{
  "format": 1,
  "kind": "live-ab-codex-result",
  "generatedAt": "2026-10-29T15:27:12.492Z",
  "provider": "codex-cli",
  "model": "gpt-6.1-sol",
  "testedVersion": "0.14.1 + SQLite fix",
  "testedCommit": "9fb13bb80038eb79b239a96186ced2ccfd93eb31",
  "nativeReportSha256": "9849b3ba873a67e9336a7875cb96927f444770f1bb2375dd7fa5b52959a2bf2f",
  "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_e03250e2be",
        "mem_e7d7c42c52",
        "mem_16162f5bd6",
        "mem_3b2105ff96",
        "mem_a2dda0d3bb",
        "mem_13a0b19ba6",
        "mem_544e5f7f1c",
        "mem_8602bf2ea3",
        "mem_afaf78d740",
        "mem_84be8f458c",
        "mem_384a176aa4",
        "mem_1903c7cb18",
        "mem_0e7ee09249",
        "mem_cec00596f3",
        "mem_8461160893",
        "mem_d56ace8206",
        "mem_3208923a17",
        "mem_36d0318b4d",
        "mem_88e87d5b0c",
        "mem_6e56881022"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-mkorf",
            "id": "mem_eb1b7d0434",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_f64473f5cb",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_bb992c645e",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_e3d42fea35",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_c9ff09288a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_f615810461",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_146c687336",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_3daeed6f0b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_6b4ef9275d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_1559042b33",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_027676dd06",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_70bb9fc86e",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_468c33d098",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_1bd8f294e2",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_a79795a000",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_f868128c0f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_6d8b3807a2",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_73d1a66c63",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_a372f713f4",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_13a0b19ba6",
            "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_eb1b7d0434",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-mkorf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_f64473f5cb",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-03jmy",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_bb992c645e",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-izkkh",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_e3d42fea35",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-zbfww",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_c9ff09288a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-yv0n0",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_f615810461",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-a4b5x",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_146c687336",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-m28ly",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_3daeed6f0b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-py2zp",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_6b4ef9275d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-fbtzd",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_1559042b33",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-ztagj",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_027676dd06",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-ge14o",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_70bb9fc86e",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-hlgwo",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_468c33d098",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-50232",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_1bd8f294e2",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-ej946",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_a79795a000",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-8wsh3",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_f868128c0f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-5k815",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_6d8b3807a2",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-hlxhw",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_73d1a66c63",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-2fb7j",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_a372f713f4",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-e7fcx",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_13a0b19ba6",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-rm66w",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 2,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_0a5f3bfa47",
        "mem_10d1d2a3d7",
        "mem_b0ee469b1e",
        "mem_d3be79b73d",
        "mem_8aedbfdf7f",
        "mem_c78c91b522",
        "mem_2cbc5c596b",
        "mem_c186be31e9",
        "mem_e01959e0ae",
        "mem_e898913fc6",
        "mem_ca0ab08ca2",
        "mem_167cd2b7a2",
        "mem_3434fa3d3e",
        "mem_a7d27c648f",
        "mem_354e23a8e7",
        "mem_16328db12b",
        "mem_078b409194",
        "mem_052bc10a1e",
        "mem_5832a9c9df",
        "mem_fc407a4c36"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-qfl7m",
            "id": "mem_3e0db0d146",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_e04cec5e54",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_c3d636fb29",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_620ca1ddbc",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_a988f6654d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_1d0fcc349a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_c28d284f5c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_1e4e19708d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_59d712d736",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_00d4fd7bad",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_ccc535b853",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_31b3ed9e25",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_00bf3f690d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_f45fe70a70",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_2280a986cd",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_b0556f9f26",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_2ba70f58a5",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_546dfcc434",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_a6e50aff94",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_c78c91b522",
            "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_3e0db0d146",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-qfl7m",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_e04cec5e54",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-bp74k",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_c3d636fb29",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-a9qrt",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_620ca1ddbc",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-jd6u3",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_a988f6654d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-vidfn",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_1d0fcc349a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-mpk5r",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_c28d284f5c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hyyqy",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_1e4e19708d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-cuzlu",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_59d712d736",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-s4xt8",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_00d4fd7bad",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-43s9i",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_ccc535b853",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-saher",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_31b3ed9e25",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-797as",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_00bf3f690d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-f9so7",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_f45fe70a70",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-u25n2",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_2280a986cd",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-kxe32",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_b0556f9f26",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-52qt3",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_2ba70f58a5",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-o77fl",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_546dfcc434",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-d78oa",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_a6e50aff94",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-yz7lh",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_c78c91b522",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-1esyu",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 3,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_d738f0787e",
        "mem_de36f0aefd",
        "mem_ee06c1dd12",
        "mem_cfc44e699a",
        "mem_649117ef9a",
        "mem_819366c6bc",
        "mem_36a1b5d32a",
        "mem_b7b7bc865b",
        "mem_7b45c08fca",
        "mem_71fa3f97f4",
        "mem_980128e11f",
        "mem_f662119c13",
        "mem_749554ca1b",
        "mem_304229bdf9",
        "mem_60262018cc",
        "mem_03bcab98b4",
        "mem_219699574d",
        "mem_822d3be06d",
        "mem_a5640e8ffb",
        "mem_9d8fa58e78"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-pxewf",
            "id": "mem_94dcc59aa6",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_a15bc88d26",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_98227b7edc",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_a735112408",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_802feb32dd",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_c527f19bc0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_87c3012863",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_e898465ae1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_aa5bd9f2c4",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_e46d765e83",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_60856fb793",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_85c4b28c04",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_94e630540d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_93d9affc6f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_e052472de2",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_5dbd2d1ea1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_02211b0f7f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_3bef46793b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_a4aeb1f198",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_819366c6bc",
            "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_94dcc59aa6",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-pxewf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_a15bc88d26",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-1e3tl",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_98227b7edc",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-gf83p",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_a735112408",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-2p3ua",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_802feb32dd",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-rgus2",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_c527f19bc0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-hblyb",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_87c3012863",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hisus",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_e898465ae1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-5toyt",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_aa5bd9f2c4",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-9h6hf",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_e46d765e83",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-jw6fx",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_60856fb793",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-70m0g",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_85c4b28c04",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-30c3x",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_94e630540d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-pp2gq",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_93d9affc6f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-h5u81",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_e052472de2",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-skod2",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_5dbd2d1ea1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-vo6pc",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_02211b0f7f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-bnezh",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_3bef46793b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-ouzrk",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_a4aeb1f198",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-abmgy",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_819366c6bc",
            "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": 23367,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 185,
        "reasoning_output_tokens": 74,
        "total_tokens": 23552
      },
      "reasoningEffort": "max",
      "configurationUpdates": [],
      "sessionLogSha256": "d3ec2168dd631ac2297ab9f9f5179635b070ce0accaea47d2ec8ab3b5b3b1f52",
      "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": "80410579551c74104a0274941240e165578800d27a94e49721c6a0c3c1cbff83",
      "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": 29630,
        "cached_input_tokens": 0,
        "cache_write_input_tokens": 0,
        "output_tokens": 455,
        "reasoning_output_tokens": 235,
        "total_tokens": 30085
      },
      "reasoningEffort": "max",
      "configurationUpdates": [],
      "sessionLogSha256": "4bfa9ea2d633b99533c74875725a469b26d6b31b536cc3955ad89637a54fc168",
      "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": "991a9dfc1d25a2fd505d5da531ccc64ff085a993da5464c486905ad3e30d672f",
      "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": 29064,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 172,
        "reasoning_output_tokens": 61,
        "total_tokens": 29236
      },
      "reasoningEffort": "max",
      "configurationUpdates": [
        "max"
      ],
      "sessionLogSha256": "52f845834f1f9a3134c7cadbc2d24c36a4134a648742b2397605a5cd51ff903a",
      "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": "df2090b4a38092386285df9e4ad7412f663b2afbb98df261256686e2183bab2d",
      "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": 29615,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 464,
        "reasoning_output_tokens": 247,
        "total_tokens": 30079
      },
      "reasoningEffort": "max",
      "configurationUpdates": [],
      "sessionLogSha256": "3177bfdc4d94435e00cbe2d5c6a97dcb4736d9c1c17a3722d75af121c498cc8b",
      "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": "dcc19455e613c2b6c3008349434eb4fbde19f6eaa2b8e3772c62e6b88e34cf22",
      "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": 23366,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 161,
        "reasoning_output_tokens": 51,
        "total_tokens": 23527
      },
      "reasoningEffort": "max",
      "configurationUpdates": [],
      "sessionLogSha256": "f5d5f92dd198205a563003248eeac1b3817b352f7af7624453608daa65ff1faf",
      "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": "cb38eac0de42c575758affb9a32875bd4938892a68566fd31532d1fd711f4b97",
      "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": 29646,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 445,
        "reasoning_output_tokens": 222,
        "total_tokens": 30091
      },
      "reasoningEffort": "max",
      "configurationUpdates": [],
      "sessionLogSha256": "a0665d8913ecfd4d13d11754f92f8a984107525b86d1448b8437e78ebedcbd32",
      "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": "e07e96d51f08d6a7ff09426f14bd049e3d282592d6c37bbdcac88a79b5ffbaf3",
      "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": 164688,
      "cached_input_tokens": 65920,
      "cache_write_input_tokens": 0,
      "output_tokens": 1882,
      "reasoning_output_tokens": 890,
      "total_tokens": 166570
    },
    "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."
  ]
}
