{
  "threshold": 0.007,
  "train_auc": 0.7208,
  "eval_auc": 0.7253,
  "train_refused_unanswerable_pct": 11.5,
  "train_false_refusal_pct": 3.58,
  "eval_refused_unanswerable_pct": 24.0,
  "eval_false_refusal_pct": 5.33,
  "eval_refused_by_category": {
    "unknown_attribute": 6
  },
  "eval_answerable_refused": {
    "alias_paraphrase": [
      2,
      25
    ],
    "multi_hop": [
      0,
      25
    ],
    "near_miss": [
      2,
      25
    ]
  }
}