{
  "schemaVersion": "modelcap-launch-validation-v1",
  "generatedAt": "2026-09-30T20:54:24.517Z",
  "ledgerDigest": "9e00e6a03d36affd9f0db0b4e3736333e6d2cbdb41a36f98e2d6ea1ca74b6a66",
  "prospective": {
    "n": 12,
    "mae": 9.3,
    "signedMedian": -1.9,
    "p80": 13.9,
    "coverage80": 0.75
  },
  "channels": {
    "corpus-prior": {
      "n": 4,
      "mae": 13.9,
      "signedMedian": -10.5,
      "p80": 21,
      "coverage80": 1
    },
    "family-succession": {
      "n": 4,
      "mae": 7.4,
      "signedMedian": -7.8,
      "p80": 13.9,
      "coverage80": 0.75
    },
    "measured-specialist": {
      "n": 5,
      "mae": 11.1,
      "signedMedian": -3.9,
      "p80": 17.1,
      "coverage80": 1
    },
    "within-card": {
      "n": 4,
      "mae": 6.5,
      "signedMedian": 6.5,
      "p80": 10.4,
      "coverage80": 0.5
    }
  },
  "publishers": {
    "deepseek": {
      "n": 3,
      "mae": 4.7,
      "signedMedian": 2.5,
      "p80": 8.8,
      "coverage80": 1
    },
    "google": {
      "n": 1,
      "mae": 17.1,
      "signedMedian": -17.1,
      "p80": 17.1,
      "coverage80": 1
    },
    "meta": {
      "n": 2,
      "mae": 10.3,
      "signedMedian": 3.4,
      "p80": 13.6,
      "coverage80": 1
    },
    "moonshotai": {
      "n": 1,
      "mae": 3.9,
      "signedMedian": -3.9,
      "p80": 3.9,
      "coverage80": 1
    },
    "nvidia": {
      "n": 1,
      "mae": 10.1,
      "signedMedian": 10.1,
      "p80": 10.1,
      "coverage80": 0
    },
    "openai": {
      "n": 2,
      "mae": 17.5,
      "signedMedian": -17.4,
      "p80": 21,
      "coverage80": 0.5
    },
    "x-ai": {
      "n": 1,
      "mae": 0.1,
      "signedMedian": 0.1,
      "p80": 0.1,
      "coverage80": 1
    },
    "xiaomi": {
      "n": 1,
      "mae": 10.4,
      "signedMedian": 10.4,
      "p80": 10.4,
      "coverage80": 0
    }
  },
  "pairwise": {
    "n": 46,
    "accuracy": 0.652,
    "minimumGap": 5
  },
  "drift": [],
  "outcomesMissing": [],
  "retrospective": {
    "label": "retrospective-2026-08-11-not-prospective",
    "n": 4,
    "mae": 28,
    "signedMedian": 22.4,
    "records": [
      {
        "modelId": "qwen/qwen3.6-27b",
        "estimatedAt": "2026-08-11T05:57:40.129Z",
        "estimate": 67.29942300757301,
        "channel": "within-card-peer-interpolation",
        "measuredAt": "2026-09-05T03:22:03.140Z",
        "measuredPoint": 23.1,
        "boards": [
          "WildClawBench OpenClaw"
        ],
        "generalBacked": false,
        "signedError": 44.2
      },
      {
        "modelId": "inclusionai/ling-3.0-flash",
        "estimatedAt": "2026-08-11T05:57:40.129Z",
        "estimate": 60.06035661419917,
        "channel": "peer-anchored-reported-benchmarks",
        "measuredAt": "2026-09-05T03:22:03.140Z",
        "measuredPoint": 59.6,
        "boards": [
          "Artificial Analysis Intelligence Index"
        ],
        "generalBacked": true,
        "signedError": 0.5
      },
      {
        "modelId": "z-ai/glm-5-turbo",
        "estimatedAt": "2026-08-11T05:57:40.129Z",
        "estimate": 80.79109371263212,
        "channel": "peer-anchored-reported-benchmarks",
        "measuredAt": "2026-09-05T03:22:03.140Z",
        "measuredPoint": 17.8,
        "boards": [
          "WildClawBench OpenClaw"
        ],
        "generalBacked": false,
        "signedError": 63
      },
      {
        "modelId": "meta/muse-glimmer-30b",
        "estimatedAt": "2026-08-11T05:57:40.129Z",
        "estimate": 51.78268433938056,
        "channel": "peer-anchored-reported-benchmarks",
        "measuredAt": "2026-09-05T03:22:03.140Z",
        "measuredPoint": 55.9,
        "boards": [
          "Artificial Analysis Intelligence Index",
          "WildClawBench OpenClaw"
        ],
        "generalBacked": true,
        "signedError": -4.1
      }
    ]
  }
}
