{
  "format": 1,
  "kind": "live-ab-codex-result",
  "generatedAt": "2026-10-29T13:42:37.358Z",
  "provider": "codex-cli",
  "model": "gpt-6.1-sol",
  "testedVersion": "0.14.0",
  "testedCommit": "48034b1fcb1eb28e88173f3568e4b09cf6670b1d",
  "nativeReportSha256": "848ece3ed321b1f9a284e34744df36b76d732e076d4d5bfd897effa741f268ca",
  "bridgeExitCode": 0,
  "method": "codex exec --skip-git-repo-check --sandbox read-only --output-last-message; control/treatment generated by scripts/live-ab.mjs --emit-prompts",
  "aggregate": {
    "control": {
      "correct": 3,
      "n": 60,
      "accuracy": 0.05
    },
    "treatment": {
      "correct": 60,
      "n": 60,
      "accuracy": 1.0
    },
    "evictedControl": {
      "correct": 0,
      "n": 57,
      "accuracy": 0.0
    },
    "evictedTreatment": {
      "correct": 57,
      "n": 57,
      "accuracy": 1.0
    }
  },
  "seeds": [
    {
      "seed": 1,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_32ef82b518",
        "mem_028ca9939e",
        "mem_ff5b5dc571",
        "mem_0126f99ff8",
        "mem_fc6b2444fb",
        "mem_a2ba305b50",
        "mem_f1ea4dd1aa",
        "mem_c3f6c4edc8",
        "mem_bcb7b0c9aa",
        "mem_21e407ac79",
        "mem_c1adf37bd1",
        "mem_1c1901c57b",
        "mem_76857b09df",
        "mem_bdcbc28841",
        "mem_0ceab1cb39",
        "mem_6dc26ce490",
        "mem_9e42f153d3",
        "mem_6d0388dcc5",
        "mem_866a68a534",
        "mem_aa69109340"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-mkorf",
            "id": "mem_94e64dc0b3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_0b2cf97acb",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_670cd726f7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_7f9a312ceb",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_3b03735f29",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_3cf52dea28",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_a97ff2e37b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_3cd9753c0d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_d156be8219",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_c34a61f2c5",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_07e74e2ffc",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_2f75610d9b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_c6af3762ad",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_5413052525",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_90b828672a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_fded70fe81",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_293c331c32",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_693a200ada",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_1df075524f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_a2ba305b50",
            "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_94e64dc0b3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-mkorf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_0b2cf97acb",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-03jmy",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_670cd726f7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-izkkh",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_7f9a312ceb",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-zbfww",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_3b03735f29",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-yv0n0",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_3cf52dea28",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-a4b5x",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_a97ff2e37b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-m28ly",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_3cd9753c0d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-py2zp",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_d156be8219",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-fbtzd",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_c34a61f2c5",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-ztagj",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_07e74e2ffc",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-ge14o",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_2f75610d9b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-hlgwo",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_c6af3762ad",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-50232",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_5413052525",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-ej946",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_90b828672a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-8wsh3",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_fded70fe81",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-5k815",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_293c331c32",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-hlxhw",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_693a200ada",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-2fb7j",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_1df075524f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-e7fcx",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_a2ba305b50",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-rm66w",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 2,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_f72da26046",
        "mem_ddceffdfa7",
        "mem_238fa76141",
        "mem_d798f7de4d",
        "mem_27b5783f36",
        "mem_e703349b41",
        "mem_ae63f4b0df",
        "mem_fc87398945",
        "mem_f4a6670f90",
        "mem_b7969bcc76",
        "mem_315883655e",
        "mem_011e28e345",
        "mem_25b6378f7d",
        "mem_1ea88a68d1",
        "mem_e7d889fe3f",
        "mem_008995e955",
        "mem_fd34a642fc",
        "mem_089c979b84",
        "mem_f0a3efd1d3",
        "mem_d5467b6f5a"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-qfl7m",
            "id": "mem_4ba58acd54",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_b92282b856",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_ebb45977ac",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_0608ea67c6",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_95a5f1214c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_267d55a0b6",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_cbeaad44b1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_bcb210c200",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_1861121edf",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_b74136ec36",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_e48c9d2f5b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_81a8b318f7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_8934b6ba47",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_f7e2ebd346",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_c2f092a6af",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_b84230b27e",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_a7a705378a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_e23e5db71f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_d4ffe256dd",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_e703349b41",
            "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_4ba58acd54",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-qfl7m",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_b92282b856",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-bp74k",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_ebb45977ac",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-a9qrt",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_0608ea67c6",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-jd6u3",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_95a5f1214c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-vidfn",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_267d55a0b6",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-mpk5r",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_cbeaad44b1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hyyqy",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_bcb210c200",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-cuzlu",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_1861121edf",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-s4xt8",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_b74136ec36",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-43s9i",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_e48c9d2f5b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-saher",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_81a8b318f7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-797as",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_8934b6ba47",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-f9so7",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_f7e2ebd346",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-u25n2",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_c2f092a6af",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-kxe32",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_b84230b27e",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-52qt3",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_a7a705378a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-o77fl",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_e23e5db71f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-d78oa",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_d4ffe256dd",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-yz7lh",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_e703349b41",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-1esyu",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 3,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_353c71815e",
        "mem_9002cad144",
        "mem_fe8028856c",
        "mem_00595fc63b",
        "mem_83da4de856",
        "mem_59cd17246a",
        "mem_e66936ff1e",
        "mem_dd993a5207",
        "mem_da0dc2e1d6",
        "mem_526a1285df",
        "mem_0106f3d461",
        "mem_da8eab143f",
        "mem_15e12bf0ad",
        "mem_44760f2bf7",
        "mem_a138406f5a",
        "mem_a1385599f4",
        "mem_2f4214ccb9",
        "mem_3c4e843494",
        "mem_6d539ff3f2",
        "mem_275fdae44f"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-pxewf",
            "id": "mem_df49130e76",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_c635a83682",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_74dc18d2a0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_4ec7de91c9",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_1e405c2979",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_c220dcfe9e",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_2d9e27d1a5",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_473e787f95",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_88aadc8fbf",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_d909fed98d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_e4b47def8d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_5d034a3a0b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_d5a33daf4e",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_e5adf7cd9b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_97eb121c9e",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_f20fe971dd",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_afcdc32596",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_cdccfdb3a1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_c80b0994e3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_59cd17246a",
            "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_df49130e76",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-pxewf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_c635a83682",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-1e3tl",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_74dc18d2a0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-gf83p",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_4ec7de91c9",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-2p3ua",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_1e405c2979",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-rgus2",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_c220dcfe9e",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-hblyb",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_2d9e27d1a5",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hisus",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_473e787f95",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-5toyt",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_88aadc8fbf",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-9h6hf",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_d909fed98d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-jw6fx",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_e4b47def8d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-70m0g",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_5d034a3a0b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-30c3x",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_d5a33daf4e",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-pp2gq",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_e5adf7cd9b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-h5u81",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_97eb121c9e",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-skod2",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_f20fe971dd",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-vo6pc",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_afcdc32596",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-bnezh",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_cdccfdb3a1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-ouzrk",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_c80b0994e3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-abmgy",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_59cd17246a",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-o73dt",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    }
  ],
  "calls": [
    {
      "seed": 1,
      "label": "control",
      "processExitCode": 0,
      "sessionTaskComplete": true,
      "recordedToolCalls": 0,
      "usage": {
        "input_tokens": 23141,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 155,
        "reasoning_output_tokens": 44,
        "total_tokens": 23296
      },
      "sessionLogSha256": "78bba1281eb890ae802bf2d96bed8b3cb804d7b73d1bb80072d2c7846ea205a4",
      "answerText": "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",
      "stderrTailSha256": "cba15fe90a5d64c0de8835c9f6eb9cd35eda01a2b5cf917f5a77d21c35b7f80d",
      "stderrTailPublished": "redacted; bridge captured only the final 1200 characters",
      "initializeWarningSeen": true,
      "analyticsWarningSeen": false
    },
    {
      "seed": 1,
      "label": "treatment",
      "processExitCode": 0,
      "sessionTaskComplete": true,
      "recordedToolCalls": 0,
      "usage": {
        "input_tokens": 29348,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 380,
        "reasoning_output_tokens": 160,
        "total_tokens": 29728
      },
      "sessionLogSha256": "ee65f8503c8464d5b0eb051c4626410ecdaf1d6ca6d2b3fb42d220a2c03a0dfd",
      "answerText": "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",
      "stderrTailSha256": "6e3c148dcbc7c55f0fda755f93fff1fa6b59cb1e8b05cb248bf71fdd05e156b8",
      "stderrTailPublished": "redacted; bridge captured only the final 1200 characters",
      "initializeWarningSeen": true,
      "analyticsWarningSeen": false
    },
    {
      "seed": 2,
      "label": "control",
      "processExitCode": 0,
      "sessionTaskComplete": true,
      "recordedToolCalls": 0,
      "usage": {
        "input_tokens": 28838,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 170,
        "reasoning_output_tokens": 59,
        "total_tokens": 29008
      },
      "sessionLogSha256": "db2b4f1e291ba226e10e4c1ebf7951f1b83e3847f860559987abd5a94cb9a4f0",
      "answerText": "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",
      "stderrTailSha256": "2cca6ef779ed3f5e7ecacf922c475a58ada900731f1b226c7c12acd05cdfa292",
      "stderrTailPublished": "redacted; bridge captured only the final 1200 characters",
      "initializeWarningSeen": true,
      "analyticsWarningSeen": false
    },
    {
      "seed": 2,
      "label": "treatment",
      "processExitCode": 0,
      "sessionTaskComplete": true,
      "recordedToolCalls": 0,
      "usage": {
        "input_tokens": 29389,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 451,
        "reasoning_output_tokens": 234,
        "total_tokens": 29840
      },
      "sessionLogSha256": "f8e790d8179cba97fcbdc38cf9e3e89f6103b24e25e5dbac9ad2ce74ffe51f92",
      "answerText": "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",
      "stderrTailSha256": "47982177b26580339cdda7bdfc489bf35f6af4817168c1e5489cb6716437f957",
      "stderrTailPublished": "redacted; bridge captured only the final 1200 characters",
      "initializeWarningSeen": true,
      "analyticsWarningSeen": false
    },
    {
      "seed": 3,
      "label": "control",
      "processExitCode": 0,
      "sessionTaskComplete": true,
      "recordedToolCalls": 0,
      "usage": {
        "input_tokens": 23140,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 170,
        "reasoning_output_tokens": 60,
        "total_tokens": 23310
      },
      "sessionLogSha256": "41625ae604a1f49342fb6a785e94133dac7ab9ba5bfb8b4af47a36b0da5c57bd",
      "answerText": "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",
      "stderrTailSha256": "8c90f8231289c365f39bcc21d76d8886c0f12565ecb5a962d46d202d5c7373f8",
      "stderrTailPublished": "redacted; bridge captured only the final 1200 characters",
      "initializeWarningSeen": true,
      "analyticsWarningSeen": false
    },
    {
      "seed": 3,
      "label": "treatment",
      "processExitCode": 0,
      "sessionTaskComplete": true,
      "recordedToolCalls": 0,
      "usage": {
        "input_tokens": 29409,
        "cached_input_tokens": 20992,
        "cache_write_input_tokens": 0,
        "output_tokens": 463,
        "reasoning_output_tokens": 240,
        "total_tokens": 29872
      },
      "sessionLogSha256": "a4bdb582f29187563f004d791786119574fd0447aebd1c335d62325eb7f42f51",
      "answerText": "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",
      "stderrTailSha256": "07d76f5750e31e3ffdf48d267027ff899d6b3b5b5e1e667cf3729943e17a7a62",
      "stderrTailPublished": "redacted; bridge captured only the final 1200 characters",
      "initializeWarningSeen": true,
      "analyticsWarningSeen": false
    }
  ],
  "usage": {
    "source": "Codex local session token_count total_token_usage; totals include reported cached input",
    "calls": 6,
    "totals": {
      "input_tokens": 163265,
      "cached_input_tokens": 86912,
      "cache_write_input_tokens": 0,
      "output_tokens": 1789,
      "reasoning_output_tokens": 797,
      "total_tokens": 165054
    },
    "billedCost": "UNKNOWN",
    "billingReceipt": "NOT_CAPTURED"
  },
  "caveats": [
    "Synthetic 300-turn fixtures; control sees tail titles and summaries, not full bodies.",
    "Treatment receives preselected search/open evidence; this is not a model-driven memory-tool benchmark.",
    "No model-issued tool calls appear in these six local session logs.",
    "Only diagnostic tails were captured by the bridge; they are redacted publicly and retained locally.",
    "The native report and local session logs remain local; billed cost is UNKNOWN."
  ]
}
