{
  "format": 1,
  "kind": "live-ab-codex-result",
  "generatedAt": "2026-10-30T09:27:52.899Z",
  "provider": "codex-cli",
  "model": "gpt-6.1-sol",
  "testedVersion": "0.26.0",
  "testedCommit": "0b39791d144c8ebdf7a4f3ddc283550438b4c8d4",
  "nativeReportSha256": "27058af6a873c9aeaced3622af1ddf33391b389c5cd767ce28096f89862d9b99",
  "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_2889053973",
        "mem_2bd2cc6123",
        "mem_7206a0d7d8",
        "mem_5a13c14fec",
        "mem_468ecc98b0",
        "mem_678d3c6586",
        "mem_8235644ea9",
        "mem_7629589423",
        "mem_17cdc0db73",
        "mem_bc16eb5f73",
        "mem_621fbd3cf8",
        "mem_594762f056",
        "mem_c6d9ffc38a",
        "mem_1411daff64",
        "mem_99079723ec",
        "mem_7b5c10dd05",
        "mem_7188060113",
        "mem_f471a226f8",
        "mem_88272a4cec",
        "mem_d7cff47c76"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-mkorf",
            "id": "mem_c0f40725c7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_7a54a79c99",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_476974b102",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_465ad58ae7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_1ad93d7c5f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_325e770d3c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_4b43596355",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_c9fd4da76c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_a56de2cd1f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_47cb27acc4",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_051359a6d5",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_30a7c07863",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_3854c96808",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_5e58bbc0d0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_bc800ffbbf",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_59a5af4261",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_79be21c2a7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_0aea3e2309",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_4bdd485b8d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_678d3c6586",
            "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_c0f40725c7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-mkorf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_7a54a79c99",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-03jmy",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_476974b102",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-izkkh",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_465ad58ae7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-zbfww",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_1ad93d7c5f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-yv0n0",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_325e770d3c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-a4b5x",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_4b43596355",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-m28ly",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_c9fd4da76c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-py2zp",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_a56de2cd1f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-fbtzd",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_47cb27acc4",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-ztagj",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_051359a6d5",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-ge14o",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_30a7c07863",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-hlgwo",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_3854c96808",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-50232",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_5e58bbc0d0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-ej946",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_bc800ffbbf",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-8wsh3",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_59a5af4261",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-5k815",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_79be21c2a7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-hlxhw",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_0aea3e2309",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-2fb7j",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_4bdd485b8d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-e7fcx",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_678d3c6586",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-rm66w",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 2,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_287254c8ca",
        "mem_f0cfc8f30f",
        "mem_722176622e",
        "mem_4bf208d23b",
        "mem_303d894677",
        "mem_339682f3c2",
        "mem_2afad1088c",
        "mem_f2f5398673",
        "mem_1b240cb688",
        "mem_8d8edb51e7",
        "mem_d0724d2ada",
        "mem_70fd378d27",
        "mem_9d16ae194d",
        "mem_8baea5e456",
        "mem_694799b2d3",
        "mem_ca9fce58ce",
        "mem_5fd348c617",
        "mem_dabca6a174",
        "mem_3b23c939a4",
        "mem_e75dc5ee0d"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-qfl7m",
            "id": "mem_d5be62b902",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_4c1f77e6b3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_c34fb4ac73",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_183eef60b1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_114a8e7110",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_320673239f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_cf8182598f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_a292d4785a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_42ebcb7a94",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_c93e421208",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_98cbaaf0db",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_164c4952d1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_d6394b9c21",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_2d2af45526",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_6916621de0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_5506865157",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_c2ef39cd2b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_de2cd64df8",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_86e37779d4",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_339682f3c2",
            "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_d5be62b902",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-qfl7m",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_4c1f77e6b3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-bp74k",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_c34fb4ac73",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-a9qrt",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_183eef60b1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-jd6u3",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_114a8e7110",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-vidfn",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_320673239f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-mpk5r",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_cf8182598f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hyyqy",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_a292d4785a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-cuzlu",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_42ebcb7a94",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-s4xt8",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_c93e421208",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-43s9i",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_98cbaaf0db",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-saher",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_164c4952d1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-797as",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_d6394b9c21",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-f9so7",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_2d2af45526",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-u25n2",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_6916621de0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-kxe32",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_5506865157",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-52qt3",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_c2ef39cd2b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-o77fl",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_de2cd64df8",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-d78oa",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_86e37779d4",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-yz7lh",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_339682f3c2",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-1esyu",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 3,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_c8100fc942",
        "mem_2705d92f60",
        "mem_b9a037c0ce",
        "mem_a61001c105",
        "mem_736eed1bac",
        "mem_35d33efa4c",
        "mem_9062370821",
        "mem_fb7b98531b",
        "mem_b159b0cadc",
        "mem_4da8fd8c63",
        "mem_4491a36888",
        "mem_d70e52e103",
        "mem_d1a9fe3d09",
        "mem_7ca5371606",
        "mem_febd544e09",
        "mem_03020eac26",
        "mem_80a212e5aa",
        "mem_f905ef3fcb",
        "mem_97622cdf8e",
        "mem_2668aebb82"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-pxewf",
            "id": "mem_0edd99d733",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_7f053d2444",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_4abe58da09",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_e08e839cd1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_46e740bee6",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_f592c6dd16",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_d24fae3434",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_feaa6d5ae0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_3777ab3e01",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_8354ee7b00",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_96d711f101",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_5c5e34585b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_737f2fb3a8",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_9416e39b30",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_94aeccf198",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_3a4d3df02f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_5f506a771c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_57cf21fe30",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_35b31dfc5c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_35d33efa4c",
            "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_0edd99d733",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-pxewf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_7f053d2444",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-1e3tl",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_4abe58da09",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-gf83p",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_e08e839cd1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-2p3ua",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_46e740bee6",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-rgus2",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_f592c6dd16",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-hblyb",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_d24fae3434",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hisus",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_feaa6d5ae0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-5toyt",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_3777ab3e01",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-9h6hf",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_8354ee7b00",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-jw6fx",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_96d711f101",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-70m0g",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_5c5e34585b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-30c3x",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_737f2fb3a8",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-pp2gq",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_9416e39b30",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-h5u81",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_94aeccf198",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-skod2",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_3a4d3df02f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-vo6pc",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_5f506a771c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-bnezh",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_57cf21fe30",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-ouzrk",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_35b31dfc5c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-abmgy",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_35d33efa4c",
            "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": 23286,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 154,
        "reasoning_output_tokens": 43,
        "total_tokens": 23440
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "fedaa1e4f218d6c5d225f858ae055ee5aa73a87c11654a4d7bbee23baedd2f6e",
      "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": "336e448a06fc86bd068b5261bef032d30e74812a2e50bfdb8fed85e33c1c266d",
      "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": 29571,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 364,
        "reasoning_output_tokens": 144,
        "total_tokens": 29935
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "9c67c95cc7f0c2738527024ef9a9c613f1a993c38053827f74dbf8e21121564e",
      "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": "453fa643d4611c72ba032d1cf00f089ff0d2ee859eae4c0c001e1825824213d6",
      "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": 23286,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 150,
        "reasoning_output_tokens": 39,
        "total_tokens": 23436
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "5c3f659171dc4417cb06476f42bd8972a87af76fb71d66206b63feb35a82ed2d",
      "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": "edbc2748239e82f9e46ae8a59bf6849deb916b69992bfc2f1ef1f8c01ac23956",
      "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": 29521,
        "cached_input_tokens": 21120,
        "cache_write_input_tokens": 0,
        "output_tokens": 355,
        "reasoning_output_tokens": 138,
        "total_tokens": 29876
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "86e7848daf64abf3ef2bb03cf0bab41ce1999afa3b5453f51531a64762330ffd",
      "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": "268c9b2a6228779eda4b035dc89997e79fc563933b260f064ec76f0425863f8a",
      "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": 28982,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 146,
        "reasoning_output_tokens": 36,
        "total_tokens": 29128
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "7945182275d8ec1a087d1694724ee3e609f7e64aae35bc3934727549b0067a7d",
      "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": "c8cb5c007390e1d789d610168c0b8e208a67a9b34fca01cdec6dce298e1cff4f",
      "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": 29607,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 371,
        "reasoning_output_tokens": 148,
        "total_tokens": 29978
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "fe070760dc6489ae09af4c1b9d353fb4e10525d9d8545e93ebea0bd18c32a9a1",
      "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": "b840b262d69424e474d700eef81486c7eae6fda3dcbf99d523e1623662337c7b",
      "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": 164253,
      "cached_input_tokens": 87040,
      "cache_write_input_tokens": 0,
      "output_tokens": 1540,
      "reasoning_output_tokens": 548,
      "total_tokens": 165793
    },
    "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."
  ]
}
