ctx_sha": "60d2d3bd3cb4a50b", "t_end": 1791523662.9505305} {"ep": "ok-00274", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "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": 225.7, "calls": 2, "tokens_in": 5985, "tokens_out": 4410, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791523668.1537814} {"ep": "ok-00314", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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": 40.5, "calls": 1, "tokens_in": 1681, "tokens_out": 709, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523683.1582408} {"ep": "ok-00273", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "p_item": null, "p_policy": null, "success": false, "score": 0.9969, "status": "ok", "correct": true, "speedup": 0.9969, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 262.2, "calls": 4, "tokens_in": 26653, "tokens_out": 4345, "ctx_chars": 7273, "ctx_sha": "1f97a75c86510f14", "t_end": 1791523701.124356} {"ep": "ok-00248", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7465, "status": "ok", "correct": true, "speedup": 0.7465, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 333.4, "calls": 3, "tokens_in": 28310, "tokens_out": 13477, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523705.83467} {"ep": "ok-00293", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 44.0461, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 135.0, "calls": 2, "tokens_in": 7207, "tokens_out": 5840, "ctx_chars": 2016, "ctx_sha": "a2bb82d0a90ca3de", "t_end": 1791523710.6751} {"ep": "ok-00265", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 84.3033, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 289.1, "calls": 2, "tokens_in": 6750, "tokens_out": 6599, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523712.0857096} {"ep": "ok-00243", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 37.5352, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 362.4, "calls": 2, "tokens_in": 160458, "tokens_out": 9081, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523718.243387} {"ep": "ok-00289", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.3908, "status": "ok", "correct": true, "speedup": 0.3908, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 170.4, "calls": 2, "tokens_in": 14223, "tokens_out": 11306, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791523723.966933} {"ep": "ok-00277", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 71.3513, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 275.7, "calls": 2, "tokens_in": 160195, "tokens_out": 8862, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523724.2426527} {"ep": "ok-00252", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0104, "status": "ok", "correct": true, "speedup": 1.0104, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 342.6, "calls": 5, "tokens_in": 42580, "tokens_out": 9486, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523729.251558} {"ep": "ok-00306", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0349, "status": "ok", "correct": true, "speedup": 1.0349, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 116.4, "calls": 2, "tokens_in": 13170, "tokens_out": 2901, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791523733.7735803} {"ep": "ok-00307", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0348, "status": "ok", "correct": true, "speedup": 1.0348, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 116.3, "calls": 3, "tokens_in": 19550, "tokens_out": 3767, "ctx_chars": 6481, "ctx_sha": "2281995c87ed0a4b", "t_end": 1791523735.8136024} {"ep": "ok-00269", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-4cfeee51c1", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7573, "status": "ok", "correct": true, "speedup": 0.7573, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 310.2, "calls": 2, "tokens_in": 8404, "tokens_out": 3935, "ctx_chars": 1884, "ctx_sha": "a37a18ff81bf7ac3", "t_end": 1791523741.6105683} {"ep": "ok-00224", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 8.9801, "status": "ok", "correct": true, "speedup": 8.9801, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 486.6, "calls": 3, "tokens_in": 18179, "tokens_out": 22478, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523743.2742653} {"ep": "ok-00298", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 48.5782, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 156.6, "calls": 2, "tokens_in": 14443, "tokens_out": 5977, "ctx_chars": 9324, "ctx_sha": "60d2d3bd3cb4a50b", "t_end": 1791523747.9723067} {"ep": "ok-00297", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "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": 163.5, "calls": 3, "tokens_in": 22472, "tokens_out": 2801, "ctx_chars": 10528, "ctx_sha": "2d3203f47b184251", "t_end": 1791523754.2523994} {"ep": "ok-00249", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.6615, "status": "ok", "correct": true, "speedup": 0.6615, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 381.5, "calls": 3, "tokens_in": 34324, "tokens_out": 18986, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791523756.852117} {"ep": "ok-00257", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0972, "status": "ok", "correct": true, "speedup": 1.0972, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 356.9, "calls": 2, "tokens_in": 17754, "tokens_out": 3339, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791523757.7494357} {"ep": "ok-00301", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.1128, "status": "ok", "correct": true, "speedup": 0.1128, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 163.9, "calls": 4, "tokens_in": 31866, "tokens_out": 5317, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791523760.5585554} {"ep": "ok-00283", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.476, "status": "ok", "correct": true, "speedup": 0.476, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 247.6, "calls": 2, "tokens_in": 10983, "tokens_out": 17728, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523766.7832417} {"ep": "ok-00303", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.023, "status": "ok", "correct": true, "speedup": 1.023, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 168.8, "calls": 3, "tokens_in": 24699, "tokens_out": 1883, "ctx_chars": 13736, "ctx_sha": "f9598e6429f01c39", "t_end": 1791523767.0085385} {"ep": "ok-00291", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8654, "status": "ok", "correct": true, "speedup": 0.8654, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 206.1, "calls": 2, "tokens_in": 14650, "tokens_out": 10521, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523767.8992279} {"ep": "ok-00288", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "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": 224.8, "calls": 4, "tokens_in": 14978, "tokens_out": 7528, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523775.6458237} {"ep": "ok-00154", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8879, "status": "ok", "correct": true, "speedup": 0.8879, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 806.0, "calls": 5, "tokens_in": 62852, "tokens_out": 12832, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791523778.489982} {"ep": "ok-00338", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0963, "status": "ok", "correct": true, "speedup": 1.0963, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 41.0, "calls": 1, "tokens_in": 6776, "tokens_out": 1071, "ctx_chars": 11064, "ctx_sha": "f8d570b75c61820c", "t_end": 1791523782.6374478} {"ep": "ok-00294", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0311, "status": "ok", "correct": true, "speedup": 1.0311, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 207.9, "calls": 3, "tokens_in": 25432, "tokens_out": 2785, "ctx_chars": 12848, "ctx_sha": "98fb6b45b82f188b", "t_end": 1791523785.9565368} {"ep": "ok-00290", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 231.8, "calls": 3, "tokens_in": 20927, "tokens_out": 1831, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791523790.217966} {"ep": "ok-00312", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1013, "status": "ok", "correct": true, "speedup": 1.1013, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 155.3, "calls": 1, "tokens_in": 7684, "tokens_out": 1056, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791523791.0163014} {"ep": "ok-00278", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 321.9, "calls": 5, "tokens_in": 402010, "tokens_out": 4470, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523792.896248} {"ep": "ok-00256", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0336, "status": "ok", "correct": true, "speedup": 1.0336, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 396.7, "calls": 2, "tokens_in": 159687, "tokens_out": 6970, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523796.503549} {"ep": "ok-00251", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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": 413.2, "calls": 4, "tokens_in": 22562, "tokens_out": 7515, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523799.8877041} {"ep": "ok-00317", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2984, "status": "ok", "correct": true, "speedup": 0.2984, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 150.7, "calls": 1, "tokens_in": 5329, "tokens_out": 2143, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523802.436585} {"ep": "ok-00184", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 15.2493, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 750.9, "calls": 3, "tokens_in": 28589, "tokens_out": 34824, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791523804.248698} {"ep": "ok-00318", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3287, "status": "ok", "correct": true, "speedup": 0.3287, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 161.3, "calls": 3, "tokens_in": 21329, "tokens_out": 5410, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791523813.9317982} {"ep": "ok-00292", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.6757, "status": "ok", "correct": true, "speedup": 0.6757, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 250.6, "calls": 3, "tokens_in": 30834, "tokens_out": 16003, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791523815.821218} {"ep": "ok-00325", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 36.4107, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 156.5, "calls": 2, "tokens_in": 14285, "tokens_out": 6064, "ctx_chars": 9324, "ctx_sha": "60d2d3bd3cb4a50b", "t_end": 1791523819.4840772} {"ep": "ok-00316", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "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": 174.5, "calls": 3, "tokens_in": 17440, "tokens_out": 2964, "ctx_chars": 7333, "ctx_sha": "42fc92cfe0f03f33", "t_end": 1791523823.0446715} {"ep": "ok-00313", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7114, "status": "ok", "correct": true, "speedup": 0.7114, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 188.0, "calls": 2, "tokens_in": 15869, "tokens_out": 6962, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791523828.0194986} {"ep": "ok-00221", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 8.8652, "status": "ok", "correct": true, "speedup": 8.8652, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 585.8, "calls": 3, "tokens_in": 254881, "tokens_out": 30526, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523829.9128892} {"ep": "ok-00242", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": true, "score": 1.9131, "status": "ok", "correct": true, "speedup": 1.9131, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 478.0, "calls": 2, "tokens_in": 18435, "tokens_out": 18163, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791523832.5886385} {"ep": "ok-00323", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.406, "status": "ok", "correct": true, "speedup": 1.406, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 171.2, "calls": 2, "tokens_in": 159351, "tokens_out": 7199, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523832.5966694} {"ep": "ok-00335", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "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": 107.8, "calls": 2, "tokens_in": 10907, "tokens_out": 2632, "ctx_chars": 7159, "ctx_sha": "1ccf94064353eca4", "t_end": 1791523837.059285} {"ep": "ok-00345", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 71.2, "calls": 1, "tokens_in": 3050, "tokens_out": 2853, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523838.0031118} {"ep": "ok-00287", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0319, "status": "ok", "correct": true, "speedup": 1.0319, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 320.5, "calls": 2, "tokens_in": 13478, "tokens_out": 4620, "ctx_chars": 8788, "ctx_sha": "796f186ac3130710", "t_end": 1791523848.376408} {"ep": "ok-00349", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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_pool_l2_050': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_l2_050 -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": 73.0, "calls": 1, "tokens_in": 1960, "tokens_out": 2015, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523851.4855413} {"ep": "ok-00295", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "p_item": null, "p_policy": null, "success": true, "score": 1.0331, "status": "ok", "correct": true, "speedup": 1.0331, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 275.2, "calls": 4, "tokens_in": 22329, "tokens_out": 4588, "ctx_chars": 3968, "ctx_sha": "1e8d83b857da86fb", "t_end": 1791523855.1213672} {"ep": "ok-00355", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0293, "status": "ok", "correct": true, "speedup": 1.0293, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 64.0, "calls": 2, "tokens_in": 10148, "tokens_out": 2657, "ctx_chars": 6332, "ctx_sha": "985655908be45697", "t_end": 1791523860.527009} {"ep": "ok-00359", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "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": 47.5, "calls": 1, "tokens_in": 4853, "tokens_out": 940, "ctx_chars": 7308, "ctx_sha": "cb4e925a23b3095d", "t_end": 1791523861.389132} {"ep": "ok-00351", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0964, "status": "ok", "correct": true, "speedup": 1.0964, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 77.0, "calls": 3, "tokens_in": 25073, "tokens_out": 3316, "ctx_chars": 11064, "ctx_sha": "f8d570b75c61820c", "t_end": 1791523862.970492} {"ep": "ok-00308", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "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": 247.6, "calls": 2, "tokens_in": 5385, "tokens_out": 2550, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791523867.9650671} {"ep": "ok-00305", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 37.1329, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 261.2, "calls": 2, "tokens_in": 6416, "tokens_out": 6294, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523872.2120407} {"ep": "ok-00326", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'relu_gn_fused': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_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/t", "wall_s": 206.9, "calls": 1, "tokens_in": 1876, "tokens_out": 1929, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523875.0550768} {"ep": "ok-00327", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4"], "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": 195.0, "calls": 2, "tokens_in": 11694, "tokens_out": 4347, "ctx_chars": 7221, "ctx_sha": "c76ebe5823d3165a", "t_end": 1791523878.1614954} {"ep": "ok-00311", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.085, "status": "ok", "correct": true, "speedup": 0.085, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 247.5, "calls": 3, "tokens_in": 29565, "tokens_out": 6434, "ctx_chars": 10587, "ctx_sha": "073757efd798c108", "t_end": 1791523881.1586766} {"ep": "ok-00336", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "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": 149.6, "calls": 2, "tokens_in": 4963, "tokens_out": 3187, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523883.3922005} {"ep": "ok-00334", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0359, "status": "ok", "correct": true, "speedup": 1.0359, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 162.2, "calls": 2, "tokens_in": 15682, "tokens_out": 2764, "ctx_chars": 12848, "ctx_sha": "c5005fba182a16d4", "t_end": 1791523886.4070854} {"ep": "ok-00350", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 113.7, "calls": 1, "tokens_in": 3050, "tokens_out": 4865, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523896.3483508} {"ep": "ok-00324", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 32.4204, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 236.8, "calls": 2, "tokens_in": 18160, "tokens_out": 7181, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791523898.5114102} {"ep": "ok-00322", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": true, "score": 1.0203, "status": "ok", "correct": true, "speedup": 1.0203, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 239.6, "calls": 3, "tokens_in": 22353, "tokens_out": 2745, "ctx_chars": 10528, "ctx_sha": "2d3203f47b184251", "t_end": 1791523899.1197162} {"ep": "ok-00340", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0459, "status": "ok", "correct": true, "speedup": 1.0459, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 161.2, "calls": 2, "tokens_in": 13931, "tokens_out": 2835, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791523909.1448505} {"ep": "ok-00299", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3052, "status": "ok", "correct": true, "speedup": 0.3052, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 321.9, "calls": 3, "tokens_in": 23366, "tokens_out": 4191, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791523915.8483484} {"ep": "ok-00371", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "no_custom_kernel", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "none of the candidate's kernels ['_relu6_kernel', '_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "wall_s": 60.7, "calls": 1, "tokens_in": 2626, "tokens_out": 4494, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523915.8593256} {"ep": "ok-00261", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1685, "status": "ok", "correct": true, "speedup": 1.1685, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 512.9, "calls": 2, "tokens_in": 12754, "tokens_out": 23076, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523918.2009046} {"ep": "ok-00337", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0347, "status": "ok", "correct": true, "speedup": 1.0347, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 189.1, "calls": 3, "tokens_in": 7912, "tokens_out": 2046, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523924.9121656} {"ep": "ok-00300", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": true, "score": 1.0206, "status": "ok", "correct": true, "speedup": 1.0206, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 335.2, "calls": 3, "tokens_in": 28891, "tokens_out": 2870, "ctx_chars": 15603, "ctx_sha": "a415cc777520c780", "t_end": 1791523929.4931934} {"ep": "ok-00320", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1058, "status": "ok", "correct": true, "speedup": 1.1058, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 277.6, "calls": 2, "tokens_in": 158682, "tokens_out": 3397, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523936.8456616} {"ep": "ok-00281", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 443.8, "calls": 4, "tokens_in": 25304, "tokens_out": 7464, "ctx_chars": 5630, "ctx_sha": "1d3288f4ac875b68", "t_end": 1791523941.5289152} {"ep": "ok-00372", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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 'gemm_div_sum': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemm_div_sum -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": 84.1, "calls": 1, "tokens_in": 1681, "tokens_out": 1250, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523944.5998602} {"ep": "ok-00331", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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": 233.8, "calls": 3, "tokens_in": 8520, "tokens_out": 2884, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523945.843732} {"ep": "ok-00247", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 7.5962, "status": "ok", "correct": true, "speedup": 7.5962, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 585.5, "calls": 3, "tokens_in": 33991, "tokens_out": 41050, "ctx_chars": 4637, "ctx_sha": "e562c22c78d786c2", "t_end": 1791523949.0037966} {"ep": "ok-00342", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3258, "status": "ok", "correct": true, "speedup": 0.3258, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 193.3, "calls": 2, "tokens_in": 12919, "tokens_out": 4178, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791523950.1026225} {"ep": "ok-00304", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4726, "status": "ok", "correct": true, "speedup": 1.4726, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 349.2, "calls": 2, "tokens_in": 160040, "tokens_out": 13747, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523950.591526} {"ep": "ok-00330", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9621, "status": "ok", "correct": true, "speedup": 0.9621, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 240.0, "calls": 3, "tokens_in": 9451, "tokens_out": 3727, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523950.6910667} {"ep": "ok-00353", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7889, "status": "ok", "correct": true, "speedup": 0.7889, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 160.4, "calls": 2, "tokens_in": 15262, "tokens_out": 5342, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791523951.3849006} {"ep": "ok-00279", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 479.2, "calls": 5, "tokens_in": 38416, "tokens_out": 4059, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791523953.356751} {"ep": "ok-00286", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0356, "status": "ok", "correct": true, "speedup": 1.0356, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 432.3, "calls": 2, "tokens_in": 159633, "tokens_out": 7052, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523959.4078948} {"ep": "ok-00356", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.2351, "status": "ok", "correct": true, "speedup": 1.2351, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 168.7, "calls": 2, "tokens_in": 6243, "tokens_out": 6329, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791523968.5765982} {"ep": "ok-00343", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0285, "status": "ok", "correct": true, "speedup": 1.0285, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 212.1, "calls": 2, "tokens_in": 13833, "tokens_out": 2172, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791523969.851029} {"ep": "ok-00319", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0344, "status": "ok", "correct": true, "speedup": 1.0344, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 312.9, "calls": 2, "tokens_in": 13089, "tokens_out": 2008, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791523970.7470293} {"ep": "ok-00309", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0035, "status": "ok", "correct": true, "speedup": 1.0035, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 360.1, "calls": 4, "tokens_in": 35103, "tokens_out": 8061, "ctx_chars": 12555, "ctx_sha": "bae97e8db7be5c58", "t_end": 1791523981.5881307} {"ep": "ok-00310", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7887, "status": "ok", "correct": true, "speedup": 0.7887, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 373.0, "calls": 2, "tokens_in": 163311, "tokens_out": 14494, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791523995.1437354} {"ep": "ok-00402", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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: assignment to attribute 'new_conv.weight.data' is not allowed (only self.); line 88: assignment to attribute 'new_conv.bias.data' is not allowed (only self.)", "wall_s": 30.4, "calls": 1, "tokens_in": 2626, "tokens_out": 3750, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791523998.9595869} {"ep": "ok-00393", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.9968, "status": "ok", "correct": true, "speedup": 0.9968, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 57.2, "calls": 3, "tokens_in": 26169, "tokens_out": 2976, "ctx_chars": 14186, "ctx_sha": "81f894fa6f6eba57", "t_end": 1791524001.7752805} {"ep": "ok-00389", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7648, "status": "ok", "correct": true, "speedup": 0.7648, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 85.0, "calls": 3, "tokens_in": 12001, "tokens_out": 4077, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524009.867197} {"ep": "ok-00365", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-d10f50ba0c", "pit-69809d3cb6", "rec-21ef38357b"], "p_item": null, "p_policy": null, "success": false, "score": 0.9413, "status": "ok", "correct": true, "speedup": 0.9413, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 181.2, "calls": 2, "tokens_in": 7124, "tokens_out": 5881, "ctx_chars": 1383, "ctx_sha": "680ebcf2a2f1ebf3", "t_end": 1791524013.779306} {"ep": "ok-00400", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3, "status": "ok", "correct": true, "speedup": 0.3, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 72.0, "calls": 3, "tokens_in": 23505, "tokens_out": 4296, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791524025.400733} {"ep": "ok-00401", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0339, "status": "ok", "correct": true, "speedup": 1.0339, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 69.7, "calls": 2, "tokens_in": 14369, "tokens_out": 3343, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791524029.1433163} {"ep": "ok-00387", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 45.7512, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 121.3, "calls": 2, "tokens_in": 17650, "tokens_out": 7509, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791524037.139171} {"ep": "ok-00411", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8274c30657", "rec-4365468e5f", "ker-6558b83d05"], "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": 15.1, "calls": 1, "tokens_in": 3925, "tokens_out": 594, "ctx_chars": 5534, "ctx_sha": "3d72d551b52c403d", "t_end": 1791524040.5072384} {"ep": "ok-00344", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.5323, "status": "ok", "correct": true, "speedup": 0.5323, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 287.0, "calls": 2, "tokens_in": 13253, "tokens_out": 5424, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791524047.543428} {"ep": "ok-00352", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6471, "status": "ok", "correct": true, "speedup": 0.6471, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 259.7, "calls": 4, "tokens_in": 33729, "tokens_out": 17409, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524049.9490097} {"ep": "ok-00399", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8274c30657", "rec-4365468e5f", "ker-6558b83d05"], "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": 103.2, "calls": 4, "tokens_in": 21216, "tokens_out": 3201, "ctx_chars": 5534, "ctx_sha": "3d72d551b52c403d", "t_end": 1791524054.5984247} {"ep": "ok-00408", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "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": 54.9, "calls": 3, "tokens_in": 16706, "tokens_out": 1870, "ctx_chars": 7308, "ctx_sha": "cb4e925a23b3095d", "t_end": 1791524056.6426632} {"ep": "ok-00378", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657", "ker-f5807f0030"], "p_item": null, "p_policy": null, "success": false, "score": 0.999, "status": "ok", "correct": true, "speedup": 0.999, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 182.5, "calls": 2, "tokens_in": 8632, "tokens_out": 4382, "ctx_chars": 3636, "ctx_sha": "c4e20fc881ca2568", "t_end": 1791524060.663194} {"ep": "ok-00404", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 90.2, "calls": 3, "tokens_in": 20929, "tokens_out": 1838, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791524060.946081} {"ep": "ok-00364", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0382, "status": "ok", "correct": true, "speedup": 1.0382, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 238.7, "calls": 2, "tokens_in": 5496, "tokens_out": 4848, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524068.6260917} {"ep": "ok-00373", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8334, "status": "ok", "correct": true, "speedup": 0.8334, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 223.4, "calls": 3, "tokens_in": 254367, "tokens_out": 13422, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524084.7770653} {"ep": "ok-00347", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 320.2, "calls": 5, "tokens_in": 43128, "tokens_out": 3811, "ctx_chars": 12555, "ctx_sha": "fb438aa3b57cd542", "t_end": 1791524088.1101832} {"ep": "ok-00382", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "p_item": null, "p_policy": null, "success": false, "score": 0.9949, "status": "ok", "correct": true, "speedup": 0.9949, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 193.4, "calls": 3, "tokens_in": 17360, "tokens_out": 2949, "ctx_chars": 7273, "ctx_sha": "1f97a75c86510f14", "t_end": 1791524089.702594} {"ep": "ok-00329", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4613, "status": "ok", "correct": true, "speedup": 1.4613, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 385.5, "calls": 3, "tokens_in": 12779, "tokens_out": 8840, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524091.3675673} {"ep": "ok-00302", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9936, "status": "ok", "correct": true, "speedup": 0.9936, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 501.5, "calls": 4, "tokens_in": 20890, "tokens_out": 6403, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524098.865264} {"ep": "ok-00358", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.4455, "status": "ok", "correct": true, "speedup": 1.4455, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 301.5, "calls": 2, "tokens_in": 6637, "tokens_out": 7011, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524105.7254255} {"ep": "ok-00409", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8933, "status": "ok", "correct": true, "speedup": 0.8933, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 100.7, "calls": 2, "tokens_in": 13199, "tokens_out": 8022, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791524110.5740943} {"ep": "ok-00391", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0322, "status": "ok", "correct": true, "speedup": 1.0322, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 175.6, "calls": 2, "tokens_in": 10885, "tokens_out": 2207, "ctx_chars": 7159, "ctx_sha": "1ccf94064353eca4", "t_end": 1791524112.4037845} {"ep": "ok-00357", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 1.0304, "status": "ok", "correct": true, "speedup": 1.0304, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 311.1, "calls": 2, "tokens_in": 7398, "tokens_out": 5357, "ctx_chars": 2175, "ctx_sha": "86963271ef726410", "t_end": 1791524113.5039473} {"ep": "ok-00417", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0399, "status": "ok", "correct": true, "speedup": 1.0399, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 59.8, "calls": 2, "tokens_in": 5148, "tokens_out": 3205, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524114.4023883} {"ep": "ok-00398", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0256, "status": "ok", "correct": true, "speedup": 1.0256, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 164.7, "calls": 3, "tokens_in": 25899, "tokens_out": 12124, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791524115.399935} {"ep": "ok-00376", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0956, "status": "ok", "correct": true, "speedup": 1.0956, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 244.8, "calls": 3, "tokens_in": 24117, "tokens_out": 2044, "ctx_chars": 12121, "ctx_sha": "03e0667a95c5bdd5", "t_end": 1791524117.0531087} {"ep": "ok-00360", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.4555, "status": "ok", "correct": true, "speedup": 0.4555, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 301.3, "calls": 2, "tokens_in": 10384, "tokens_out": 15621, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524117.0763896} {"ep": "ok-00420", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0365, "status": "ok", "correct": true, "speedup": 1.0365, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 58.2, "calls": 2, "tokens_in": 10331, "tokens_out": 2867, "ctx_chars": 6332, "ctx_sha": "985655908be45697", "t_end": 1791524119.1149993} {"ep": "ok-00412", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 94.4, "calls": 2, "tokens_in": 15267, "tokens_out": 5515, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791524123.5756352} {"ep": "ok-00414", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.9919, "status": "ok", "correct": true, "speedup": 0.9919, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 85.9, "calls": 2, "tokens_in": 16927, "tokens_out": 3067, "ctx_chars": 14186, "ctx_sha": "81f894fa6f6eba57", "t_end": 1791524126.4090934} {"ep": "ok-00284", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 8.1858, "status": "ok", "correct": true, "speedup": 8.1858, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 615.5, "calls": 3, "tokens_in": 30578, "tokens_out": 20796, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791524134.8978047} {"ep": "ok-00392", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.9897, "status": "ok", "correct": true, "speedup": 0.9897, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 194.6, "calls": 3, "tokens_in": 18152, "tokens_out": 2984, "ctx_chars": 7758, "ctx_sha": "ae9fa76cd68a90a1", "t_end": 1791524136.10187} {"ep": "ok-00375", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.1161, "status": "ok", "correct": true, "speedup": 6.1161, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 271.8, "calls": 3, "tokens_in": 22816, "tokens_out": 18963, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524139.7702866} {"ep": "ok-00366", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.3879, "status": "ok", "correct": true, "speedup": 4.3879, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 323.9, "calls": 2, "tokens_in": 12826, "tokens_out": 23255, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524156.480077} {"ep": "ok-00397", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.0631, "status": "ok", "correct": true, "speedup": 0.0631, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 208.3, "calls": 3, "tokens_in": 25989, "tokens_out": 6205, "ctx_chars": 8141, "ctx_sha": "6911e5d55595673c", "t_end": 1791524158.9255438} {"ep": "ok-00354", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 369.6, "calls": 5, "tokens_in": 408753, "tokens_out": 6859, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524162.4630756} {"ep": "ok-00341", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4"], "p_item": null, "p_policy": null, "success": true, "score": 1.031, "status": "ok", "correct": true, "speedup": 1.031, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 413.5, "calls": 2, "tokens_in": 11817, "tokens_out": 4824, "ctx_chars": 7221, "ctx_sha": "c76ebe5823d3165a", "t_end": 1791524167.7835543} {"ep": "ok-00435", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0145, "status": "ok", "correct": true, "speedup": 1.0145, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 50.9, "calls": 1, "tokens_in": 1723, "tokens_out": 1089, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524169.991255} {"ep": "ok-00315", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 75.2254, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 523.5, "calls": 2, "tokens_in": 160399, "tokens_out": 9709, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524171.3927274} {"ep": "ok-00396", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 230.8, "calls": 3, "tokens_in": 20360, "tokens_out": 6298, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791524180.8762271} {"ep": "ok-00388", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.73, "status": "ok", "correct": true, "speedup": 0.73, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 263.2, "calls": 5, "tokens_in": 58567, "tokens_out": 10191, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791524181.4448774} {"ep": "ok-00333", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0358, "status": "ok", "correct": true, "speedup": 1.0358, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 458.5, "calls": 2, "tokens_in": 159851, "tokens_out": 7312, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524182.4636476} {"ep": "ok-00361", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff"], "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": 378.4, "calls": 3, "tokens_in": 17651, "tokens_out": 3436, "ctx_chars": 5518, "ctx_sha": "7180f8dff0056426", "t_end": 1791524197.8715672} {"ep": "ok-00370", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff"], "p_item": null, "p_policy": null, "success": true, "score": 1.032, "status": "ok", "correct": true, "speedup": 1.032, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 349.6, "calls": 3, "tokens_in": 15969, "tokens_out": 2655, "ctx_chars": 5518, "ctx_sha": "7180f8dff0056426", "t_end": 1791524201.0815759} {"ep": "ok-00369", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 361.2, "calls": 3, "tokens_in": 242783, "tokens_out": 4779, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524209.5751178} {"ep": "ok-00406", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.036, "status": "ok", "correct": true, "speedup": 1.036, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 220.3, "calls": 2, "tokens_in": 6433, "tokens_out": 6374, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524215.4786046} {"ep": "ok-00363", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4"], "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": 391.0, "calls": 3, "tokens_in": 20342, "tokens_out": 2881, "ctx_chars": 9128, "ctx_sha": "055c3b32ed6a1efe", "t_end": 1791524219.0344734} {"ep": "ok-00394", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5693, "status": "ok", "correct": true, "speedup": 0.5693, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 274.3, "calls": 4, "tokens_in": 35426, "tokens_out": 17337, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524220.1448236} {"ep": "ok-00403", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7567, "status": "ok", "correct": true, "speedup": 0.7567, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 255.4, "calls": 2, "tokens_in": 164275, "tokens_out": 13949, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524225.2327187} {"ep": "ok-00426", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.8261, "status": "ok", "correct": true, "speedup": 0.8261, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 126.6, "calls": 4, "tokens_in": 24072, "tokens_out": 5311, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524225.4697437} {"ep": "ok-00386", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9579, "status": "ok", "correct": true, "speedup": 0.9579, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 314.2, "calls": 4, "tokens_in": 18572, "tokens_out": 4590, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524230.0277472} {"ep": "ok-00425", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0206, "status": "ok", "correct": true, "speedup": 1.0206, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 145.9, "calls": 3, "tokens_in": 25394, "tokens_out": 2925, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791524237.2651067} {"ep": "ok-00405", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9973, "status": "ok", "correct": true, "speedup": 0.9973, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 256.3, "calls": 2, "tokens_in": 159543, "tokens_out": 5360, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524237.8446648} {"ep": "ok-00285", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 711.0, "calls": 4, "tokens_in": 29763, "tokens_out": 7343, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791524238.0003216} {"ep": "ok-00368", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 406.7, "calls": 3, "tokens_in": 26331, "tokens_out": 3064, "ctx_chars": 14186, "ctx_sha": "81f894fa6f6eba57", "t_end": 1791524244.6624124} {"ep": "ok-00430", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9349, "status": "ok", "correct": true, "speedup": 0.9349, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 131.9, "calls": 2, "tokens_in": 16577, "tokens_out": 4061, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791524245.4396434} {"ep": "ok-00395", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 8.0806, "status": "ok", "correct": true, "speedup": 8.0806, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 298.2, "calls": 3, "tokens_in": 17754, "tokens_out": 19796, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524247.187738} {"ep": "ok-00383", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9341, "status": "ok", "correct": true, "speedup": 0.9341, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 349.4, "calls": 2, "tokens_in": 19367, "tokens_out": 5528, "ctx_chars": 15603, "ctx_sha": "3f3a125c98fd04bf", "t_end": 1791524247.909146} {"ep": "ok-00348", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0148, "status": "ok", "correct": true, "speedup": 1.0148, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 485.9, "calls": 3, "tokens_in": 25329, "tokens_out": 2887, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791524261.5655403} {"ep": "ok-00427", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.774, "status": "ok", "correct": true, "speedup": 0.774, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 156.7, "calls": 3, "tokens_in": 10234, "tokens_out": 1697, "ctx_chars": 1993, "ctx_sha": "e81d6bc04df8963f", "t_end": 1791524262.3922036} {"ep": "ok-00410", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5475, "status": "ok", "correct": true, "speedup": 1.5475, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 249.6, "calls": 2, "tokens_in": 6136, "tokens_out": 6498, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524263.3542323} {"ep": "ok-00431", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 158.3, "calls": 3, "tokens_in": 20884, "tokens_out": 1834, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791524272.6793528} {"ep": "ok-00407", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "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": 274.9, "calls": 4, "tokens_in": 25583, "tokens_out": 8510, "ctx_chars": 5978, "ctx_sha": "6db7ec2d3f2a73bf", "t_end": 1791524273.8490672} {"ep": "ok-00423", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.5647, "status": "ok", "correct": true, "speedup": 1.5647, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 191.1, "calls": 2, "tokens_in": 5973, "tokens_out": 5845, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524279.241839} {"ep": "ok-00440", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0259, "status": "ok", "correct": true, "speedup": 1.0259, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 141.5, "calls": 3, "tokens_in": 25316, "tokens_out": 2928, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791524281.2922394} {"ep": "ok-00433", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.6666, "status": "ok", "correct": true, "speedup": 0.6666, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 164.3, "calls": 2, "tokens_in": 9722, "tokens_out": 11827, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524281.3407192} {"ep": "ok-00447", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0365, "status": "ok", "correct": true, "speedup": 1.0365, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 103.2, "calls": 2, "tokens_in": 4973, "tokens_out": 2946, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524284.0575485} {"ep": "ok-00445", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 116.1, "calls": 2, "tokens_in": 17743, "tokens_out": 5944, "ctx_chars": 14186, "ctx_sha": "9cdfa12549d40778", "t_end": 1791524286.1394534} {"ep": "ok-00452", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.097, "status": "ok", "correct": true, "speedup": 1.097, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 80.9, "calls": 3, "tokens_in": 24159, "tokens_out": 2080, "ctx_chars": 12103, "ctx_sha": "42cb8c90d2cfce7e", "t_end": 1791524290.4773078} {"ep": "ok-00346", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 5.1426, "status": "ok", "correct": true, "speedup": 5.1426, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 541.8, "calls": 3, "tokens_in": 19428, "tokens_out": 20425, "ctx_chars": 1495, "ctx_sha": "983928657b2b0e88", "t_end": 1791524308.806184} {"ep": "ok-00374", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 6.3588, "status": "ok", "correct": true, "speedup": 6.3588, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 452.0, "calls": 3, "tokens_in": 30786, "tokens_out": 38078, "ctx_chars": 2713, "ctx_sha": "d18291fca1598bb8", "t_end": 1791524314.9950042} {"ep": "ok-00384", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 6.8203, "status": "ok", "correct": true, "speedup": 6.8203, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 428.8, "calls": 3, "tokens_in": 21513, "tokens_out": 24873, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524327.8934875} {"ep": "ok-00432", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "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": 213.2, "calls": 3, "tokens_in": 25498, "tokens_out": 3003, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791524328.6160777} {"ep": "ok-00339", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8832, "status": "ok", "correct": true, "speedup": 0.8832, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 586.8, "calls": 5, "tokens_in": 54611, "tokens_out": 10028, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524330.1214447} {"ep": "ok-00415", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9336, "status": "ok", "correct": true, "speedup": 0.9336, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 289.1, "calls": 4, "tokens_in": 328830, "tokens_out": 9440, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524336.6788251} {"ep": "ok-00429", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff"], "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": 227.6, "calls": 3, "tokens_in": 17846, "tokens_out": 3549, "ctx_chars": 5518, "ctx_sha": "7180f8dff0056426", "t_end": 1791524340.018803} {"ep": "ok-00381", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0312, "status": "ok", "correct": true, "speedup": 1.0312, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 453.6, "calls": 2, "tokens_in": 16320, "tokens_out": 2377, "ctx_chars": 13736, "ctx_sha": "1ff228bcf6371290", "t_end": 1791524340.0444915} {"ep": "ok-00377", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8281, "status": "ok", "correct": true, "speedup": 0.8281, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 466.8, "calls": 2, "tokens_in": 11375, "tokens_out": 20573, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524341.8231206} {"ep": "ok-00362", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3085, "status": "ok", "correct": true, "speedup": 0.3085, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 524.0, "calls": 3, "tokens_in": 23364, "tokens_out": 4215, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791524347.0745592} {"ep": "ok-00437", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657", "ker-f5807f0030"], "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": 220.7, "calls": 2, "tokens_in": 8870, "tokens_out": 5043, "ctx_chars": 3636, "ctx_sha": "c4e20fc881ca2568", "t_end": 1791524347.1086748} {"ep": "ok-00458", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0251, "status": "ok", "correct": true, "speedup": 1.0251, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 122.2, "calls": 3, "tokens_in": 16831, "tokens_out": 1966, "ctx_chars": 7308, "ctx_sha": "cb4e925a23b3095d", "t_end": 1791524352.2281296} {"ep": "ok-00438", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.819, "status": "ok", "correct": true, "speedup": 0.819, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 223.5, "calls": 2, "tokens_in": 165726, "tokens_out": 10010, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524358.4001613} {"ep": "ok-00461", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0339, "status": "ok", "correct": true, "speedup": 1.0339, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 124.7, "calls": 2, "tokens_in": 10287, "tokens_out": 2868, "ctx_chars": 6332, "ctx_sha": "985655908be45697", "t_end": 1791524362.701381} {"ep": "ok-00451", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.1159, "status": "ok", "correct": true, "speedup": 0.1159, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 161.7, "calls": 4, "tokens_in": 31644, "tokens_out": 4848, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791524362.8294306} {"ep": "ok-00321", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7416, "status": "ok", "correct": true, "speedup": 0.7416, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 706.2, "calls": 5, "tokens_in": 56771, "tokens_out": 11015, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524365.5584383} {"ep": "ok-00385", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 11.3773, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 458.6, "calls": 3, "tokens_in": 20802, "tokens_out": 28069, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524367.7234979} {"ep": "ok-00428", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 260.0, "calls": 2, "tokens_in": 159496, "tokens_out": 6882, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524370.547017} {"ep": "ok-00332", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 653.2, "calls": 4, "tokens_in": 19189, "tokens_out": 10603, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524371.476891} {"ep": "ok-00434", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 264.8, "calls": 2, "tokens_in": 159928, "tokens_out": 6538, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524381.8542447} {"ep": "ok-00457", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0378, "status": "ok", "correct": true, "speedup": 1.0378, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 164.4, "calls": 2, "tokens_in": 5014, "tokens_out": 3084, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524389.8791833} {"ep": "ok-00439", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.1062, "status": "ok", "correct": true, "speedup": 0.1062, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 257.5, "calls": 4, "tokens_in": 31284, "tokens_out": 4775, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791524393.5563345} {"ep": "ok-00367", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0259, "status": "ok", "correct": true, "speedup": 1.0259, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 563.7, "calls": 2, "tokens_in": 10660, "tokens_out": 2080, "ctx_chars": 6811, "ctx_sha": "fcadd21f6f40e59e", "t_end": 1791524400.7737763} {"ep": "ok-00422", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5972, "status": "ok", "correct": true, "speedup": 0.5972, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 316.5, "calls": 2, "tokens_in": 10224, "tokens_out": 14204, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524401.2740018} {"ep": "ok-00380", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3"], "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": 520.4, "calls": 5, "tokens_in": 22510, "tokens_out": 3232, "ctx_chars": 3492, "ctx_sha": "8e815cc7e524fc7b", "t_end": 1791524403.7452302} {"ep": "ok-00459", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 179.4, "calls": 3, "tokens_in": 24707, "tokens_out": 1893, "ctx_chars": 13736, "ctx_sha": "f9598e6429f01c39", "t_end": 1791524416.6950984} {"ep": "ok-00490", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0976, "status": "ok", "correct": true, "speedup": 1.0976, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 57.5, "calls": 1, "tokens_in": 7684, "tokens_out": 1073, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791524420.189072} {"ep": "ok-00449", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.1136, "status": "ok", "correct": true, "speedup": 0.1136, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 242.8, "calls": 3, "tokens_in": 26537, "tokens_out": 6649, "ctx_chars": 8141, "ctx_sha": "6911e5d55595673c", "t_end": 1791524425.2617047} {"ep": "ok-00328", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0207, "status": "ok", "correct": true, "speedup": 1.0207, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 726.5, "calls": 2, "tokens_in": 5586, "tokens_out": 2829, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524427.5943773} {"ep": "ok-00379", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 548.1, "calls": 2, "tokens_in": 158908, "tokens_out": 4365, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524429.2979608} {"ep": "ok-00390", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "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": 503.3, "calls": 3, "tokens_in": 17670, "tokens_out": 14973, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524432.7887444} {"ep": "ok-00477", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8239, "status": "ok", "correct": true, "speedup": 0.8239, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 126.5, "calls": 2, "tokens_in": 10338, "tokens_out": 5038, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524435.2951822} {"ep": "ok-00442", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": false, "score": 1.0019, "status": "ok", "correct": true, "speedup": 1.0019, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 279.6, "calls": 5, "tokens_in": 37995, "tokens_out": 7454, "ctx_chars": 6127, "ctx_sha": "6d5266a306356454", "t_end": 1791524438.5223284} {"ep": "ok-00474", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.7933, "status": "ok", "correct": true, "speedup": 0.7933, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 167.0, "calls": 2, "tokens_in": 6380, "tokens_out": 1636, "ctx_chars": 1993, "ctx_sha": "e81d6bc04df8963f", "t_end": 1791524451.0633616} {"ep": "ok-00443", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9759, "status": "ok", "correct": true, "speedup": 0.9759, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 294.3, "calls": 4, "tokens_in": 334377, "tokens_out": 13074, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524456.804497} {"ep": "ok-00482", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "p_item": null, "p_policy": null, "success": true, "score": 1.0116, "status": "ok", "correct": true, "speedup": 1.0116, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 122.0, "calls": 3, "tokens_in": 11646, "tokens_out": 6573, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791524458.705415} {"ep": "ok-00485", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 131.8, "calls": 2, "tokens_in": 14179, "tokens_out": 2697, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791524473.6162226} {"ep": "ok-00467", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0349, "status": "ok", "correct": true, "speedup": 1.0349, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 215.1, "calls": 2, "tokens_in": 6375, "tokens_out": 6252, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524477.4725556} {"ep": "ok-00498", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'fold_bn_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fold_bn_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", "wall_s": 99.5, "calls": 1, "tokens_in": 2759, "tokens_out": 2883, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524493.0645351} {"ep": "ok-00466", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.1104, "status": "ok", "correct": true, "speedup": 0.1104, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 239.1, "calls": 3, "tokens_in": 22900, "tokens_out": 4541, "ctx_chars": 8141, "ctx_sha": "6911e5d55595673c", "t_end": 1791524500.6837835} {"ep": "ok-00413", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7969, "status": "ok", "correct": true, "speedup": 0.7969, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 468.5, "calls": 4, "tokens_in": 338605, "tokens_out": 13623, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524505.6208339} {"ep": "ok-00472", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.1006, "status": "ok", "correct": true, "speedup": 1.1006, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 225.0, "calls": 3, "tokens_in": 29118, "tokens_out": 2209, "ctx_chars": 16078, "ctx_sha": "44ad9fe30fc2339e", "t_end": 1791524506.2581995} {"ep": "ok-00506", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'relu_gn_ext': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=relu_gn_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", "wall_s": 85.5, "calls": 1, "tokens_in": 1876, "tokens_out": 1811, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524514.821651} {"ep": "ok-00510", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0348, "status": "ok", "correct": true, "speedup": 1.0348, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 68.7, "calls": 2, "tokens_in": 4899, "tokens_out": 2991, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524519.759083} {"ep": "ok-00454", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0135, "status": "ok", "correct": true, "speedup": 1.0135, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 301.9, "calls": 2, "tokens_in": 5378, "tokens_out": 4979, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524520.96228} {"ep": "ok-00456", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 33.2881, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 297.5, "calls": 2, "tokens_in": 7450, "tokens_out": 5506, "ctx_chars": 2256, "ctx_sha": "5bcd96aec06b92bc", "t_end": 1791524522.7273517} {"ep": "ok-00491", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.9845, "status": "ok", "correct": true, "speedup": 0.9845, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 161.5, "calls": 3, "tokens_in": 22307, "tokens_out": 2903, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791524524.2816236} {"ep": "ok-00484", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.2967, "status": "ok", "correct": true, "speedup": 0.2967, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 188.6, "calls": 3, "tokens_in": 20451, "tokens_out": 4133, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524528.6196249} {"ep": "ok-00486", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0099, "status": "ok", "correct": true, "speedup": 1.0099, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 188.6, "calls": 3, "tokens_in": 21824, "tokens_out": 2303, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791524535.655811} {"ep": "ok-00421", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.1079, "status": "ok", "correct": true, "speedup": 6.1079, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 468.7, "calls": 3, "tokens_in": 29718, "tokens_out": 30339, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524537.3205104} {"ep": "ok-00424", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.1413, "status": "ok", "correct": true, "speedup": 7.1413, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 449.1, "calls": 3, "tokens_in": 27935, "tokens_out": 21240, "ctx_chars": 7644, "ctx_sha": "1bcf1308b5ca023c", "t_end": 1791524538.8164456} {"ep": "ok-00418", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.5373, "status": "ok", "correct": true, "speedup": 5.5373, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 487.1, "calls": 2, "tokens_in": 10617, "tokens_out": 20400, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524543.7198427} {"ep": "ok-00479", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "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": 216.4, "calls": 2, "tokens_in": 5784, "tokens_out": 5955, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524544.3266752} {"ep": "ok-00480", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4"], "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": 217.2, "calls": 2, "tokens_in": 11664, "tokens_out": 4238, "ctx_chars": 7221, "ctx_sha": "c76ebe5823d3165a", "t_end": 1791524545.8087192} {"ep": "ok-00476", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.344, "status": "ok", "correct": true, "speedup": 1.344, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 259.6, "calls": 2, "tokens_in": 160235, "tokens_out": 11846, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524550.1190171} {"ep": "ok-00489", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9335, "status": "ok", "correct": true, "speedup": 0.9335, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 200.3, "calls": 2, "tokens_in": 16891, "tokens_out": 4865, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791524558.6579142} {"ep": "ok-00513", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0304, "status": "ok", "correct": true, "speedup": 1.0304, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 85.2, "calls": 1, "tokens_in": 1933, "tokens_out": 3243, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524558.828515} {"ep": "ok-00460", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.9127, "status": "ok", "correct": true, "speedup": 0.9127, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 322.7, "calls": 3, "tokens_in": 18089, "tokens_out": 5980, "ctx_chars": 2169, "ctx_sha": "4663d45691d76c7e", "t_end": 1791524560.530347} {"ep": "ok-00478", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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: no class ModelNew defined", "wall_s": 245.6, "calls": 4, "tokens_in": 34565, "tokens_out": 4260, "ctx_chars": 12555, "ctx_sha": "fb438aa3b57cd542", "t_end": 1791524560.6184626} {"ep": "ok-00464", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7776, "status": "ok", "correct": true, "speedup": 0.7776, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 314.9, "calls": 4, "tokens_in": 35524, "tokens_out": 6531, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791524562.1080506} {"ep": "ok-00465", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3"], "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": 314.3, "calls": 5, "tokens_in": 25406, "tokens_out": 4462, "ctx_chars": 3492, "ctx_sha": "8e815cc7e524fc7b", "t_end": 1791524562.2338355} {"ep": "ok-00481", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7558, "status": "ok", "correct": true, "speedup": 0.7558, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 252.4, "calls": 3, "tokens_in": 15555, "tokens_out": 4433, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524582.4837403} {"ep": "ok-00509", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.2992, "status": "ok", "correct": true, "speedup": 0.2992, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 144.3, "calls": 3, "tokens_in": 20446, "tokens_out": 4161, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524582.8298197} {"ep": "ok-00444", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.533, "status": "ok", "correct": true, "speedup": 1.533, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 420.2, "calls": 2, "tokens_in": 160333, "tokens_out": 13690, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524587.9988015} {"ep": "ok-00507", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4"], "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": 161.2, "calls": 3, "tokens_in": 20282, "tokens_out": 2863, "ctx_chars": 9128, "ctx_sha": "055c3b32ed6a1efe", "t_end": 1791524593.9732797} {"ep": "ok-00492", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8735, "status": "ok", "correct": true, "speedup": 0.8735, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 241.4, "calls": 5, "tokens_in": 56556, "tokens_out": 10601, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524606.976268} {"ep": "ok-00520", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "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": 100.8, "calls": 3, "tokens_in": 12690, "tokens_out": 1909, "ctx_chars": 4565, "ctx_sha": "77e8064d2cc468b9", "t_end": 1791524620.5425317} {"ep": "ok-00516", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 44.5395, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 123.5, "calls": 2, "tokens_in": 7408, "tokens_out": 6748, "ctx_chars": 2016, "ctx_sha": "a2bb82d0a90ca3de", "t_end": 1791524624.1623} {"ep": "ok-00525", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.9978, "status": "ok", "correct": true, "speedup": 0.9978, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 89.0, "calls": 3, "tokens_in": 22404, "tokens_out": 2949, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791524624.6373408} {"ep": "ok-00495", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": false, "score": 0.9357, "status": "ok", "correct": true, "speedup": 0.9357, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 256.8, "calls": 2, "tokens_in": 19083, "tokens_out": 4905, "ctx_chars": 15603, "ctx_sha": "3f3a125c98fd04bf", "t_end": 1791524628.321658} {"ep": "ok-00535", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 69.0, "calls": 3, "tokens_in": 20118, "tokens_out": 1898, "ctx_chars": 9950, "ctx_sha": "cbff30e3b5d0d366", "t_end": 1791524629.5955088} {"ep": "ok-00531", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0966, "status": "ok", "correct": true, "speedup": 1.0966, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 80.4, "calls": 2, "tokens_in": 18975, "tokens_out": 2150, "ctx_chars": 16078, "ctx_sha": "44ad9fe30fc2339e", "t_end": 1791524630.5538676} {"ep": "ok-00511", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2607, "status": "ok", "correct": true, "speedup": 1.2607, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 176.6, "calls": 2, "tokens_in": 159371, "tokens_out": 7796, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524633.4409292} {"ep": "ok-00497", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8712, "status": "ok", "correct": true, "speedup": 0.8712, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 244.3, "calls": 2, "tokens_in": 160144, "tokens_out": 4280, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524634.1588001} {"ep": "ok-00494", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-4cfeee51c1", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7566, "status": "ok", "correct": true, "speedup": 0.7566, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 266.5, "calls": 3, "tokens_in": 14881, "tokens_out": 4503, "ctx_chars": 1884, "ctx_sha": "a37a18ff81bf7ac3", "t_end": 1791524636.99964} {"ep": "ok-00469", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 5.977, "status": "ok", "correct": true, "speedup": 5.977, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 380.5, "calls": 3, "tokens_in": 31379, "tokens_out": 24371, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791524653.1973803} {"ep": "ok-00419", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 3.9167, "status": "ok", "correct": true, "speedup": 3.9167, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 592.7, "calls": 3, "tokens_in": 249413, "tokens_out": 26183, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524653.3533015} {"ep": "ok-00446", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7977, "status": "ok", "correct": true, "speedup": 0.7977, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 484.9, "calls": 4, "tokens_in": 336641, "tokens_out": 12686, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524656.2674568} {"ep": "ok-00488", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "p_item": null, "p_policy": null, "success": false, "score": 0.9955, "status": "ok", "correct": true, "speedup": 0.9955, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 305.3, "calls": 3, "tokens_in": 17251, "tokens_out": 2876, "ctx_chars": 7273, "ctx_sha": "1f97a75c86510f14", "t_end": 1791524657.5110867} {"ep": "ok-00534", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.7368, "status": "ok", "correct": true, "speedup": 0.7368, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 98.5, "calls": 2, "tokens_in": 6497, "tokens_out": 1697, "ctx_chars": 2270, "ctx_sha": "cbeec28bae225a7b", "t_end": 1791524659.0251033} {"ep": "ok-00523", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1074, "status": "ok", "correct": true, "speedup": 1.1074, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 144.3, "calls": 1, "tokens_in": 78394, "tokens_out": 2068, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524668.6110775} {"ep": "ok-00530", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-d10f50ba0c", "pit-69809d3cb6", "rec-21ef38357b"], "p_item": null, "p_policy": null, "success": false, "score": 0.9434, "status": "ok", "correct": true, "speedup": 0.9434, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 125.1, "calls": 2, "tokens_in": 7023, "tokens_out": 5610, "ctx_chars": 1383, "ctx_sha": "680ebcf2a2f1ebf3", "t_end": 1791524670.87582} {"ep": "ok-00524", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0381, "status": "ok", "correct": true, "speedup": 1.0381, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 157.9, "calls": 1, "tokens_in": 1933, "tokens_out": 2985, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524686.5066216} {"ep": "ok-00499", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.7836, "status": "ok", "correct": true, "speedup": 0.7836, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 288.1, "calls": 2, "tokens_in": 6489, "tokens_out": 1673, "ctx_chars": 2270, "ctx_sha": "cbeec28bae225a7b", "t_end": 1791524688.8374815} {"ep": "ok-00453", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.007, "status": "ok", "correct": true, "speedup": 0.007, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 473.5, "calls": 2, "tokens_in": 160665, "tokens_out": 6062, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524688.9516084} {"ep": "ok-00528", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4977, "status": "ok", "correct": true, "speedup": 1.4977, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 145.7, "calls": 2, "tokens_in": 5888, "tokens_out": 5846, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524689.3731425} {"ep": "ok-00468", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7841, "status": "ok", "correct": true, "speedup": 0.7841, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 427.8, "calls": 4, "tokens_in": 28239, "tokens_out": 7629, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524691.1532226} {"ep": "ok-00532", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 139.7, "calls": 2, "tokens_in": 15037, "tokens_out": 5230, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791524698.3810291} {"ep": "ok-00462", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 5.503, "status": "ok", "correct": true, "speedup": 5.503, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 460.3, "calls": 3, "tokens_in": 28298, "tokens_out": 33534, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524704.916464} {"ep": "ok-00487", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9293, "status": "ok", "correct": true, "speedup": 0.9293, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 358.2, "calls": 3, "tokens_in": 240382, "tokens_out": 6253, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524705.2745445} {"ep": "ok-00526", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.223, "status": "ok", "correct": true, "speedup": 0.223, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 168.0, "calls": 1, "tokens_in": 5329, "tokens_out": 2139, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524705.3108027} {"ep": "ok-00519", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0245, "status": "ok", "correct": true, "speedup": 1.0245, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 190.8, "calls": 2, "tokens_in": 5056, "tokens_out": 2933, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524705.6052327} {"ep": "ok-00441", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0003, "status": "ok", "correct": true, "speedup": 1.0003, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 550.7, "calls": 5, "tokens_in": 37097, "tokens_out": 3633, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791524707.1543138} {"ep": "ok-00455", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 4.568, "status": "ok", "correct": true, "speedup": 4.568, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 494.3, "calls": 3, "tokens_in": 21076, "tokens_out": 22081, "ctx_chars": 1495, "ctx_sha": "983928657b2b0e88", "t_end": 1791524714.422239} {"ep": "ok-00416", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 10.92, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 666.4, "calls": 3, "tokens_in": 28368, "tokens_out": 35551, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524716.3707218} {"ep": "ok-00436", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 4.2874, "status": "ok", "correct": true, "speedup": 4.2874, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 594.7, "calls": 3, "tokens_in": 30896, "tokens_out": 27845, "ctx_chars": 7992, "ctx_sha": "03c04da8eac89804", "t_end": 1791524718.2301593} {"ep": "ok-00533", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 47.4483, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 161.4, "calls": 2, "tokens_in": 7455, "tokens_out": 6084, "ctx_chars": 2256, "ctx_sha": "5bcd96aec06b92bc", "t_end": 1791524720.2119708} {"ep": "ok-00501", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 58.0813, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 316.6, "calls": 2, "tokens_in": 18281, "tokens_out": 8440, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791524720.3151567} {"ep": "ok-00538", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-e75be99f9e", "ker-071e045dd4"], "p_item": null, "p_policy": null, "success": true, "score": 1.0237, "status": "ok", "correct": true, "speedup": 1.0237, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 140.7, "calls": 3, "tokens_in": 18178, "tokens_out": 2956, "ctx_chars": 7245, "ctx_sha": "5c9cac21cf11798f", "t_end": 1791524723.1439304} {"ep": "ok-00500", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7608, "status": "ok", "correct": true, "speedup": 0.7608, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 327.2, "calls": 2, "tokens_in": 10620, "tokens_out": 4175, "ctx_chars": 4637, "ctx_sha": "47dd73f8ccb986e2", "t_end": 1791524728.4913535} {"ep": "ok-00471", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.2187, "status": "ok", "correct": true, "speedup": 6.2187, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 455.9, "calls": 3, "tokens_in": 27269, "tokens_out": 17429, "ctx_chars": 7644, "ctx_sha": "1bcf1308b5ca023c", "t_end": 1791524735.0971751} {"ep": "ok-00544", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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": 113.8, "calls": 1, "tokens_in": 1723, "tokens_out": 989, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524737.984394} {"ep": "ok-00493", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.995, "status": "ok", "correct": true, "speedup": 0.995, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 373.1, "calls": 3, "tokens_in": 18430, "tokens_out": 3120, "ctx_chars": 7758, "ctx_sha": "ae9fa76cd68a90a1", "t_end": 1791524740.8540711} {"ep": "ok-00537", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9258, "status": "ok", "correct": true, "speedup": 0.9258, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 180.1, "calls": 2, "tokens_in": 7062, "tokens_out": 11015, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524742.289717} {"ep": "ok-00504", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.159, "status": "ok", "correct": true, "speedup": 0.159, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 318.7, "calls": 4, "tokens_in": 18019, "tokens_out": 5470, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524743.9817383} {"ep": "ok-00448", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8163, "status": "ok", "correct": true, "speedup": 0.8163, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 565.4, "calls": 3, "tokens_in": 24759, "tokens_out": 18186, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524746.8819177} {"ep": "ok-00522", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0229, "status": "ok", "correct": true, "speedup": 1.0229, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 229.1, "calls": 2, "tokens_in": 10700, "tokens_out": 2061, "ctx_chars": 6811, "ctx_sha": "fcadd21f6f40e59e", "t_end": 1791524751.80061} {"ep": "ok-00558", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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_pool_l2_050': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=fused_pool_l2_050 -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": 81.3, "calls": 1, "tokens_in": 1960, "tokens_out": 1814, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524752.1422856} {"ep": "ok-00515", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0958, "status": "ok", "correct": true, "speedup": 1.0958, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 260.0, "calls": 3, "tokens_in": 24253, "tokens_out": 2133, "ctx_chars": 12121, "ctx_sha": "03e0667a95c5bdd5", "t_end": 1791524753.0750875} {"ep": "ok-00503", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": false, "score": 0.1725, "status": "ok", "correct": true, "speedup": 0.1725, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 336.5, "calls": 3, "tokens_in": 30199, "tokens_out": 10156, "ctx_chars": 8141, "ctx_sha": "6911e5d55595673c", "t_end": 1791524756.725109} {"ep": "ok-00470", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 19.1635, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 494.4, "calls": 2, "tokens_in": 14894, "tokens_out": 6013, "ctx_chars": 10255, "ctx_sha": "359838044746c0df", "t_end": 1791524768.2518961} {"ep": "ok-00450", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 5.0806, "status": "ok", "correct": true, "speedup": 5.0806, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 580.7, "calls": 3, "tokens_in": 33343, "tokens_out": 36856, "ctx_chars": 4637, "ctx_sha": "e562c22c78d786c2", "t_end": 1791524778.6034367} {"ep": "ok-00508", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.6763, "status": "ok", "correct": true, "speedup": 1.6763, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 345.4, "calls": 3, "tokens_in": 243837, "tokens_out": 13050, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524780.7339492} {"ep": "ok-00473", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9094, "status": "ok", "correct": true, "speedup": 0.9094, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 502.4, "calls": 4, "tokens_in": 36085, "tokens_out": 17110, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524783.7002513} {"ep": "ok-00550", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "p_item": null, "p_policy": null, "success": true, "score": 1.0245, "status": "ok", "correct": true, "speedup": 1.0245, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 151.4, "calls": 3, "tokens_in": 12672, "tokens_out": 1888, "ctx_chars": 4565, "ctx_sha": "77e8064d2cc468b9", "t_end": 1791524785.5860682} {"ep": "ok-00483", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3"], "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": 450.7, "calls": 5, "tokens_in": 24248, "tokens_out": 3957, "ctx_chars": 3492, "ctx_sha": "8e815cc7e524fc7b", "t_end": 1791524790.7229695} {"ep": "ok-00565", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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 'gn_ht': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gn_ht -DTORCH_API_INCLUDE_EXTENSION_H -I/usr/local/eval-pch -isystem /usr/local/lib/python3.10/dist-packages/torch/include -isystem /usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/api/in", "wall_s": 87.1, "calls": 1, "tokens_in": 1723, "tokens_out": 1791, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524792.0542548} {"ep": "ok-00554", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.8973, "status": "ok", "correct": true, "speedup": 0.8973, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 144.3, "calls": 3, "tokens_in": 17521, "tokens_out": 4878, "ctx_chars": 2922, "ctx_sha": "3cb6e9a4694064be", "t_end": 1791524800.5645897} {"ep": "ok-00505", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "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": 375.9, "calls": 5, "tokens_in": 22997, "tokens_out": 8555, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791524803.4702034} {"ep": "ok-00541", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.6736, "status": "ok", "correct": true, "speedup": 0.6736, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 213.3, "calls": 2, "tokens_in": 16214, "tokens_out": 12965, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791524807.3169086} {"ep": "ok-00567", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7835, "status": "ok", "correct": true, "speedup": 0.7835, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 104.2, "calls": 2, "tokens_in": 13454, "tokens_out": 4495, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524809.5368757} {"ep": "ok-00556", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0372, "status": "ok", "correct": true, "speedup": 1.0372, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 152.4, "calls": 2, "tokens_in": 15694, "tokens_out": 2874, "ctx_chars": 12848, "ctx_sha": "c5005fba182a16d4", "t_end": 1791524811.4097881} {"ep": "ok-00575", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4647, "status": "ok", "correct": true, "speedup": 1.4647, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 89.2, "calls": 2, "tokens_in": 6001, "tokens_out": 6071, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524812.3492599} {"ep": "ok-00475", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9273, "status": "ok", "correct": true, "speedup": 0.9273, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 527.5, "calls": 5, "tokens_in": 56007, "tokens_out": 25830, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524813.64908} {"ep": "ok-00529", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1002, "status": "ok", "correct": true, "speedup": 1.1002, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 271.5, "calls": 2, "tokens_in": 158872, "tokens_out": 3493, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524815.8368404} {"ep": "ok-00563", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 126.1, "calls": 3, "tokens_in": 22475, "tokens_out": 2985, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791524817.2259915} {"ep": "ok-00549", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9758, "status": "ok", "correct": true, "speedup": 0.9758, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 184.3, "calls": 2, "tokens_in": 8881, "tokens_out": 4144, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524817.6949956} {"ep": "ok-00545", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": true, "score": 1.0185, "status": "ok", "correct": true, "speedup": 1.0185, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 194.1, "calls": 3, "tokens_in": 25277, "tokens_out": 2921, "ctx_chars": 12352, "ctx_sha": "5533cb2a86547de2", "t_end": 1791524818.7413528} {"ep": "ok-00518", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 313.8, "calls": 2, "tokens_in": 160864, "tokens_out": 5303, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524820.0192108} {"ep": "ok-00557", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.097, "status": "ok", "correct": true, "speedup": 1.097, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 151.7, "calls": 1, "tokens_in": 7259, "tokens_out": 1053, "ctx_chars": 12103, "ctx_sha": "42cb8c90d2cfce7e", "t_end": 1791524820.300332} {"ep": "ok-00540", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 31.273, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 240.0, "calls": 3, "tokens_in": 32814, "tokens_out": 7795, "ctx_chars": 16078, "ctx_sha": "7102bc51b235fd0f", "t_end": 1791524827.9574156} {"ep": "ok-00543", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "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": 217.1, "calls": 3, "tokens_in": 22603, "tokens_out": 2920, "ctx_chars": 10528, "ctx_sha": "2d3203f47b184251", "t_end": 1791524837.6702845} {"ep": "ok-00580", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9944, "status": "ok", "correct": true, "speedup": 0.9944, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 95.9, "calls": 1, "tokens_in": 1605, "tokens_out": 2281, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524838.1954012} {"ep": "ok-00552", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.1749, "status": "ok", "correct": true, "speedup": 0.1749, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 190.6, "calls": 4, "tokens_in": 27976, "tokens_out": 7516, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524843.7799726} {"ep": "ok-00521", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 7.1064, "status": "ok", "correct": true, "speedup": 7.1064, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 328.2, "calls": 3, "tokens_in": 24691, "tokens_out": 28853, "ctx_chars": 1495, "ctx_sha": "983928657b2b0e88", "t_end": 1791524849.1688032} {"ep": "ok-00562", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0136, "status": "ok", "correct": true, "speedup": 1.0136, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 168.2, "calls": 3, "tokens_in": 24591, "tokens_out": 7705, "ctx_chars": 12555, "ctx_sha": "bae97e8db7be5c58", "t_end": 1791524857.5589743} {"ep": "ok-00560", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0369, "status": "ok", "correct": true, "speedup": 0.0369, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 168.8, "calls": 2, "tokens_in": 161526, "tokens_out": 6499, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524857.6867352} {"ep": "ok-00574", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0347, "status": "ok", "correct": true, "speedup": 1.0347, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 139.9, "calls": 3, "tokens_in": 22058, "tokens_out": 2848, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791524860.2407424} {"ep": "ok-00587", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8045, "status": "ok", "correct": true, "speedup": 0.8045, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 96.1, "calls": 2, "tokens_in": 13553, "tokens_out": 5435, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791524864.3453343} {"ep": "ok-00599", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0274, "status": "ok", "correct": true, "speedup": 1.0274, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 53.7, "calls": 1, "tokens_in": 1856, "tokens_out": 1044, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524866.0231543} {"ep": "ok-00592", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0377, "status": "ok", "correct": true, "speedup": 1.0377, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 80.9, "calls": 2, "tokens_in": 5133, "tokens_out": 3174, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524871.6241605} {"ep": "ok-00463", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 7.2562, "status": "ok", "correct": true, "speedup": 7.2562, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 628.5, "calls": 3, "tokens_in": 29811, "tokens_out": 29922, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524873.9630466} {"ep": "ok-00593", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0255, "status": "ok", "correct": true, "speedup": 1.0255, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 82.2, "calls": 2, "tokens_in": 4831, "tokens_out": 2591, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524874.233952} {"ep": "ok-00542", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0352, "status": "ok", "correct": true, "speedup": 1.0352, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 267.8, "calls": 2, "tokens_in": 6720, "tokens_out": 6701, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524874.79994} {"ep": "ok-00539", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8274c30657", "rec-4365468e5f", "ker-6558b83d05"], "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": 292.4, "calls": 5, "tokens_in": 31118, "tokens_out": 4510, "ctx_chars": 5534, "ctx_sha": "3d72d551b52c403d", "t_end": 1791524875.2054627} {"ep": "ok-00566", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "p_item": null, "p_policy": null, "success": true, "score": 1.0028, "status": "ok", "correct": true, "speedup": 1.0028, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 196.1, "calls": 3, "tokens_in": 10481, "tokens_out": 7465, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791524901.3961434} {"ep": "ok-00588", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 122.9, "calls": 2, "tokens_in": 17742, "tokens_out": 5740, "ctx_chars": 14186, "ctx_sha": "9cdfa12549d40778", "t_end": 1791524901.4624453} {"ep": "ok-00619", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.307, "status": "ok", "correct": true, "speedup": 0.307, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 42.3, "calls": 1, "tokens_in": 5329, "tokens_out": 2097, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791524916.5781577} {"ep": "ok-00546", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "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": 294.6, "calls": 4, "tokens_in": 25463, "tokens_out": 8549, "ctx_chars": 5978, "ctx_sha": "6db7ec2d3f2a73bf", "t_end": 1791524922.8850489} {"ep": "ok-00600", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.8916, "status": "ok", "correct": true, "speedup": 0.8916, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 110.9, "calls": 1, "tokens_in": 2489, "tokens_out": 3296, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524924.519373} {"ep": "ok-00571", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.1377, "status": "ok", "correct": true, "speedup": 0.1377, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 210.8, "calls": 5, "tokens_in": 33656, "tokens_out": 9598, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524927.2081716} {"ep": "ok-00597", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": true, "score": 1.0131, "status": "ok", "correct": true, "speedup": 1.0131, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 118.4, "calls": 2, "tokens_in": 17743, "tokens_out": 5560, "ctx_chars": 14186, "ctx_sha": "9cdfa12549d40778", "t_end": 1791524927.900433} {"ep": "ok-00548", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 1.0551, "status": "ok", "correct": true, "speedup": 1.0551, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 297.6, "calls": 5, "tokens_in": 62466, "tokens_out": 12340, "ctx_chars": 9125, "ctx_sha": "51be303cdfcd2fbe", "t_end": 1791524928.1102464} {"ep": "ok-00512", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 471.0, "calls": 4, "tokens_in": 350237, "tokens_out": 20111, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524929.6878743} {"ep": "ok-00573", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0995, "status": "ok", "correct": true, "speedup": 1.0995, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 211.3, "calls": 3, "tokens_in": 25401, "tokens_out": 2063, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791524931.494584} {"ep": "ok-00605", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.008, "status": "ok", "correct": true, "speedup": 1.008, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 115.3, "calls": 2, "tokens_in": 12093, "tokens_out": 5234, "ctx_chars": 7261, "ctx_sha": "dbcfd75c6a2698c6", "t_end": 1791524935.3113437} {"ep": "ok-00577", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.101, "status": "ok", "correct": true, "speedup": 1.101, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 203.7, "calls": 1, "tokens_in": 8863, "tokens_out": 1099, "ctx_chars": 16078, "ctx_sha": "44ad9fe30fc2339e", "t_end": 1791524938.751002} {"ep": "ok-00555", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.9567, "status": "ok", "correct": true, "speedup": 0.9567, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 285.0, "calls": 3, "tokens_in": 22779, "tokens_out": 8756, "ctx_chars": 2169, "ctx_sha": "4663d45691d76c7e", "t_end": 1791524942.5391495} {"ep": "ok-00536", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 3.667, "status": "ok", "correct": true, "speedup": 3.667, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 382.1, "calls": 2, "tokens_in": 14031, "tokens_out": 25447, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791524944.1789477} {"ep": "ok-00570", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.8126, "status": "ok", "correct": true, "speedup": 4.8126, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 237.5, "calls": 2, "tokens_in": 10408, "tokens_out": 19790, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524951.9294963} {"ep": "ok-00608", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0151, "status": "ok", "correct": true, "speedup": 1.0151, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 114.3, "calls": 2, "tokens_in": 11689, "tokens_out": 4503, "ctx_chars": 7261, "ctx_sha": "dbcfd75c6a2698c6", "t_end": 1791524951.9481337} {"ep": "ok-00559", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7757, "status": "ok", "correct": true, "speedup": 0.7757, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 274.7, "calls": 2, "tokens_in": 163386, "tokens_out": 14930, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524961.1669924} {"ep": "ok-00598", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0327, "status": "ok", "correct": true, "speedup": 1.0327, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 152.4, "calls": 2, "tokens_in": 13199, "tokens_out": 2536, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791524963.8361616} {"ep": "ok-00582", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": false, "score": 0.8229, "status": "ok", "correct": true, "speedup": 0.8229, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 217.7, "calls": 3, "tokens_in": 10555, "tokens_out": 1937, "ctx_chars": 2270, "ctx_sha": "cbeec28bae225a7b", "t_end": 1791524964.6071875} {"ep": "ok-00581", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.4902, "status": "ok", "correct": true, "speedup": 1.4902, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 220.8, "calls": 3, "tokens_in": 14062, "tokens_out": 11533, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524964.7860847} {"ep": "ok-00629", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 43.9, "calls": 1, "tokens_in": 1960, "tokens_out": 1288, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791524971.971064} {"ep": "ok-00610", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 105.936, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 133.0, "calls": 2, "tokens_in": 8223, "tokens_out": 7281, "ctx_chars": 2256, "ctx_sha": "5bcd96aec06b92bc", "t_end": 1791524976.7978086} {"ep": "ok-00578", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.5105, "status": "ok", "correct": true, "speedup": 0.5105, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 240.6, "calls": 2, "tokens_in": 9331, "tokens_out": 10166, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524978.6055415} {"ep": "ok-00591", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 75.9658, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 194.9, "calls": 2, "tokens_in": 6797, "tokens_out": 7411, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524980.4486532} {"ep": "ok-00572", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "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": 271.1, "calls": 3, "tokens_in": 9234, "tokens_out": 7118, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791524989.280889} {"ep": "ok-00564", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0443, "status": "ok", "correct": true, "speedup": 0.0443, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 292.8, "calls": 2, "tokens_in": 167281, "tokens_out": 12899, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791524991.1678853} {"ep": "ok-00585", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "p_item": null, "p_policy": null, "success": false, "score": 1.0011, "status": "ok", "correct": true, "speedup": 1.0011, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 239.1, "calls": 5, "tokens_in": 25062, "tokens_out": 8902, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791524992.1631641} {"ep": "ok-00586", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7035, "status": "ok", "correct": true, "speedup": 0.7035, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 237.9, "calls": 5, "tokens_in": 58920, "tokens_out": 11423, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791524994.6555123} {"ep": "ok-00576", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-d0dcdcbae6"], "p_item": null, "p_policy": null, "success": true, "score": 1.023, "status": "ok", "correct": true, "speedup": 1.023, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 268.0, "calls": 3, "tokens_in": 28974, "tokens_out": 2924, "ctx_chars": 15603, "ctx_sha": "a415cc777520c780", "t_end": 1791524996.5328336} {"ep": "ok-00569", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7471, "status": "ok", "correct": true, "speedup": 0.7471, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 293.3, "calls": 2, "tokens_in": 13675, "tokens_out": 7023, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791525000.4404693} {"ep": "ok-00553", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7487, "status": "ok", "correct": true, "speedup": 0.7487, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 349.1, "calls": 3, "tokens_in": 28684, "tokens_out": 10079, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791525002.4539495} {"ep": "ok-00502", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 6.3316, "status": "ok", "correct": true, "speedup": 6.3316, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 594.2, "calls": 3, "tokens_in": 25062, "tokens_out": 20452, "ctx_chars": 2713, "ctx_sha": "d18291fca1598bb8", "t_end": 1791525010.9393122} {"ep": "ok-00647", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 25.6, "calls": 1, "tokens_in": 1814, "tokens_out": 1982, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525016.7661438} {"ep": "ok-00596", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7862, "status": "ok", "correct": true, "speedup": 0.7862, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 212.4, "calls": 2, "tokens_in": 13358, "tokens_out": 5780, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791525019.7407217} {"ep": "ok-00496", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-33cd992453", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 6.7965, "status": "ok", "correct": true, "speedup": 6.7965, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 641.5, "calls": 3, "tokens_in": 21324, "tokens_out": 23756, "ctx_chars": 1495, "ctx_sha": "983928657b2b0e88", "t_end": 1791525023.3372273} {"ep": "ok-00514", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6484, "status": "ok", "correct": true, "speedup": 0.6484, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 549.1, "calls": 3, "tokens_in": 244465, "tokens_out": 12594, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525026.5741494} {"ep": "ok-00609", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.0008, "status": "ok", "correct": true, "speedup": 1.0008, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 199.3, "calls": 2, "tokens_in": 12092, "tokens_out": 5219, "ctx_chars": 7261, "ctx_sha": "dbcfd75c6a2698c6", "t_end": 1791525037.5333037} {"ep": "ok-00655", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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": 19.0, "calls": 1, "tokens_in": 1681, "tokens_out": 698, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525038.7000918} {"ep": "ok-00618", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 40.1287, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 167.2, "calls": 2, "tokens_in": 15564, "tokens_out": 7046, "ctx_chars": 10255, "ctx_sha": "359838044746c0df", "t_end": 1791525041.2064376} {"ep": "ok-00561", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "pit-c5e387d239"], "p_item": null, "p_policy": null, "success": true, "score": 8.7859, "status": "ok", "correct": true, "speedup": 8.7859, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 357.8, "calls": 3, "tokens_in": 20818, "tokens_out": 21348, "ctx_chars": 696, "ctx_sha": "4047841f6f5065d2", "t_end": 1791525046.786107} {"ep": "ok-00642", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f5807f0030", "ker-4a82a14d5e"], "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": 74.9, "calls": 2, "tokens_in": 12025, "tokens_out": 5274, "ctx_chars": 7549, "ctx_sha": "f0881682a422c1e8", "t_end": 1791525046.82791} {"ep": "ok-00611", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8911, "status": "ok", "correct": true, "speedup": 0.8911, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 198.4, "calls": 3, "tokens_in": 20044, "tokens_out": 13350, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525047.542696} {"ep": "ok-00604", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4947, "status": "ok", "correct": true, "speedup": 1.4947, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 230.8, "calls": 2, "tokens_in": 6773, "tokens_out": 9043, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525049.561861} {"ep": "ok-00621", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 176.2, "calls": 5, "tokens_in": 35838, "tokens_out": 9395, "ctx_chars": 5630, "ctx_sha": "1d3288f4ac875b68", "t_end": 1791525051.4182909} {"ep": "ok-00623", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 153.4, "calls": 3, "tokens_in": 20116, "tokens_out": 1893, "ctx_chars": 9950, "ctx_sha": "cbff30e3b5d0d366", "t_end": 1791525054.8353658} {"ep": "ok-00590", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9237, "status": "ok", "correct": true, "speedup": 0.9237, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 272.5, "calls": 3, "tokens_in": 13312, "tokens_out": 5886, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525056.193924} {"ep": "ok-00638", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0976, "status": "ok", "correct": true, "speedup": 1.0976, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 98.5, "calls": 3, "tokens_in": 24211, "tokens_out": 2104, "ctx_chars": 12121, "ctx_sha": "03e0667a95c5bdd5", "t_end": 1791525059.6703544} {"ep": "ok-00613", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "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": 204.4, "calls": 5, "tokens_in": 32377, "tokens_out": 4359, "ctx_chars": 6127, "ctx_sha": "6d5266a306356454", "t_end": 1791525062.089153} {"ep": "ok-00631", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.6554, "status": "ok", "correct": true, "speedup": 0.6554, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 133.7, "calls": 2, "tokens_in": 16019, "tokens_out": 10255, "ctx_chars": 9125, "ctx_sha": "e44fb9b172e13ebf", "t_end": 1791525065.2302332} {"ep": "ok-00637", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0, "status": "no_custom_kernel", "correct": false, "speedup": 0.0, "infra": false, "infra_reruns": 0, "error": "none of the candidate's kernels ['_add_relu_kernel', '_relu_kernel'] ran on the GPU during forward (torch-only paths are not a kernel)", "wall_s": 115.2, "calls": 1, "tokens_in": 2917, "tokens_out": 5377, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525067.1823332} {"ep": "ok-00606", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": false, "score": 0.9983, "status": "ok", "correct": true, "speedup": 0.9983, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 249.0, "calls": 5, "tokens_in": 36767, "tokens_out": 3621, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791525069.2649636} {"ep": "ok-00602", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8268, "status": "ok", "correct": true, "speedup": 0.8268, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 259.7, "calls": 2, "tokens_in": 161806, "tokens_out": 6480, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525076.9236763} {"ep": "ok-00645", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "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 'gemv_sum_mod': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemv_sum_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": 98.0, "calls": 1, "tokens_in": 1681, "tokens_out": 1148, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525078.4322453} {"ep": "ok-00517", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285"], "p_item": null, "p_policy": null, "success": true, "score": 5.5018, "status": "ok", "correct": true, "speedup": 5.5018, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 573.1, "calls": 3, "tokens_in": 28331, "tokens_out": 34080, "ctx_chars": 369, "ctx_sha": "92409fabb91e61c8", "t_end": 1791525078.703284} {"ep": "ok-00656", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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 'gemv_divsum': [1/3] c++ -MMD -MF main.o.d -DTORCH_EXTENSION_NAME=gemv_divsum -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": 65.2, "calls": 1, "tokens_in": 1814, "tokens_out": 1256, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525088.570481} {"ep": "ok-00607", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.4096, "status": "ok", "correct": true, "speedup": 1.4096, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 275.9, "calls": 2, "tokens_in": 7118, "tokens_out": 9630, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525103.877298} {"ep": "ok-00579", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6938, "status": "ok", "correct": true, "speedup": 0.6938, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 363.0, "calls": 4, "tokens_in": 38271, "tokens_out": 9096, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791525103.8782446} {"ep": "ok-00654", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "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": 88.4, "calls": 3, "tokens_in": 20975, "tokens_out": 4249, "ctx_chars": 7010, "ctx_sha": "303c2eea0b6f8387", "t_end": 1791525105.167462} {"ep": "ok-00626", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6973, "status": "ok", "correct": true, "speedup": 0.6973, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 192.3, "calls": 3, "tokens_in": 20912, "tokens_out": 13804, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525116.7893162} {"ep": "ok-00663", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "p_item": null, "p_policy": null, "success": false, "score": 0.9975, "status": "ok", "correct": true, "speedup": 0.9975, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 70.1, "calls": 3, "tokens_in": 17313, "tokens_out": 2907, "ctx_chars": 7273, "ctx_sha": "1f97a75c86510f14", "t_end": 1791525117.664857} {"ep": "ok-00551", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.6161, "status": "ok", "correct": true, "speedup": 6.6161, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 502.9, "calls": 3, "tokens_in": 30295, "tokens_out": 24058, "ctx_chars": 7644, "ctx_sha": "1bcf1308b5ca023c", "t_end": 1791525139.9295797} {"ep": "ok-00628", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0256, "status": "ok", "correct": true, "speedup": 1.0256, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 212.2, "calls": 3, "tokens_in": 20100, "tokens_out": 1872, "ctx_chars": 9950, "ctx_sha": "cbff30e3b5d0d366", "t_end": 1791525140.140464} {"ep": "ok-00633", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "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": 205.4, "calls": 3, "tokens_in": 17191, "tokens_out": 7557, "ctx_chars": 5978, "ctx_sha": "6db7ec2d3f2a73bf", "t_end": 1791525144.1961966} {"ep": "ok-00612", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 287.3, "calls": 2, "tokens_in": 16228, "tokens_out": 2121, "ctx_chars": 13736, "ctx_sha": "1ff228bcf6371290", "t_end": 1791525144.8939025} {"ep": "ok-00527", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 8.3297, "status": "ok", "correct": true, "speedup": 8.3297, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 612.0, "calls": 4, "tokens_in": 25217, "tokens_out": 25160, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525150.863673} {"ep": "ok-00620", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0332, "status": "ok", "correct": true, "speedup": 1.0332, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 278.7, "calls": 2, "tokens_in": 6013, "tokens_out": 5375, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525153.4768965} {"ep": "ok-00589", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 6.2841, "status": "ok", "correct": true, "speedup": 6.2841, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 379.2, "calls": 2, "tokens_in": 12273, "tokens_out": 25158, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525159.980517} {"ep": "ok-00636", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 1.0329, "status": "ok", "correct": true, "speedup": 1.0329, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 209.5, "calls": 2, "tokens_in": 7333, "tokens_out": 4551, "ctx_chars": 2175, "ctx_sha": "86963271ef726410", "t_end": 1791525161.4178455} {"ep": "ok-00653", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9334, "status": "ok", "correct": true, "speedup": 0.9334, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 154.0, "calls": 3, "tokens_in": 242020, "tokens_out": 6687, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525164.900723} {"ep": "ok-00644", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9993, "status": "ok", "correct": true, "speedup": 0.9993, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 196.1, "calls": 3, "tokens_in": 9050, "tokens_out": 3276, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525174.7010684} {"ep": "ok-00547", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9326, "status": "ok", "correct": true, "speedup": 0.9326, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 552.2, "calls": 4, "tokens_in": 38779, "tokens_out": 22034, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525181.7723734} {"ep": "ok-00650", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030", "ker-4a82a14d5e"], "p_item": null, "p_policy": null, "success": false, "score": 0.9952, "status": "ok", "correct": true, "speedup": 0.9952, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 185.8, "calls": 2, "tokens_in": 17752, "tokens_out": 5333, "ctx_chars": 14186, "ctx_sha": "9cdfa12549d40778", "t_end": 1791525182.334284} {"ep": "ok-00635", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.8434, "status": "ok", "correct": true, "speedup": 0.8434, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 238.6, "calls": 2, "tokens_in": 12037, "tokens_out": 5967, "ctx_chars": 4637, "ctx_sha": "47dd73f8ccb986e2", "t_end": 1791525182.7389517} {"ep": "ok-00670", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "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": 119.1, "calls": 3, "tokens_in": 17018, "tokens_out": 2155, "ctx_chars": 7308, "ctx_sha": "cb4e925a23b3095d", "t_end": 1791525184.3424332} {"ep": "ok-00639", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 231.5, "calls": 5, "tokens_in": 38613, "tokens_out": 4127, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791525195.329297} {"ep": "ok-00651", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0247, "status": "ok", "correct": true, "speedup": 1.0247, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 195.6, "calls": 2, "tokens_in": 13636, "tokens_out": 4698, "ctx_chars": 8788, "ctx_sha": "796f186ac3130710", "t_end": 1791525196.0723321} {"ep": "ok-00657", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-d10f50ba0c", "pit-69809d3cb6", "rec-21ef38357b"], "p_item": null, "p_policy": null, "success": false, "score": 0.9377, "status": "ok", "correct": true, "speedup": 0.9377, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 172.6, "calls": 2, "tokens_in": 7033, "tokens_out": 5304, "ctx_chars": 1383, "ctx_sha": "680ebcf2a2f1ebf3", "t_end": 1791525199.141172} {"ep": "ok-00667", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3002, "status": "ok", "correct": true, "speedup": 0.3002, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 146.5, "calls": 3, "tokens_in": 20102, "tokens_out": 4262, "ctx_chars": 6059, "ctx_sha": "fcbd714fceba4ac3", "t_end": 1791525202.6718779} {"ep": "ok-00594", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.1547, "status": "ok", "correct": true, "speedup": 0.1547, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 404.1, "calls": 2, "tokens_in": 11692, "tokens_out": 22220, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525204.67209} {"ep": "ok-00632", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9129, "status": "ok", "correct": true, "speedup": 0.9129, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 273.0, "calls": 2, "tokens_in": 8802, "tokens_out": 5451, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525208.3515973} {"ep": "ok-00617", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 9.3978, "status": "ok", "correct": true, "speedup": 9.3978, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 337.6, "calls": 2, "tokens_in": 17201, "tokens_out": 17022, "ctx_chars": 10587, "ctx_sha": "bc692baaaeca6a2f", "t_end": 1791525209.1985855} {"ep": "ok-00661", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-69809d3cb6", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4"], "p_item": null, "p_policy": null, "success": true, "score": 1.035, "status": "ok", "correct": true, "speedup": 1.035, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 163.1, "calls": 3, "tokens_in": 20331, "tokens_out": 2908, "ctx_chars": 9128, "ctx_sha": "055c3b32ed6a1efe", "t_end": 1791525209.8969948} {"ep": "ok-00584", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 4.9513, "status": "ok", "correct": true, "speedup": 4.9513, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 459.4, "calls": 3, "tokens_in": 26800, "tokens_out": 29269, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525211.58747} {"ep": "ok-00658", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-e79cba77da", "les-d10f50ba0c", "les-d9b41ee5fa", "les-6405d23c44", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "rec-7d67d21ded"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 74.1312, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 178.8, "calls": 2, "tokens_in": 8805, "tokens_out": 8068, "ctx_chars": 2256, "ctx_sha": "5bcd96aec06b92bc", "t_end": 1791525216.2835486} {"ep": "ok-00669", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f5807f0030"], "p_item": null, "p_policy": null, "success": false, "score": 0.9955, "status": "ok", "correct": true, "speedup": 0.9955, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 163.2, "calls": 3, "tokens_in": 17264, "tokens_out": 2849, "ctx_chars": 7333, "ctx_sha": "42fc92cfe0f03f33", "t_end": 1791525225.3067944} {"ep": "ok-00648", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 233.4, "calls": 3, "tokens_in": 10511, "tokens_out": 8339, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525225.518648} {"ep": "ok-00603", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 1.2172, "status": "ok", "correct": true, "speedup": 1.2172, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 413.9, "calls": 3, "tokens_in": 243802, "tokens_out": 6114, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525231.5850227} {"ep": "ok-00668", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1025, "status": "ok", "correct": true, "speedup": 1.1025, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 176.6, "calls": 4, "tokens_in": 19836, "tokens_out": 5079, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525236.2636793} {"ep": "ok-00659", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 198.1, "calls": 2, "tokens_in": 12123, "tokens_out": 7450, "ctx_chars": 2425, "ctx_sha": "5c5e8811718de973", "t_end": 1791525236.8062582} {"ep": "ok-00614", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "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": 377.7, "calls": 5, "tokens_in": 32301, "tokens_out": 4205, "ctx_chars": 6127, "ctx_sha": "6d5266a306356454", "t_end": 1791525237.9109716} {"ep": "ok-00674", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": true, "score": 1.0364, "status": "ok", "correct": true, "speedup": 1.0364, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 161.4, "calls": 2, "tokens_in": 5317, "tokens_out": 3531, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525239.8636858} {"ep": "ok-00643", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7563, "status": "ok", "correct": true, "speedup": 0.7563, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 266.7, "calls": 3, "tokens_in": 27390, "tokens_out": 13106, "ctx_chars": 5888, "ctx_sha": "9bd167fbd898e624", "t_end": 1791525243.5329528} {"ep": "ok-00665", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-ae3c5733ff", "ker-38bc1e9f51"], "p_item": null, "p_policy": null, "success": true, "score": 1.0336, "status": "ok", "correct": true, "speedup": 1.0336, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 193.7, "calls": 3, "tokens_in": 19963, "tokens_out": 3999, "ctx_chars": 6481, "ctx_sha": "2281995c87ed0a4b", "t_end": 1791525245.105885} {"ep": "ok-00625", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8148, "status": "ok", "correct": true, "speedup": 0.8148, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 322.9, "calls": 2, "tokens_in": 163964, "tokens_out": 17393, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525245.7606528} {"ep": "ok-00679", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "p_item": null, "p_policy": null, "success": true, "score": 1.0253, "status": "ok", "correct": true, "speedup": 1.0253, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 145.7, "calls": 3, "tokens_in": 12570, "tokens_out": 1786, "ctx_chars": 4565, "ctx_sha": "77e8064d2cc468b9", "t_end": 1791525250.8870363} {"ep": "ok-00685", "task": "L2_061", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-24bf5ba8a9", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-a172f35135", "rec-001120b436", "rec-e75be99f9e", "ker-071e045dd4"], "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": 108.4, "calls": 3, "tokens_in": 18330, "tokens_out": 2988, "ctx_chars": 7245, "ctx_sha": "5c9cac21cf11798f", "t_end": 1791525253.2919474} {"ep": "ok-00697", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657"], "p_item": null, "p_policy": null, "success": true, "score": 1.0371, "status": "ok", "correct": true, "speedup": 1.0371, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 57.6, "calls": 2, "tokens_in": 5433, "tokens_out": 2690, "ctx_chars": 768, "ctx_sha": "74e5521f8e62f4de", "t_end": 1791525253.6773627} {"ep": "ok-00687", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.4088, "status": "ok", "correct": true, "speedup": 1.4088, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 105.6, "calls": 2, "tokens_in": 5678, "tokens_out": 5284, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525259.0875092} {"ep": "ok-00627", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0348, "status": "ok", "correct": true, "speedup": 1.0348, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 333.0, "calls": 2, "tokens_in": 163678, "tokens_out": 13121, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525260.1994045} {"ep": "ok-00583", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.4863, "status": "ok", "correct": true, "speedup": 7.4863, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 515.5, "calls": 3, "tokens_in": 247854, "tokens_out": 22318, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525267.2834542} {"ep": "ok-00700", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.294, "status": "ok", "correct": true, "speedup": 0.294, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 65.0, "calls": 3, "tokens_in": 19809, "tokens_out": 4091, "ctx_chars": 6059, "ctx_sha": "fcbd714fceba4ac3", "t_end": 1791525269.6972487} {"ep": "ok-00615", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.1019, "status": "ok", "correct": true, "speedup": 1.1019, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 408.5, "calls": 4, "tokens_in": 24682, "tokens_out": 6464, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525272.8790588} {"ep": "ok-00704", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 64.7, "calls": 2, "tokens_in": 10864, "tokens_out": 2360, "ctx_chars": 6811, "ctx_sha": "fcadd21f6f40e59e", "t_end": 1791525276.2745066} {"ep": "ok-00698", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-8b7c11b862", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd"], "p_item": null, "p_policy": null, "success": true, "score": 1.0322, "status": "ok", "correct": true, "speedup": 1.0322, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 78.6, "calls": 3, "tokens_in": 13927, "tokens_out": 2658, "ctx_chars": 3968, "ctx_sha": "1e8d83b857da86fb", "t_end": 1791525277.736328} {"ep": "ok-00703", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.7427, "status": "ok", "correct": true, "speedup": 0.7427, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 68.8, "calls": 2, "tokens_in": 9089, "tokens_out": 4140, "ctx_chars": 2169, "ctx_sha": "4663d45691d76c7e", "t_end": 1791525278.6603389} {"ep": "ok-00689", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "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": 119.9, "calls": 3, "tokens_in": 24402, "tokens_out": 8165, "ctx_chars": 4637, "ctx_sha": "47dd73f8ccb986e2", "t_end": 1791525281.2883897} {"ep": "ok-00672", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": 213.3, "calls": 2, "tokens_in": 10708, "tokens_out": 2115, "ctx_chars": 6811, "ctx_sha": "fcadd21f6f40e59e", "t_end": 1791525282.5983143} {"ep": "ok-00677", "task": "L2_022", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0343, "status": "ok", "correct": true, "speedup": 1.0343, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 179.7, "calls": 3, "tokens_in": 21665, "tokens_out": 2772, "ctx_chars": 9546, "ctx_sha": "fcb53f6a93403e98", "t_end": 1791525283.5292084} {"ep": "ok-00568", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.8661, "status": "ok", "correct": true, "speedup": 0.8661, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 582.1, "calls": 5, "tokens_in": 52747, "tokens_out": 9851, "ctx_chars": 5802, "ctx_sha": "c3f789aa6f5dcf18", "t_end": 1791525287.7098382} {"ep": "ok-00701", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-f1f0450765", "ker-370fab9980"], "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": 81.8, "calls": 2, "tokens_in": 13796, "tokens_out": 2085, "ctx_chars": 10373, "ctx_sha": "a70e73b80ca58faf", "t_end": 1791525290.1329238} {"ep": "ok-00673", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.9948, "status": "ok", "correct": true, "speedup": 0.9948, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 215.1, "calls": 3, "tokens_in": 22333, "tokens_out": 2898, "ctx_chars": 10823, "ctx_sha": "20b7935cf56f91ca", "t_end": 1791525292.063885} {"ep": "ok-00681", "task": "L2_033", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.9977, "status": "ok", "correct": true, "speedup": 0.9977, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 177.8, "calls": 4, "tokens_in": 24263, "tokens_out": 7571, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525295.4910061} {"ep": "ok-00694", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 27.8537, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 113.2, "calls": 3, "tokens_in": 29294, "tokens_out": 7032, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791525295.9011288} {"ep": "ok-00666", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "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": 248.6, "calls": 4, "tokens_in": 30855, "tokens_out": 7273, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791525303.4294882} {"ep": "ok-00684", "task": "L2_030", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 163.4, "calls": 1, "tokens_in": 1856, "tokens_out": 1069, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525307.555456} {"ep": "ok-00595", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 504.2, "calls": 4, "tokens_in": 322463, "tokens_out": 9378, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525307.683317} {"ep": "ok-00706", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0983, "status": "ok", "correct": true, "speedup": 1.0983, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 83.0, "calls": 3, "tokens_in": 25613, "tokens_out": 2208, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791525308.3485053} {"ep": "ok-00641", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 346.3, "calls": 5, "tokens_in": 407027, "tokens_out": 6236, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525311.0558264} {"ep": "ok-00718", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.0999, "status": "ok", "correct": true, "speedup": 1.0999, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 58.3, "calls": 3, "tokens_in": 29093, "tokens_out": 2173, "ctx_chars": 16078, "ctx_sha": "44ad9fe30fc2339e", "t_end": 1791525311.9580452} {"ep": "ok-00702", "task": "L2_030", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-f1f0450765", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": true, "score": 1.0324, "status": "ok", "correct": true, "speedup": 1.0324, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 104.6, "calls": 2, "tokens_in": 10917, "tokens_out": 2506, "ctx_chars": 7159, "ctx_sha": "1ccf94064353eca4", "t_end": 1791525313.8103797} {"ep": "ok-00691", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.623, "status": "ok", "correct": true, "speedup": 0.623, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 140.2, "calls": 2, "tokens_in": 8607, "tokens_out": 9291, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525314.9063435} {"ep": "ok-00716", "task": "L2_050", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.1002, "status": "ok", "correct": true, "speedup": 1.1002, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 64.5, "calls": 1, "tokens_in": 7684, "tokens_out": 1081, "ctx_chars": 12888, "ctx_sha": "c0dcc8ddc9a91092", "t_end": 1791525315.3936625} {"ep": "ok-00646", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7948, "status": "ok", "correct": true, "speedup": 0.7948, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 332.2, "calls": 3, "tokens_in": 248324, "tokens_out": 9992, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525321.507936} {"ep": "ok-00688", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.6873, "status": "ok", "correct": true, "speedup": 0.6873, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 163.2, "calls": 3, "tokens_in": 243898, "tokens_out": 5595, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525323.1453104} {"ep": "ok-00652", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 6.2228, "status": "ok", "correct": true, "speedup": 6.2228, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 327.3, "calls": 3, "tokens_in": 28418, "tokens_out": 18920, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791525329.742092} {"ep": "ok-00616", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "p_item": null, "p_policy": null, "success": false, "score": 0.8211, "status": "ok", "correct": true, "speedup": 0.8211, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 465.0, "calls": 5, "tokens_in": 59776, "tokens_out": 20414, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525331.03792} {"ep": "ok-00622", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7189, "status": "ok", "correct": true, "speedup": 0.7189, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 433.3, "calls": 5, "tokens_in": 51645, "tokens_out": 13930, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525334.6509337} {"ep": "ok-00660", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "rec-97181ed7d3", "rec-8bd287f31a", "rec-d2c54a1922", "rec-8274c30657", "rec-4365468e5f", "rec-63e1a542cd", "ker-6558b83d05", "ker-370fab9980"], "p_item": null, "p_policy": null, "success": false, "score": 0.998, "status": "ok", "correct": true, "speedup": 0.998, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 293.8, "calls": 5, "tokens_in": 35280, "tokens_out": 2621, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791525335.0251896} {"ep": "ok-00634", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8355, "status": "ok", "correct": true, "speedup": 0.8355, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 394.7, "calls": 4, "tokens_in": 339015, "tokens_out": 13457, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525337.220477} {"ep": "ok-00601", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7693, "status": "ok", "correct": true, "speedup": 0.7693, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 521.5, "calls": 5, "tokens_in": 57521, "tokens_out": 11126, "ctx_chars": 6513, "ctx_sha": "1aa698d3a9589f25", "t_end": 1791525337.3005393} {"ep": "ok-00630", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 6.0002, "status": "ok", "correct": true, "speedup": 6.0002, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 409.6, "calls": 3, "tokens_in": 31165, "tokens_out": 20752, "ctx_chars": 10587, "ctx_sha": "bc692baaaeca6a2f", "t_end": 1791525339.2697957} {"ep": "ok-00664", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-6ea0c69e03", "pit-474c4e4cdf", "pit-b4c54d1d46", "pit-83f095e15c", "pit-25393eeb09", "pit-8b7c11b862", "ker-6558b83d05", "ker-370fab9980"], "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": 291.2, "calls": 4, "tokens_in": 25793, "tokens_out": 7534, "ctx_chars": 5978, "ctx_sha": "6db7ec2d3f2a73bf", "t_end": 1791525340.7180445} {"ep": "ok-00683", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.0844, "status": "ok", "correct": true, "speedup": 0.0844, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 212.8, "calls": 2, "tokens_in": 164493, "tokens_out": 9607, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525352.961204} {"ep": "ok-00712", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.1189, "status": "ok", "correct": true, "speedup": 0.1189, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 117.6, "calls": 4, "tokens_in": 38094, "tokens_out": 6753, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791525357.4845521} {"ep": "ok-00715", "task": "L2_033", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["rec-8274c30657", "ker-f5807f0030"], "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": 117.1, "calls": 2, "tokens_in": 9959, "tokens_out": 7296, "ctx_chars": 3636, "ctx_sha": "c4e20fc881ca2568", "t_end": 1791525362.8770676} {"ep": "ok-00708", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-69809d3cb6", "pit-0d52154172", "pit-4e0e42c44e", "pit-9be3ce52bf", "pit-65672ca4bf", "rec-21ef38357b", "rec-a172f35135", "rec-001120b436", "rec-edeef3809c", "rec-7d67d21ded", "rec-e75be99f9e", "ker-071e045dd4", "ker-49cd13f98a"], "p_item": null, "p_policy": null, "success": true, "score": 1.7744, "status": "ok", "correct": true, "speedup": 1.7744, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 143.8, "calls": 3, "tokens_in": 35263, "tokens_out": 11037, "ctx_chars": 16078, "ctx_sha": "7102bc51b235fd0f", "t_end": 1791525375.3454626} {"ep": "ok-00707", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "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": 162.5, "calls": 5, "tokens_in": 23857, "tokens_out": 9219, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525388.0231297} {"ep": "ok-00699", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_tables_select", "ctx_arm": null, "mask": ["les-93e64733c9", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7627, "status": "ok", "correct": true, "speedup": 0.7627, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 187.9, "calls": 5, "tokens_in": 55606, "tokens_out": 11081, "ctx_chars": 5802, "ctx_sha": "c3f789aa6f5dcf18", "t_end": 1791525390.5726595} {"ep": "ok-00682", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 253.6, "calls": 5, "tokens_in": 49470, "tokens_out": 10960, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525393.5549157} {"ep": "ok-00693", "task": "L3_023", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.2429, "status": "ok", "correct": true, "speedup": 1.2429, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 215.3, "calls": 2, "tokens_in": 11219, "tokens_out": 20466, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525397.6738179} {"ep": "ok-00692", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "organ_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.7626, "status": "ok", "correct": true, "speedup": 0.7626, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 217.0, "calls": 4, "tokens_in": 46544, "tokens_out": 19559, "ctx_chars": 6861, "ctx_sha": "9b6e0a6de2f42888", "t_end": 1791525398.7689216} {"ep": "ok-00676", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "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": 312.1, "calls": 3, "tokens_in": 239612, "tokens_out": 9369, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525400.6263936} {"ep": "ok-00709", "task": "L3_040", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.1181, "status": "ok", "correct": true, "speedup": 0.1181, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 165.5, "calls": 4, "tokens_in": 28565, "tokens_out": 8336, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525401.7754776} {"ep": "ok-00662", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 5.7398, "status": "ok", "correct": true, "speedup": 5.7398, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 371.1, "calls": 2, "tokens_in": 164624, "tokens_out": 28166, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525417.949381} {"ep": "ok-00686", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 269.4, "calls": 4, "tokens_in": 41944, "tokens_out": 23346, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525420.262749} {"ep": "ok-00675", "task": "L3_023", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.3029, "status": "ok", "correct": true, "speedup": 0.3029, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 352.3, "calls": 3, "tokens_in": 20122, "tokens_out": 4154, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791525431.0095453} {"ep": "ok-00690", "task": "L2_022", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.3631, "status": "ok", "correct": true, "speedup": 1.3631, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 288.6, "calls": 3, "tokens_in": 243672, "tokens_out": 12142, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525453.5408745} {"ep": "ok-00640", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.8089, "status": "ok", "correct": true, "speedup": 0.8089, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 490.8, "calls": 5, "tokens_in": 45654, "tokens_out": 10199, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525455.3710194} {"ep": "ok-00695", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285"], "p_item": null, "p_policy": null, "success": true, "score": 5.997, "status": "ok", "correct": true, "speedup": 5.997, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 279.3, "calls": 3, "tokens_in": 26013, "tokens_out": 28274, "ctx_chars": 369, "ctx_sha": "92409fabb91e61c8", "t_end": 1791525463.6561944} {"ep": "ok-00624", "task": "L3_010", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["prior", "les-93e64733c9", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-24bf5ba8a9", "les-5c37cab285", "pit-263235db52", "pit-06df4b1c90", "pit-720c125700", "pit-3a07b0abdd", "rec-04ea4c7983", "ker-5a91e892c6"], "p_item": null, "p_policy": null, "success": false, "score": 0.6236, "status": "ok", "correct": true, "speedup": 0.6236, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 557.6, "calls": 5, "tokens_in": 56807, "tokens_out": 11103, "ctx_chars": 6417, "ctx_sha": "c0c0cdc9f418388a", "t_end": 1791525474.1388545} {"ep": "ok-00705", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 7.6355, "status": "ok", "correct": true, "speedup": 7.6355, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 260.7, "calls": 3, "tokens_in": 33547, "tokens_out": 24170, "ctx_chars": 10587, "ctx_sha": "bc692baaaeca6a2f", "t_end": 1791525476.9684334} {"ep": "ok-00680", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285", "rec-97181ed7d3"], "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": 373.8, "calls": 4, "tokens_in": 16690, "tokens_out": 7269, "ctx_chars": 1080, "ctx_sha": "6e25c78196dc23dc", "t_end": 1791525490.617981} {"ep": "ok-00696", "task": "L3_032", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": false, "score": 0.9367, "status": "ok", "correct": true, "speedup": 0.9367, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 299.7, "calls": 3, "tokens_in": 22110, "tokens_out": 6509, "ctx_chars": 4637, "ctx_sha": "47dd73f8ccb986e2", "t_end": 1791525495.0300927} {"ep": "ok-00678", "task": "L2_014", "split": "probe", "reader": "claude-opus-4-8", "policy": "online", "arm": "provenance", "ctx_arm": "living:rC", "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": "outputs produced during timing do not match the reference (output mismatch beyond atol=rtol=0.0001); results must not be cached or skipped", "wall_s": 398.0, "calls": 5, "tokens_in": 37856, "tokens_out": 4485, "ctx_chars": 9192, "ctx_sha": "9ac79c33be050f60", "t_end": 1791525501.9116762} {"ep": "ok-00717", "task": "L3_040", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "show_all", "ctx_arm": null, "mask": ["les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-33cd992453", "pit-c5e387d239", "pit-72f6005e71", "pit-b924c52976", "pit-8b9dc1534f", "pit-fb58481a1f", "rec-b5dde2147d", "ker-abc5cb7218", "ker-dfc8d8394b"], "p_item": null, "p_policy": null, "success": true, "score": 6.9873, "status": "ok", "correct": true, "speedup": 6.9873, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 283.0, "calls": 3, "tokens_in": 31898, "tokens_out": 28245, "ctx_chars": 8224, "ctx_sha": "71fd1a97cbd02e3b", "t_end": 1791525536.3312848} {"ep": "ok-00713", "task": "L2_050", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 10.0, "status": "ok", "correct": true, "speedup": 83.2035, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 311.8, "calls": 2, "tokens_in": 160323, "tokens_out": 8631, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525555.3022435} {"ep": "ok-00671", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "annotated_all", "ctx_arm": null, "mask": ["prior", "les-15e9e8569f", "les-93e64733c9", "les-4cfeee51c1", "les-e79cba77da", "les-1a767e9b1b", "les-0aec41e64f", "les-11e399176f", "les-d10f50ba0c", "les-d9b41ee5fa", "les-49a7dd4aa1", "les-6405d23c44", "les-24bf5ba8a9", "les-6c7acdf532", "les-5c37cab285", "pit-d5872964f6", "pit-8435e9ebfe"], "p_item": null, "p_policy": null, "success": true, "score": 6.5574, "status": "ok", "correct": true, "speedup": 6.5574, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 527.0, "calls": 3, "tokens_in": 37036, "tokens_out": 42863, "ctx_chars": 4637, "ctx_sha": "e562c22c78d786c2", "t_end": 1791525594.1745322} {"ep": "ok-00710", "task": "L2_014", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "prior", "ctx_arm": null, "mask": ["prior"], "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": 357.6, "calls": 5, "tokens_in": 31214, "tokens_out": 14580, "ctx_chars": 495, "ctx_sha": "2f9f2d27b23856b0", "t_end": 1791525594.3953302} {"ep": "ok-00719", "task": "L2_061", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "ace", "ctx_arm": "ace", "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 1.0361, "status": "ok", "correct": true, "speedup": 1.0361, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 356.6, "calls": 2, "tokens_in": 159882, "tokens_out": 7728, "ctx_chars": 182830, "ctx_sha": "ad8a8989f86b9bbb", "t_end": 1791525615.729736} {"ep": "ok-00714", "task": "L3_010", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": false, "score": 0.7437, "status": "ok", "correct": true, "speedup": 0.7437, "infra": false, "infra_reruns": 0, "error": "ok", "wall_s": 387.5, "calls": 3, "tokens_in": 18614, "tokens_out": 10528, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525632.603011} {"ep": "ok-00649", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "opus_digest_select", "ctx_arm": null, "mask": ["les-5c37cab285"], "p_item": null, "p_policy": null, "success": true, "score": 5.4235, "status": "ok", "correct": true, "speedup": 5.4235, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 699.3, "calls": 3, "tokens_in": 25770, "tokens_out": 28975, "ctx_chars": 369, "ctx_sha": "92409fabb91e61c8", "t_end": 1791525693.9229095} {"ep": "ok-00711", "task": "L3_032", "split": "probe", "reader": "claude-opus-5-5", "policy": "online", "arm": "bare", "ctx_arm": null, "mask": [], "p_item": null, "p_policy": null, "success": true, "score": 7.2076, "status": "ok", "correct": true, "speedup": 7.2076, "infra": false, "infra_reruns": 0, "error": "", "wall_s": 468.1, "calls": 3, "tokens_in": 27732, "tokens_out": 33734, "ctx_chars": 0, "ctx_sha": "e3b0c44298fc1c14", "t_end": 1791525706.011594}