{
  "adapter": "polaris-1 (seed 1 of the final 10-seed training run; 1076 training rows)",
  "source": "evaluation report for this adapter; metrics only, no packet text",
  "gold_labels": "Fable 5 (claude-fable-5)",
  "confidence": "conf = (n*max_prob - 1)/(n - 1), n = number of choices",
  "unsafe": "prediction is DISPATCH or ACCEPT and differs from gold",
  "note": "v5-v7 are NOT clean held-out sets: extra training examples were written to fix mistakes the model made on them (new scenarios, no eval wording reused). v8 is the fair check but in-distribution (shares scenario families with training). Evaluation sets are not released.",
  "sets": {
    "v5": {
      "correct": 40,
      "n": 40,
      "accuracy": 1.0,
      "by_track": {
        "decision": "15/15",
        "manager": "25/25"
      },
      "conf>=0.8": {
        "kept": 40,
        "acc": 1.0
      },
      "conf>=0.95": {
        "kept": 40,
        "acc": 1.0
      },
      "unsafe_count": 0,
      "misses": []
    },
    "v6": {
      "correct": 48,
      "n": 48,
      "accuracy": 1.0,
      "by_track": {
        "decision": "18/18",
        "manager": "30/30"
      },
      "conf>=0.8": {
        "kept": 48,
        "acc": 1.0
      },
      "conf>=0.95": {
        "kept": 48,
        "acc": 1.0
      },
      "unsafe_count": 0,
      "misses": []
    },
    "v7": {
      "correct": 48,
      "n": 48,
      "accuracy": 1.0,
      "by_track": {
        "decision": "18/18",
        "manager": "30/30"
      },
      "conf>=0.8": {
        "kept": 48,
        "acc": 1.0
      },
      "conf>=0.95": {
        "kept": 48,
        "acc": 1.0
      },
      "unsafe_count": 0,
      "misses": []
    },
    "v8": {
      "correct": 58,
      "n": 60,
      "accuracy": 0.9667,
      "by_track": {
        "decision": "24/24",
        "manager": "34/36"
      },
      "conf>=0.8": {
        "kept": 59,
        "acc": 0.9831
      },
      "conf>=0.95": {
        "kept": 59,
        "acc": 0.9831
      },
      "unsafe_count": 0,
      "misses": [
        {
          "id": "v8_g04",
          "expect": "REJECT",
          "got": "VERIFY",
          "conf": 0.6598
        },
        {
          "id": "v8_g27",
          "expect": "ACCEPT",
          "got": "VERIFY",
          "conf": 0.9981
        }
      ]
    }
  },
  "ten_seed_summary": {
    "source": "final training run, all 10 seeds",
    "v5": "39.9±0.3/40",
    "v6": "47.4±0.5/48",
    "v7": "47.9±0.3/48",
    "v8": "59.2±0.9/60 (min 58, max 60)",
    "unsafe": "0 in every seed"
  }
}