{ "format": 1, "kind": "live-ab-claude-result", "generatedAt": "2026-10-29T11:09:57.404Z", "provider": "apimaster", "baseUrl": "https://apimaster.ai/v1", "model": "claude-opus-5-5", "method": "live-ab.mjs --emit-prompts batch prompts; OpenAI-compatible /chat/completions; exact-FACT grading; tail membership saved", "seeds": [ { "seed": 1, "turns": 300, "tailCount": 20, "tailIds": [ "mem_301ddcbed7", "mem_5d0361e5e6", "mem_85a0e06d9e", "mem_a4e37d982c", "mem_08aacf4f4c", "mem_476735d740", "mem_cc70bc2942", "mem_326fe38c69", "mem_ffa587151a", "mem_014048b9df", "mem_4707859af3", "mem_68db023620", "mem_95a24894f1", "mem_e246ceff93", "mem_129e60ed43", "mem_3599496614", "mem_81c799664a", "mem_feea8fe2f8", "mem_17b1e838ec", "mem_1a6865b594" ], "probes": 20, "evictedProbes": 19, "control": { "rows": [ { "index": 0, "turn": 0, "topic": "gateway", "expected": "FACT-000-mkorf", "id": "mem_13e4cd5d45", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 1, "turn": 15, "topic": "router", "expected": "FACT-015-03jmy", "id": "mem_ef1fa3b5f6", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 2, "turn": 30, "topic": "gateway", "expected": "FACT-030-izkkh", "id": "mem_ca1b70b920", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 3, "turn": 45, "topic": "router", "expected": "FACT-045-zbfww", "id": "mem_8460938b5d", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 4, "turn": 60, "topic": "gateway", "expected": "FACT-060-yv0n0", "id": "mem_97a6023191", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 5, "turn": 75, "topic": "router", "expected": "FACT-075-a4b5x", "id": "mem_6caca224b1", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 6, "turn": 90, "topic": "gateway", "expected": "FACT-090-m28ly", "id": "mem_7e8fc3f46c", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 7, "turn": 105, "topic": "router", "expected": "FACT-105-py2zp", "id": "mem_1f628f3b43", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 8, "turn": 120, "topic": "gateway", "expected": "FACT-120-fbtzd", "id": "mem_a02671f031", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 9, "turn": 135, "topic": "router", "expected": "FACT-135-ztagj", "id": "mem_d33836747c", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 10, "turn": 150, "topic": "gateway", "expected": "FACT-150-ge14o", "id": "mem_717e7a9d1c", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 11, "turn": 165, "topic": "router", "expected": "FACT-165-hlgwo", "id": "mem_505d9cb8c0", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 12, "turn": 180, "topic": "gateway", "expected": "FACT-180-50232", "id": "mem_c4ef08c237", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 13, "turn": 195, "topic": "router", "expected": "FACT-195-ej946", "id": "mem_501cd54aee", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 14, "turn": 210, "topic": "gateway", "expected": "FACT-210-8wsh3", "id": "mem_751915d50b", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 15, "turn": 225, "topic": "router", "expected": "FACT-225-5k815", "id": "mem_400400f190", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 16, "turn": 240, "topic": "gateway", "expected": "FACT-240-hlxhw", "id": "mem_688a3a3222", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 17, "turn": 255, "topic": "router", "expected": "FACT-255-2fb7j", "id": "mem_cc0003d596", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 18, "turn": 270, "topic": "gateway", "expected": "FACT-270-e7fcx", "id": "mem_a41f20f720", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 19, "turn": 285, "topic": "router", "expected": "FACT-285-rm66w", "id": "mem_476735d740", "inTail": true, "evicted": false, "answer": "FACT-285-rm66w", "correct": true } ], "correct": 1, "total": 20 }, "treatment": { "rows": [ { "index": 0, "turn": 0, "topic": "gateway", "expected": "FACT-000-mkorf", "id": "mem_13e4cd5d45", "inTail": false, "evicted": true, "answer": "FACT-000-mkorf", "correct": true }, { "index": 1, "turn": 15, "topic": "router", "expected": "FACT-015-03jmy", "id": "mem_ef1fa3b5f6", "inTail": false, "evicted": true, "answer": "FACT-015-03jmy", "correct": true }, { "index": 2, "turn": 30, "topic": "gateway", "expected": "FACT-030-izkkh", "id": "mem_ca1b70b920", "inTail": false, "evicted": true, "answer": "FACT-030-izkkh", "correct": true }, { "index": 3, "turn": 45, "topic": "router", "expected": "FACT-045-zbfww", "id": "mem_8460938b5d", "inTail": false, "evicted": true, "answer": "FACT-045-zbfww", "correct": true }, { "index": 4, "turn": 60, "topic": "gateway", "expected": "FACT-060-yv0n0", "id": "mem_97a6023191", "inTail": false, "evicted": true, "answer": "FACT-060-yv0n0", "correct": true }, { "index": 5, "turn": 75, "topic": "router", "expected": "FACT-075-a4b5x", "id": "mem_6caca224b1", "inTail": false, "evicted": true, "answer": "FACT-075-a4b5x", "correct": true }, { "index": 6, "turn": 90, "topic": "gateway", "expected": "FACT-090-m28ly", "id": "mem_7e8fc3f46c", "inTail": false, "evicted": true, "answer": "FACT-090-m28ly", "correct": true }, { "index": 7, "turn": 105, "topic": "router", "expected": "FACT-105-py2zp", "id": "mem_1f628f3b43", "inTail": false, "evicted": true, "answer": "FACT-105-py2zp", "correct": true }, { "index": 8, "turn": 120, "topic": "gateway", "expected": "FACT-120-fbtzd", "id": "mem_a02671f031", "inTail": false, "evicted": true, "answer": "FACT-120-fbtzd", "correct": true }, { "index": 9, "turn": 135, "topic": "router", "expected": "FACT-135-ztagj", "id": "mem_d33836747c", "inTail": false, "evicted": true, "answer": "FACT-135-ztagj", "correct": true }, { "index": 10, "turn": 150, "topic": "gateway", "expected": "FACT-150-ge14o", "id": "mem_717e7a9d1c", "inTail": false, "evicted": true, "answer": "FACT-150-ge14o", "correct": true }, { "index": 11, "turn": 165, "topic": "router", "expected": "FACT-165-hlgwo", "id": "mem_505d9cb8c0", "inTail": false, "evicted": true, "answer": "FACT-165-hlgwo", "correct": true }, { "index": 12, "turn": 180, "topic": "gateway", "expected": "FACT-180-50232", "id": "mem_c4ef08c237", "inTail": false, "evicted": true, "answer": "FACT-180-50232", "correct": true }, { "index": 13, "turn": 195, "topic": "router", "expected": "FACT-195-ej946", "id": "mem_501cd54aee", "inTail": false, "evicted": true, "answer": "FACT-195-ej946", "correct": true }, { "index": 14, "turn": 210, "topic": "gateway", "expected": "FACT-210-8wsh3", "id": "mem_751915d50b", "inTail": false, "evicted": true, "answer": "FACT-210-8wsh3", "correct": true }, { "index": 15, "turn": 225, "topic": "router", "expected": "FACT-225-5k815", "id": "mem_400400f190", "inTail": false, "evicted": true, "answer": "FACT-225-5k815", "correct": true }, { "index": 16, "turn": 240, "topic": "gateway", "expected": "FACT-240-hlxhw", "id": "mem_688a3a3222", "inTail": false, "evicted": true, "answer": "FACT-240-hlxhw", "correct": true }, { "index": 17, "turn": 255, "topic": "router", "expected": "FACT-255-2fb7j", "id": "mem_cc0003d596", "inTail": false, "evicted": true, "answer": "FACT-255-2fb7j", "correct": true }, { "index": 18, "turn": 270, "topic": "gateway", "expected": "FACT-270-e7fcx", "id": "mem_a41f20f720", "inTail": false, "evicted": true, "answer": "FACT-270-e7fcx", "correct": true }, { "index": 19, "turn": 285, "topic": "router", "expected": "FACT-285-rm66w", "id": "mem_476735d740", "inTail": true, "evicted": false, "answer": "FACT-285-rm66w", "correct": true } ], "correct": 20, "total": 20 } }, { "seed": 2, "turns": 300, "tailCount": 20, "tailIds": [ "mem_cfec18b604", "mem_debc6733e9", "mem_1860b918c2", "mem_320fc85469", "mem_49d53f7fa0", "mem_cd5b5795f1", "mem_174c133836", "mem_1f9b9c964b", "mem_c6568ee4e3", "mem_d5611297ed", "mem_174a50828d", "mem_8bb77ebf7b", "mem_beec4d324d", "mem_efc4bcc8cd", "mem_672757afa3", "mem_8f368b475a", "mem_a9985a524c", "mem_d5891fe977", "mem_ddbc06d5cf", "mem_b27cdfa6ff" ], "probes": 20, "evictedProbes": 19, "control": { "rows": [ { "index": 0, "turn": 0, "topic": "gateway", "expected": "FACT-000-qfl7m", "id": "mem_4ca097172c", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 1, "turn": 15, "topic": "router", "expected": "FACT-015-bp74k", "id": "mem_416f0e3506", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 2, "turn": 30, "topic": "gateway", "expected": "FACT-030-a9qrt", "id": "mem_fb2e572cde", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 3, "turn": 45, "topic": "router", "expected": "FACT-045-jd6u3", "id": "mem_be89fc2d2e", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 4, "turn": 60, "topic": "gateway", "expected": "FACT-060-vidfn", "id": "mem_8644c1c355", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 5, "turn": 75, "topic": "router", "expected": "FACT-075-mpk5r", "id": "mem_237d63d396", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 6, "turn": 90, "topic": "gateway", "expected": "FACT-090-hyyqy", "id": "mem_8ef808ec95", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 7, "turn": 105, "topic": "router", "expected": "FACT-105-cuzlu", "id": "mem_d6c4cdf382", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 8, "turn": 120, "topic": "gateway", "expected": "FACT-120-s4xt8", "id": "mem_be3bf48249", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 9, "turn": 135, "topic": "router", "expected": "FACT-135-43s9i", "id": "mem_fc9bf8b707", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 10, "turn": 150, "topic": "gateway", "expected": "FACT-150-saher", "id": "mem_b776561ec7", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 11, "turn": 165, "topic": "router", "expected": "FACT-165-797as", "id": "mem_fc21c90064", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 12, "turn": 180, "topic": "gateway", "expected": "FACT-180-f9so7", "id": "mem_ab802f2f60", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 13, "turn": 195, "topic": "router", "expected": "FACT-195-u25n2", "id": "mem_8fff17c12f", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 14, "turn": 210, "topic": "gateway", "expected": "FACT-210-kxe32", "id": "mem_ac4b38d72c", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 15, "turn": 225, "topic": "router", "expected": "FACT-225-52qt3", "id": "mem_a8f56a834c", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 16, "turn": 240, "topic": "gateway", "expected": "FACT-240-o77fl", "id": "mem_62459a796a", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 17, "turn": 255, "topic": "router", "expected": "FACT-255-d78oa", "id": "mem_2883dbd324", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 18, "turn": 270, "topic": "gateway", "expected": "FACT-270-yz7lh", "id": "mem_1a8be20aa2", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 19, "turn": 285, "topic": "router", "expected": "FACT-285-1esyu", "id": "mem_49d53f7fa0", "inTail": true, "evicted": false, "answer": "FACT-285-1esyu", "correct": true } ], "correct": 1, "total": 20 }, "treatment": { "rows": [ { "index": 0, "turn": 0, "topic": "gateway", "expected": "FACT-000-qfl7m", "id": "mem_4ca097172c", "inTail": false, "evicted": true, "answer": "FACT-000-qfl7m", "correct": true }, { "index": 1, "turn": 15, "topic": "router", "expected": "FACT-015-bp74k", "id": "mem_416f0e3506", "inTail": false, "evicted": true, "answer": "FACT-015-bp74k", "correct": true }, { "index": 2, "turn": 30, "topic": "gateway", "expected": "FACT-030-a9qrt", "id": "mem_fb2e572cde", "inTail": false, "evicted": true, "answer": "FACT-030-a9qrt", "correct": true }, { "index": 3, "turn": 45, "topic": "router", "expected": "FACT-045-jd6u3", "id": "mem_be89fc2d2e", "inTail": false, "evicted": true, "answer": "FACT-045-jd6u3", "correct": true }, { "index": 4, "turn": 60, "topic": "gateway", "expected": "FACT-060-vidfn", "id": "mem_8644c1c355", "inTail": false, "evicted": true, "answer": "FACT-060-vidfn", "correct": true }, { "index": 5, "turn": 75, "topic": "router", "expected": "FACT-075-mpk5r", "id": "mem_237d63d396", "inTail": false, "evicted": true, "answer": "FACT-075-mpk5r", "correct": true }, { "index": 6, "turn": 90, "topic": "gateway", "expected": "FACT-090-hyyqy", "id": "mem_8ef808ec95", "inTail": false, "evicted": true, "answer": "FACT-090-hyyqy", "correct": true }, { "index": 7, "turn": 105, "topic": "router", "expected": "FACT-105-cuzlu", "id": "mem_d6c4cdf382", "inTail": false, "evicted": true, "answer": "FACT-105-cuzlu", "correct": true }, { "index": 8, "turn": 120, "topic": "gateway", "expected": "FACT-120-s4xt8", "id": "mem_be3bf48249", "inTail": false, "evicted": true, "answer": "FACT-120-s4xt8", "correct": true }, { "index": 9, "turn": 135, "topic": "router", "expected": "FACT-135-43s9i", "id": "mem_fc9bf8b707", "inTail": false, "evicted": true, "answer": "FACT-135-43s9i", "correct": true }, { "index": 10, "turn": 150, "topic": "gateway", "expected": "FACT-150-saher", "id": "mem_b776561ec7", "inTail": false, "evicted": true, "answer": "FACT-150-saher", "correct": true }, { "index": 11, "turn": 165, "topic": "router", "expected": "FACT-165-797as", "id": "mem_fc21c90064", "inTail": false, "evicted": true, "answer": "FACT-165-797as", "correct": true }, { "index": 12, "turn": 180, "topic": "gateway", "expected": "FACT-180-f9so7", "id": "mem_ab802f2f60", "inTail": false, "evicted": true, "answer": "FACT-180-f9so7", "correct": true }, { "index": 13, "turn": 195, "topic": "router", "expected": "FACT-195-u25n2", "id": "mem_8fff17c12f", "inTail": false, "evicted": true, "answer": "FACT-195-u25n2", "correct": true }, { "index": 14, "turn": 210, "topic": "gateway", "expected": "FACT-210-kxe32", "id": "mem_ac4b38d72c", "inTail": false, "evicted": true, "answer": "FACT-210-kxe32", "correct": true }, { "index": 15, "turn": 225, "topic": "router", "expected": "FACT-225-52qt3", "id": "mem_a8f56a834c", "inTail": false, "evicted": true, "answer": "FACT-225-52qt3", "correct": true }, { "index": 16, "turn": 240, "topic": "gateway", "expected": "FACT-240-o77fl", "id": "mem_62459a796a", "inTail": false, "evicted": true, "answer": "FACT-240-o77fl", "correct": true }, { "index": 17, "turn": 255, "topic": "router", "expected": "FACT-255-d78oa", "id": "mem_2883dbd324", "inTail": false, "evicted": true, "answer": "FACT-255-d78oa", "correct": true }, { "index": 18, "turn": 270, "topic": "gateway", "expected": "FACT-270-yz7lh", "id": "mem_1a8be20aa2", "inTail": false, "evicted": true, "answer": "FACT-270-yz7lh", "correct": true }, { "index": 19, "turn": 285, "topic": "router", "expected": "FACT-285-1esyu", "id": "mem_49d53f7fa0", "inTail": true, "evicted": false, "answer": "FACT-285-1esyu", "correct": true } ], "correct": 20, "total": 20 } }, { "seed": 3, "turns": 300, "tailCount": 20, "tailIds": [ "mem_c7a6d9437e", "mem_06cc8b2cbe", "mem_2ef646c703", "mem_9e0602d27b", "mem_c484dd9d34", "mem_f8989500f1", "mem_1989fe21f7", "mem_50e3fd8863", "mem_aa53324bfd", "mem_ac7a03173c", "mem_4495037a11", "mem_564ded9012", "mem_788b425652", "mem_8b7f15ae73", "mem_2c7a65b5bd", "mem_a8f02c5a31", "mem_db3fe89e39", "mem_db7d6c27b9", "mem_f6bf9ab505", "mem_7d6686e37c" ], "probes": 20, "evictedProbes": 19, "control": { "rows": [ { "index": 0, "turn": 0, "topic": "gateway", "expected": "FACT-000-pxewf", "id": "mem_c8e28367b4", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 1, "turn": 15, "topic": "router", "expected": "FACT-015-1e3tl", "id": "mem_fa44bd4492", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 2, "turn": 30, "topic": "gateway", "expected": "FACT-030-gf83p", "id": "mem_b774f3c4a2", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 3, "turn": 45, "topic": "router", "expected": "FACT-045-2p3ua", "id": "mem_e378351f94", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 4, "turn": 60, "topic": "gateway", "expected": "FACT-060-rgus2", "id": "mem_9bd4e25c97", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 5, "turn": 75, "topic": "router", "expected": "FACT-075-hblyb", "id": "mem_830c02a70e", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 6, "turn": 90, "topic": "gateway", "expected": "FACT-090-hisus", "id": "mem_161f8ed912", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 7, "turn": 105, "topic": "router", "expected": "FACT-105-5toyt", "id": "mem_8101a93d7a", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 8, "turn": 120, "topic": "gateway", "expected": "FACT-120-9h6hf", "id": "mem_2461b3b250", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 9, "turn": 135, "topic": "router", "expected": "FACT-135-jw6fx", "id": "mem_cee1019da7", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 10, "turn": 150, "topic": "gateway", "expected": "FACT-150-70m0g", "id": "mem_1e1ca1297d", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 11, "turn": 165, "topic": "router", "expected": "FACT-165-30c3x", "id": "mem_8f39a7480a", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 12, "turn": 180, "topic": "gateway", "expected": "FACT-180-pp2gq", "id": "mem_b728eb8a28", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 13, "turn": 195, "topic": "router", "expected": "FACT-195-h5u81", "id": "mem_41f66b21a3", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 14, "turn": 210, "topic": "gateway", "expected": "FACT-210-skod2", "id": "mem_1e2eb0dba0", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 15, "turn": 225, "topic": "router", "expected": "FACT-225-vo6pc", "id": "mem_8f825d8529", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 16, "turn": 240, "topic": "gateway", "expected": "FACT-240-bnezh", "id": "mem_5811f57b75", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 17, "turn": 255, "topic": "router", "expected": "FACT-255-ouzrk", "id": "mem_4213aa33d4", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 18, "turn": 270, "topic": "gateway", "expected": "FACT-270-abmgy", "id": "mem_3a1e02d66a", "inTail": false, "evicted": true, "answer": "UNKNOWN", "correct": false }, { "index": 19, "turn": 285, "topic": "router", "expected": "FACT-285-o73dt", "id": "mem_f8989500f1", "inTail": true, "evicted": false, "answer": "FACT-285-o73dt", "correct": true } ], "correct": 1, "total": 20 }, "treatment": { "rows": [ { "index": 0, "turn": 0, "topic": "gateway", "expected": "FACT-000-pxewf", "id": "mem_c8e28367b4", "inTail": false, "evicted": true, "answer": "FACT-000-pxewf", "correct": true }, { "index": 1, "turn": 15, "topic": "router", "expected": "FACT-015-1e3tl", "id": "mem_fa44bd4492", "inTail": false, "evicted": true, "answer": "FACT-015-1e3tl", "correct": true }, { "index": 2, "turn": 30, "topic": "gateway", "expected": "FACT-030-gf83p", "id": "mem_b774f3c4a2", "inTail": false, "evicted": true, "answer": "FACT-030-gf83p", "correct": true }, { "index": 3, "turn": 45, "topic": "router", "expected": "FACT-045-2p3ua", "id": "mem_e378351f94", "inTail": false, "evicted": true, "answer": "FACT-045-2p3ua", "correct": true }, { "index": 4, "turn": 60, "topic": "gateway", "expected": "FACT-060-rgus2", "id": "mem_9bd4e25c97", "inTail": false, "evicted": true, "answer": "FACT-060-rgus2", "correct": true }, { "index": 5, "turn": 75, "topic": "router", "expected": "FACT-075-hblyb", "id": "mem_830c02a70e", "inTail": false, "evicted": true, "answer": "FACT-075-hblyb", "correct": true }, { "index": 6, "turn": 90, "topic": "gateway", "expected": "FACT-090-hisus", "id": "mem_161f8ed912", "inTail": false, "evicted": true, "answer": "FACT-090-hisus", "correct": true }, { "index": 7, "turn": 105, "topic": "router", "expected": "FACT-105-5toyt", "id": "mem_8101a93d7a", "inTail": false, "evicted": true, "answer": "FACT-105-5toyt", "correct": true }, { "index": 8, "turn": 120, "topic": "gateway", "expected": "FACT-120-9h6hf", "id": "mem_2461b3b250", "inTail": false, "evicted": true, "answer": "FACT-120-9h6hf", "correct": true }, { "index": 9, "turn": 135, "topic": "router", "expected": "FACT-135-jw6fx", "id": "mem_cee1019da7", "inTail": false, "evicted": true, "answer": "FACT-135-jw6fx", "correct": true }, { "index": 10, "turn": 150, "topic": "gateway", "expected": "FACT-150-70m0g", "id": "mem_1e1ca1297d", "inTail": false, "evicted": true, "answer": "FACT-150-70m0g", "correct": true }, { "index": 11, "turn": 165, "topic": "router", "expected": "FACT-165-30c3x", "id": "mem_8f39a7480a", "inTail": false, "evicted": true, "answer": "FACT-165-30c3x", "correct": true }, { "index": 12, "turn": 180, "topic": "gateway", "expected": "FACT-180-pp2gq", "id": "mem_b728eb8a28", "inTail": false, "evicted": true, "answer": "FACT-180-pp2gq", "correct": true }, { "index": 13, "turn": 195, "topic": "router", "expected": "FACT-195-h5u81", "id": "mem_41f66b21a3", "inTail": false, "evicted": true, "answer": "FACT-195-h5u81", "correct": true }, { "index": 14, "turn": 210, "topic": "gateway", "expected": "FACT-210-skod2", "id": "mem_1e2eb0dba0", "inTail": false, "evicted": true, "answer": "FACT-210-skod2", "correct": true }, { "index": 15, "turn": 225, "topic": "router", "expected": "FACT-225-vo6pc", "id": "mem_8f825d8529", "inTail": false, "evicted": true, "answer": "FACT-225-vo6pc", "correct": true }, { "index": 16, "turn": 240, "topic": "gateway", "expected": "FACT-240-bnezh", "id": "mem_5811f57b75", "inTail": false, "evicted": true, "answer": "FACT-240-bnezh", "correct": true }, { "index": 17, "turn": 255, "topic": "router", "expected": "FACT-255-ouzrk", "id": "mem_4213aa33d4", "inTail": false, "evicted": true, "answer": "FACT-255-ouzrk", "correct": true }, { "index": 18, "turn": 270, "topic": "gateway", "expected": "FACT-270-abmgy", "id": "mem_3a1e02d66a", "inTail": false, "evicted": true, "answer": "FACT-270-abmgy", "correct": true }, { "index": 19, "turn": 285, "topic": "router", "expected": "FACT-285-o73dt", "id": "mem_f8989500f1", "inTail": true, "evicted": false, "answer": "FACT-285-o73dt", "correct": true } ], "correct": 20, "total": 20 } } ], "aggregate": { "control": { "correct": 3, "n": 60, "accuracy": 0.05 }, "treatment": { "correct": 60, "n": 60, "accuracy": 1 }, "evictedControl": { "correct": 0, "n": 57, "accuracy": 0 }, "evictedTreatment": { "correct": 57, "n": 57, "accuracy": 1 } }, "usage": { "promptTokens": 39028, "completionTokens": 1648, "totalTokens": 40676, "calls": 6 }, "raw": [ { "seed": 1, "label": "control", "textTail": "Q0: UNKNOWN\nQ1: UNKNOWN\nQ2: UNKNOWN\nQ3: UNKNOWN\nQ4: UNKNOWN\nQ5: UNKNOWN\nQ6: UNKNOWN\nQ7: UNKNOWN\nQ8: UNKNOWN\nQ9: UNKNOWN\nQ10: UNKNOWN\nQ11: UNKNOWN\nQ12: UNKNOWN\nQ13: UNKNOWN\nQ14: UNKNOWN\nQ15: UNKNOWN\nQ16: UNKNOWN\nQ17: UNKNOWN\nQ18: UNKNOWN\nQ19: FACT-285-rm66w", "usage": { "prompt_tokens": 1198, "completion_tokens": 244, "total_tokens": 1442, "usage_semantic": "openai", "usage_source": "anthropic", "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "reasoning_tokens": 0 }, "input_tokens": 1198, "output_tokens": 0, "input_tokens_details": null, "claude_cache_creation_5_m_tokens": 0, "claude_cache_creation_1_h_tokens": 0 } }, { "seed": 1, "label": "treatment", "textTail": "Q0: FACT-000-mkorf\nQ1: FACT-015-03jmy\nQ2: FACT-030-izkkh\nQ3: FACT-045-zbfww\nQ4: FACT-060-yv0n0\nQ5: FACT-075-a4b5x\nQ6: FACT-090-m28ly\nQ7: FACT-105-py2zp\nQ8: FACT-120-fbtzd\nQ9: FACT-135-ztagj\nQ10: FACT-150-ge14o\nQ11: FACT-165-hlgwo\nQ12: FACT-180-50232\nQ13: FACT-195-ej946\nQ14: FACT-210-8wsh3\nQ15: FACT-225-5k815\nQ16: FACT-240-hlxhw\nQ17: FACT-255-2fb7j\nQ18: FACT-270-e7fcx\nQ19: FACT-285-rm66w", "usage": { "prompt_tokens": 11755, "completion_tokens": 305, "total_tokens": 12060, "usage_semantic": "openai", "usage_source": "anthropic", "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "reasoning_tokens": 0 }, "input_tokens": 11755, "output_tokens": 0, "input_tokens_details": null, "claude_cache_creation_5_m_tokens": 0, "claude_cache_creation_1_h_tokens": 0 } }, { "seed": 2, "label": "control", "textTail": "Q0: UNKNOWN\nQ1: UNKNOWN\nQ2: UNKNOWN\nQ3: UNKNOWN\nQ4: UNKNOWN\nQ5: UNKNOWN\nQ6: UNKNOWN\nQ7: UNKNOWN\nQ8: UNKNOWN\nQ9: UNKNOWN\nQ10: UNKNOWN\nQ11: UNKNOWN\nQ12: UNKNOWN\nQ13: UNKNOWN\nQ14: UNKNOWN\nQ15: UNKNOWN\nQ16: UNKNOWN\nQ17: UNKNOWN\nQ18: UNKNOWN\nQ19: FACT-285-1esyu", "usage": { "prompt_tokens": 1200, "completion_tokens": 244, "total_tokens": 1444, "usage_semantic": "openai", "usage_source": "anthropic", "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "reasoning_tokens": 0 }, "input_tokens": 1200, "output_tokens": 0, "input_tokens_details": null, "claude_cache_creation_5_m_tokens": 0, "claude_cache_creation_1_h_tokens": 0 } }, { "seed": 2, "label": "treatment", "textTail": "Q0: FACT-000-qfl7m\nQ1: FACT-015-bp74k\nQ2: FACT-030-a9qrt\nQ3: FACT-045-jd6u3\nQ4: FACT-060-vidfn\nQ5: FACT-075-mpk5r\nQ6: FACT-090-hyyqy\nQ7: FACT-105-cuzlu\nQ8: FACT-120-s4xt8\nQ9: FACT-135-43s9i\nQ10: FACT-150-saher\nQ11: FACT-165-797as\nQ12: FACT-180-f9so7\nQ13: FACT-195-u25n2\nQ14: FACT-210-kxe32\nQ15: FACT-225-52qt3\nQ16: FACT-240-o77fl\nQ17: FACT-255-d78oa\nQ18: FACT-270-yz7lh\nQ19: FACT-285-1esyu", "usage": { "prompt_tokens": 11814, "completion_tokens": 305, "total_tokens": 12119, "usage_semantic": "openai", "usage_source": "anthropic", "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "reasoning_tokens": 0 }, "input_tokens": 11814, "output_tokens": 0, "input_tokens_details": null, "claude_cache_creation_5_m_tokens": 0, "claude_cache_creation_1_h_tokens": 0 } }, { "seed": 3, "label": "control", "textTail": "Q0: UNKNOWN\nQ1: UNKNOWN\nQ2: UNKNOWN\nQ3: UNKNOWN\nQ4: UNKNOWN\nQ5: UNKNOWN\nQ6: UNKNOWN\nQ7: UNKNOWN\nQ8: UNKNOWN\nQ9: UNKNOWN\nQ10: UNKNOWN\nQ11: UNKNOWN\nQ12: UNKNOWN\nQ13: UNKNOWN\nQ14: UNKNOWN\nQ15: UNKNOWN\nQ16: UNKNOWN\nQ17: UNKNOWN\nQ18: UNKNOWN\nQ19: FACT-285-o73dt", "usage": { "prompt_tokens": 1200, "completion_tokens": 244, "total_tokens": 1444, "usage_semantic": "openai", "usage_source": "anthropic", "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "reasoning_tokens": 0 }, "input_tokens": 1200, "output_tokens": 0, "input_tokens_details": null, "claude_cache_creation_5_m_tokens": 0, "claude_cache_creation_1_h_tokens": 0 } }, { "seed": 3, "label": "treatment", "textTail": "Q0: FACT-000-pxewf\nQ1: FACT-015-1e3tl\nQ2: FACT-030-gf83p\nQ3: FACT-045-2p3ua\nQ4: FACT-060-rgus2\nQ5: FACT-075-hblyb\nQ6: FACT-090-hisus\nQ7: FACT-105-5toyt\nQ8: FACT-120-9h6hf\nQ9: FACT-135-jw6fx\nQ10: FACT-150-70m0g\nQ11: FACT-165-30c3x\nQ12: FACT-180-pp2gq\nQ13: FACT-195-h5u81\nQ14: FACT-210-skod2\nQ15: FACT-225-vo6pc\nQ16: FACT-240-bnezh\nQ17: FACT-255-ouzrk\nQ18: FACT-270-abmgy\nQ19: FACT-285-o73dt", "usage": { "prompt_tokens": 11861, "completion_tokens": 306, "total_tokens": 12167, "usage_semantic": "openai", "usage_source": "anthropic", "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "image_tokens": 0, "reasoning_tokens": 0 }, "input_tokens": 11861, "output_tokens": 0, "input_tokens_details": null, "claude_cache_creation_5_m_tokens": 0, "claude_cache_creation_1_h_tokens": 0 } } ], "caveats": [ "Control/treatment prompts use synthetic fixtures; no private data is sent.", "Batch prompts ask the model to answer only from the supplied context; this is evidence-in-prompt, not a tool-calling loop.", "Usage comes from the gateway response; verify with your own APIMaster dashboard if needed.", "Tail membership is saved explicitly; evicted subset is verified.", "Synthetic fixture and evidence-in-prompt; no private prompts or keys are stored." ], "contributedBy": "DSH APIMaster Claude run", "runBy": "local APIMaster OpenAI-compatible gateway", "verifiedTail": true, "seedsRun": "3 seeds x 20 probes" }