{
  "format": 1,
  "kind": "live-ab-codex-result",
  "generatedAt": "2026-10-30T10:09:44.884Z",
  "provider": "codex-cli",
  "model": "gpt-6.1-sol",
  "testedVersion": "0.30.0",
  "testedCommit": "7d813147e9cc6d3aa9d61ebf321647061f44054d",
  "nativeReportSha256": "2e9e846b50f84dfd99edc1152f68be2cb7df3490af89ac15e622403cf6c1773e",
  "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_86e47b5501",
        "mem_ccd460f3a1",
        "mem_90b0200b2d",
        "mem_1c267a1389",
        "mem_64a94a3a78",
        "mem_cb1811a61c",
        "mem_5ff002b578",
        "mem_a35fffe0d5",
        "mem_c9c6b56713",
        "mem_792952bc27",
        "mem_847f91f22f",
        "mem_eb593c58f3",
        "mem_a59be41270",
        "mem_f4cd1640f8",
        "mem_92209fe631",
        "mem_91070751a1",
        "mem_86844073c8",
        "mem_620471d512",
        "mem_dbdfc59df3",
        "mem_5379155f3f"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-mkorf",
            "id": "mem_d76e36f878",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_c5d9018097",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_16adbe949d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_6d3aae888a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_a004a1d87b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_f4d8841d91",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_ecac215439",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_00f795370c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_1c8d02ddaa",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_1d57356c17",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_cd1f15c1b4",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_33477497c0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_f21d109fee",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_fa071d3ffa",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_289902db31",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_7e063cb8c6",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_b149db4930",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_509ccfbd07",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_9bebd41838",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_cb1811a61c",
            "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_d76e36f878",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-mkorf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_c5d9018097",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-03jmy",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_16adbe949d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-izkkh",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_6d3aae888a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-zbfww",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_a004a1d87b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-yv0n0",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_f4d8841d91",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-a4b5x",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_ecac215439",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-m28ly",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_00f795370c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-py2zp",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_1c8d02ddaa",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-fbtzd",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_1d57356c17",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-ztagj",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_cd1f15c1b4",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-ge14o",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_33477497c0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-hlgwo",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_f21d109fee",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-50232",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_fa071d3ffa",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-ej946",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_289902db31",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-8wsh3",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_7e063cb8c6",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-5k815",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_b149db4930",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-hlxhw",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_509ccfbd07",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-2fb7j",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_9bebd41838",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-e7fcx",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_cb1811a61c",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-rm66w",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 2,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_6c8b51e32a",
        "mem_86d42248fc",
        "mem_93b076a54a",
        "mem_300b7bb024",
        "mem_e2d00e00b6",
        "mem_4ed5bbbf02",
        "mem_0edc4d119a",
        "mem_1f478d870a",
        "mem_7896285914",
        "mem_6b51361dac",
        "mem_f0db424f0b",
        "mem_0c7980272c",
        "mem_5b320c5b25",
        "mem_b5c4cc336e",
        "mem_af4b81dbc8",
        "mem_414a98c1ef",
        "mem_655fecd568",
        "mem_8f0a6caaec",
        "mem_16bc3c1b72",
        "mem_8cd9f88341"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-qfl7m",
            "id": "mem_5930708e8b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_a612c6b7f3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_23b4785fcd",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_6f9cfa8996",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_1d9f12d261",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_62210cf99c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_f8d72ac5f7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_3bed8cb5c7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_e0cd5d530a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_7ab0358b3d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_9b2a9c55c1",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_102a758dea",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_719a9bbdc0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_9ffffa5b0d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_75634de8a7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_096b3f3c98",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_b2753b0d83",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_6a75a7d9db",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_8f7e28f8ff",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_4ed5bbbf02",
            "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_5930708e8b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-qfl7m",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_a612c6b7f3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-bp74k",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_23b4785fcd",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-a9qrt",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_6f9cfa8996",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-jd6u3",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_1d9f12d261",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-vidfn",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_62210cf99c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-mpk5r",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_f8d72ac5f7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hyyqy",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_3bed8cb5c7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-cuzlu",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_e0cd5d530a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-s4xt8",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_7ab0358b3d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-43s9i",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_9b2a9c55c1",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-saher",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_102a758dea",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-797as",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_719a9bbdc0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-f9so7",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_9ffffa5b0d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-u25n2",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_75634de8a7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-kxe32",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_096b3f3c98",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-52qt3",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_b2753b0d83",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-o77fl",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_6a75a7d9db",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-d78oa",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_8f7e28f8ff",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-yz7lh",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_4ed5bbbf02",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-1esyu",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 3,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_9b27de8222",
        "mem_7c0c6ed549",
        "mem_2cfa8bd518",
        "mem_14e256c604",
        "mem_d8b5b9c24d",
        "mem_c231ee4ccb",
        "mem_ae714190d5",
        "mem_32e9fc86bf",
        "mem_516283afc8",
        "mem_56ec74760d",
        "mem_09c71e0ddb",
        "mem_bd4f3c4a3c",
        "mem_3bb713b6e1",
        "mem_96c5650fa2",
        "mem_154a984e0d",
        "mem_1d29d19d69",
        "mem_7e69faf3c3",
        "mem_7de37bcfae",
        "mem_b10d084a91",
        "mem_e58fdb67eb"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-pxewf",
            "id": "mem_803f8ebe74",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_594ab8b929",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_6ef882b8f7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_ac29e7e608",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_b2c67fa674",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_2d607fa970",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_d16423113b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_e627cdbec4",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_e48addeea3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_38cdb40da8",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_1912e66195",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_87e82fc793",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_714eefbe48",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_116cdb6c4d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_c5b126f353",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_9c617eadad",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_8aa1147483",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_787646ae19",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_95cc762dc3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_c231ee4ccb",
            "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_803f8ebe74",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-pxewf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_594ab8b929",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-1e3tl",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_6ef882b8f7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-gf83p",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_ac29e7e608",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-2p3ua",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_b2c67fa674",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-rgus2",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_2d607fa970",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-hblyb",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_d16423113b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hisus",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_e627cdbec4",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-5toyt",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_e48addeea3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-9h6hf",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_38cdb40da8",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-jw6fx",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_1912e66195",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-70m0g",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_87e82fc793",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-30c3x",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_714eefbe48",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-pp2gq",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_116cdb6c4d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-h5u81",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_c5b126f353",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-skod2",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_9c617eadad",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-vo6pc",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_8aa1147483",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-bnezh",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_787646ae19",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-ouzrk",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_95cc762dc3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-abmgy",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_c231ee4ccb",
            "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": 23290,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 140,
        "reasoning_output_tokens": 29,
        "total_tokens": 23430
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "8c8565a035ff208c34debc273c400c604e1220dd3a553e8f8b514606db21f685",
      "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": "330e9ce195ac9886e072cead399595cd18d7af4a0912d0b13bc5b7704f0f9ce0",
      "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": 29487,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 411,
        "reasoning_output_tokens": 191,
        "total_tokens": 29898
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "b6d62143cd06bb2129439b6f0f7b7fa14138ded8ff6f16f9bcf510fae231e4b3",
      "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": "24dc14fbf6b1053ea9afce944806829ba6e8127c94c428337e85d6f5500c5e12",
      "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": 23290,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 144,
        "reasoning_output_tokens": 33,
        "total_tokens": 23434
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "3ce6e5e18d418d9532e5a1b119f9e1ee63f707d713c084f0fdacfa9d96aada10",
      "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": "acee9b40adfd490614bea52483d881585cf2c2553b639abbacbbbf38a89c70f9",
      "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": 29667,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 513,
        "reasoning_output_tokens": 296,
        "total_tokens": 30180
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "7d118f526ad9dadf8e92173d406134bd4866f1cac54d916c53075c2b22d8fd05",
      "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": "729d39ac1ca396e8cb306fb7aa7e67f57adf79ef11dfaef1b7ef078db1c9940c",
      "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": 23289,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 150,
        "reasoning_output_tokens": 40,
        "total_tokens": 23439
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "bfa796a08dd2b0b5e180ef557a6bbfb36b8fe19e69e166e599025f757fa1f7e4",
      "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": "9f7ae7f88969b9d936fed29022f43836bd2a3db1d9d27a45109be373a1f4a81f",
      "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": 29480,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 395,
        "reasoning_output_tokens": 172,
        "total_tokens": 29875
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "5025f0d8174ccd1a470a2ae215e7309ed2b52b4dc924f1005900961d70355586",
      "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": "b1ff3cc562c0990b30cd506f602534f62525e56f4ae0165316b8b7b4e635914d",
      "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": 158503,
      "cached_input_tokens": 79104,
      "cache_write_input_tokens": 0,
      "output_tokens": 1753,
      "reasoning_output_tokens": 761,
      "total_tokens": 160256
    },
    "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."
  ]
}
