{
  "format": 1,
  "kind": "live-ab-codex-result",
  "generatedAt": "2026-10-30T09:47:06.731Z",
  "provider": "codex-cli",
  "model": "gpt-6.1-sol",
  "testedVersion": "0.27.0",
  "testedCommit": "3970ecff39b5e8be8373c50329e16458416ff0c5",
  "nativeReportSha256": "75b32f1ba58c354c01ef7c53dd24e528a679effb6df74126835c4307799a2565",
  "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_b84fdd80ed",
        "mem_649a177c73",
        "mem_7e247b20d0",
        "mem_3c503d7af4",
        "mem_9fc4358994",
        "mem_85f34b5744",
        "mem_cf444c6eb2",
        "mem_291a7fa817",
        "mem_b371418a8b",
        "mem_5ce7260be4",
        "mem_d9649962c2",
        "mem_4de082b9b0",
        "mem_a4a9e20df2",
        "mem_cc6dcd504d",
        "mem_99debc2d00",
        "mem_bd31f3bf64",
        "mem_35ecb5dc58",
        "mem_b40fa74ac6",
        "mem_97de1ff633",
        "mem_a7fe87dc24"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-mkorf",
            "id": "mem_960745e376",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_745bbc8ff0",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_214361e181",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_a4c5ce87b9",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_ddd58793aa",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_d8f3b6dea2",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_603ff2550f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_6038ae0381",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_a6cf7725cc",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_30b7771edc",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_dba2f6c00a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_ab2abdce80",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_c7c43094a5",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_5378604545",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_59640073ca",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_fa58d7cf3a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_6d575696df",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_3afbaafba2",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_2630b6b8f3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_85f34b5744",
            "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_960745e376",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-mkorf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-03jmy",
            "id": "mem_745bbc8ff0",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-03jmy",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-izkkh",
            "id": "mem_214361e181",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-izkkh",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-zbfww",
            "id": "mem_a4c5ce87b9",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-zbfww",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-yv0n0",
            "id": "mem_ddd58793aa",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-yv0n0",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-a4b5x",
            "id": "mem_d8f3b6dea2",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-a4b5x",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-m28ly",
            "id": "mem_603ff2550f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-m28ly",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-py2zp",
            "id": "mem_6038ae0381",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-py2zp",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-fbtzd",
            "id": "mem_a6cf7725cc",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-fbtzd",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-ztagj",
            "id": "mem_30b7771edc",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-ztagj",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-ge14o",
            "id": "mem_dba2f6c00a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-ge14o",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-hlgwo",
            "id": "mem_ab2abdce80",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-hlgwo",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-50232",
            "id": "mem_c7c43094a5",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-50232",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-ej946",
            "id": "mem_5378604545",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-ej946",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-8wsh3",
            "id": "mem_59640073ca",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-8wsh3",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-5k815",
            "id": "mem_fa58d7cf3a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-5k815",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-hlxhw",
            "id": "mem_6d575696df",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-hlxhw",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-2fb7j",
            "id": "mem_3afbaafba2",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-2fb7j",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-e7fcx",
            "id": "mem_2630b6b8f3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-e7fcx",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-rm66w",
            "id": "mem_85f34b5744",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-rm66w",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 2,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_1553fa31e7",
        "mem_11dea1e80b",
        "mem_46316833f9",
        "mem_c1fc3ae0e8",
        "mem_996e714400",
        "mem_6dc33a4738",
        "mem_658990f7fa",
        "mem_6e8f85d7d9",
        "mem_027c839a43",
        "mem_ba76a81d77",
        "mem_3d0903ad86",
        "mem_0f571b0243",
        "mem_473f7bd1c2",
        "mem_bf08330f9a",
        "mem_51e2fb0d4d",
        "mem_a48e8ffc41",
        "mem_d3c71bb0bc",
        "mem_3c87500885",
        "mem_ddd6e3acc2",
        "mem_a44acc5bc9"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-qfl7m",
            "id": "mem_4bdcf20b14",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_f4e1f2b5de",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_559a3746b5",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_3368132bea",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_4d39b2780f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_187602fb6c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_c87aaae92b",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_5aadc93c60",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_b80b51b656",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_907a62fa9c",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_a93650c7cf",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_dba712fd08",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_3ddaa60826",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_b3c5c36161",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_9cc1d4d986",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_775acc0140",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_7316ab3cbb",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_3889b66c6f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_5add272dc4",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_6dc33a4738",
            "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_4bdcf20b14",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-qfl7m",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-bp74k",
            "id": "mem_f4e1f2b5de",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-bp74k",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-a9qrt",
            "id": "mem_559a3746b5",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-a9qrt",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-jd6u3",
            "id": "mem_3368132bea",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-jd6u3",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-vidfn",
            "id": "mem_4d39b2780f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-vidfn",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-mpk5r",
            "id": "mem_187602fb6c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-mpk5r",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hyyqy",
            "id": "mem_c87aaae92b",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hyyqy",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-cuzlu",
            "id": "mem_5aadc93c60",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-cuzlu",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-s4xt8",
            "id": "mem_b80b51b656",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-s4xt8",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-43s9i",
            "id": "mem_907a62fa9c",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-43s9i",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-saher",
            "id": "mem_a93650c7cf",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-saher",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-797as",
            "id": "mem_dba712fd08",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-797as",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-f9so7",
            "id": "mem_3ddaa60826",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-f9so7",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-u25n2",
            "id": "mem_b3c5c36161",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-u25n2",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-kxe32",
            "id": "mem_9cc1d4d986",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-kxe32",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-52qt3",
            "id": "mem_775acc0140",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-52qt3",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-o77fl",
            "id": "mem_7316ab3cbb",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-o77fl",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-d78oa",
            "id": "mem_3889b66c6f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-d78oa",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-yz7lh",
            "id": "mem_5add272dc4",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-yz7lh",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-1esyu",
            "id": "mem_6dc33a4738",
            "inTail": true,
            "evicted": false,
            "answer": "FACT-285-1esyu",
            "correct": true
          }
        ],
        "correct": 20,
        "total": 20
      }
    },
    {
      "seed": 3,
      "turns": 300,
      "tailCount": 20,
      "tailIds": [
        "mem_ed684b83f4",
        "mem_f1a635833c",
        "mem_7b678732e1",
        "mem_fb301fbce9",
        "mem_478ae8cda8",
        "mem_98d285b861",
        "mem_0dddc10a05",
        "mem_2789d18796",
        "mem_8de501e75d",
        "mem_72fc740e37",
        "mem_ea377af1a1",
        "mem_2a0696b9f1",
        "mem_77aa90adde",
        "mem_2cda2d7766",
        "mem_e6baaffd87",
        "mem_a35e408091",
        "mem_699e85011e",
        "mem_819483bafe",
        "mem_737f12dfa0",
        "mem_844f74c38b"
      ],
      "probes": 20,
      "evictedProbes": 19,
      "control": {
        "rows": [
          {
            "index": 0,
            "turn": 0,
            "topic": "gateway",
            "expected": "FACT-000-pxewf",
            "id": "mem_a9859c8bef",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_58c0eb0ef3",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_52ca8dc4d7",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_42702bb43d",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_1a0c1bbd31",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_15c687ffce",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_4d207591cc",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_e41421ae03",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_a92ac08559",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_5145ec2609",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_fe2e3ff24f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_da38351b3a",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_214a0946e5",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_a65325c42f",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_ec5b1e4071",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_5874d95467",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_3ae5ba67ee",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_18480203e6",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_c28122e1a9",
            "inTail": false,
            "evicted": true,
            "answer": "UNKNOWN",
            "correct": false
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_98d285b861",
            "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_a9859c8bef",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-000-pxewf",
            "correct": true
          },
          {
            "index": 1,
            "turn": 15,
            "topic": "router",
            "expected": "FACT-015-1e3tl",
            "id": "mem_58c0eb0ef3",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-015-1e3tl",
            "correct": true
          },
          {
            "index": 2,
            "turn": 30,
            "topic": "gateway",
            "expected": "FACT-030-gf83p",
            "id": "mem_52ca8dc4d7",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-030-gf83p",
            "correct": true
          },
          {
            "index": 3,
            "turn": 45,
            "topic": "router",
            "expected": "FACT-045-2p3ua",
            "id": "mem_42702bb43d",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-045-2p3ua",
            "correct": true
          },
          {
            "index": 4,
            "turn": 60,
            "topic": "gateway",
            "expected": "FACT-060-rgus2",
            "id": "mem_1a0c1bbd31",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-060-rgus2",
            "correct": true
          },
          {
            "index": 5,
            "turn": 75,
            "topic": "router",
            "expected": "FACT-075-hblyb",
            "id": "mem_15c687ffce",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-075-hblyb",
            "correct": true
          },
          {
            "index": 6,
            "turn": 90,
            "topic": "gateway",
            "expected": "FACT-090-hisus",
            "id": "mem_4d207591cc",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-090-hisus",
            "correct": true
          },
          {
            "index": 7,
            "turn": 105,
            "topic": "router",
            "expected": "FACT-105-5toyt",
            "id": "mem_e41421ae03",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-105-5toyt",
            "correct": true
          },
          {
            "index": 8,
            "turn": 120,
            "topic": "gateway",
            "expected": "FACT-120-9h6hf",
            "id": "mem_a92ac08559",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-120-9h6hf",
            "correct": true
          },
          {
            "index": 9,
            "turn": 135,
            "topic": "router",
            "expected": "FACT-135-jw6fx",
            "id": "mem_5145ec2609",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-135-jw6fx",
            "correct": true
          },
          {
            "index": 10,
            "turn": 150,
            "topic": "gateway",
            "expected": "FACT-150-70m0g",
            "id": "mem_fe2e3ff24f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-150-70m0g",
            "correct": true
          },
          {
            "index": 11,
            "turn": 165,
            "topic": "router",
            "expected": "FACT-165-30c3x",
            "id": "mem_da38351b3a",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-165-30c3x",
            "correct": true
          },
          {
            "index": 12,
            "turn": 180,
            "topic": "gateway",
            "expected": "FACT-180-pp2gq",
            "id": "mem_214a0946e5",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-180-pp2gq",
            "correct": true
          },
          {
            "index": 13,
            "turn": 195,
            "topic": "router",
            "expected": "FACT-195-h5u81",
            "id": "mem_a65325c42f",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-195-h5u81",
            "correct": true
          },
          {
            "index": 14,
            "turn": 210,
            "topic": "gateway",
            "expected": "FACT-210-skod2",
            "id": "mem_ec5b1e4071",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-210-skod2",
            "correct": true
          },
          {
            "index": 15,
            "turn": 225,
            "topic": "router",
            "expected": "FACT-225-vo6pc",
            "id": "mem_5874d95467",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-225-vo6pc",
            "correct": true
          },
          {
            "index": 16,
            "turn": 240,
            "topic": "gateway",
            "expected": "FACT-240-bnezh",
            "id": "mem_3ae5ba67ee",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-240-bnezh",
            "correct": true
          },
          {
            "index": 17,
            "turn": 255,
            "topic": "router",
            "expected": "FACT-255-ouzrk",
            "id": "mem_18480203e6",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-255-ouzrk",
            "correct": true
          },
          {
            "index": 18,
            "turn": 270,
            "topic": "gateway",
            "expected": "FACT-270-abmgy",
            "id": "mem_c28122e1a9",
            "inTail": false,
            "evicted": true,
            "answer": "FACT-270-abmgy",
            "correct": true
          },
          {
            "index": 19,
            "turn": 285,
            "topic": "router",
            "expected": "FACT-285-o73dt",
            "id": "mem_98d285b861",
            "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": 23296,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 150,
        "reasoning_output_tokens": 39,
        "total_tokens": 23446
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "437951a9120ce3a731cb2812038a53b1dd0df339afe3d4b9a0fc0fe743d2ef4d",
      "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": "2167570ab9a3dd89ee827822aff4713e692e274987b38a12f775220724143d1e",
      "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": 35243,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 362,
        "reasoning_output_tokens": 142,
        "total_tokens": 35605
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "d0111329cef70a61cbdc2bfda47096cb67259ac8568af919d45f09a1b7001d97",
      "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": "e8b012febc383598cbb3ff504863b28681f7670b3c4725f76878c64163b2b342",
      "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": 23296,
        "cached_input_tokens": 21120,
        "cache_write_input_tokens": 0,
        "output_tokens": 150,
        "reasoning_output_tokens": 39,
        "total_tokens": 23446
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "477e29edc40cfa71838fbac871cb6c24c322429e2c69fb6c696321dbdf52c14b",
      "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": "69cd5e2ecdef55d805f9e5d63d292a03038267fe10952751f3a51332c3c9663f",
      "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": 29543,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 357,
        "reasoning_output_tokens": 140,
        "total_tokens": 29900
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "f23663d5fbec09b96d0b06d0f26d308954944e258439a4d0b7008670a7e3675e",
      "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": "381ef5f3cd93b637aaf27b2746b7b117be7554207e72542c6896b8ae4613c985",
      "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": 23295,
        "cached_input_tokens": 21120,
        "cache_write_input_tokens": 0,
        "output_tokens": 161,
        "reasoning_output_tokens": 51,
        "total_tokens": 23456
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "3e8523d5227ec5c85100bf34dd9df1c6ad22edb372b5b42cec118b8603663245",
      "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": "6fd8335e47f6e1b902f434d662060e40b1a3be0f9ea2ed99c5869bc7b7d16741",
      "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": 29542,
        "cached_input_tokens": 13184,
        "cache_write_input_tokens": 0,
        "output_tokens": 370,
        "reasoning_output_tokens": 147,
        "total_tokens": 29912
      },
      "reasoningEffort": "xhigh",
      "configurationUpdates": [],
      "sessionLogSha256": "acd00c8fa4305b14449869a9bd68ff97ded90fbe04d7940241b7889697e4fcf6",
      "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": "0117116b6e397b95df2f0c1edadf96b718e7606916f39726fb68711d718baca1",
      "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": 164215,
      "cached_input_tokens": 94976,
      "cache_write_input_tokens": 0,
      "output_tokens": 1550,
      "reasoning_output_tokens": 558,
      "total_tokens": 165765
    },
    "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."
  ]
}
