calibration.json

{
  "fitted_on": "benchmarks/_raw_dev_unlisted.json",
  "n_dev_items": 5441,
  "temperature": 1.4978117508891504,
  "ece_before": 0.048161102888937414,
  "ece_after": 0.011165273365421908,
  "thresholds": {
    "max_accuracy": {
      "threshold": 0.318732,
      "dev_combined_accuracy": 0.8213563683146481
    },
    "zero_regression": {
      "threshold": 0.984069,
      "dev_coverage": 0.07755927219261165
    }
  },
  "default_threshold": 0.318732,
  "note": "Fitted on dev only. scripts/evaluate.py reports the real test-set regression count at these thresholds; a dev-set zero-regression point is an empirical guarantee, not a proof."
}