{ "overall_auc": 0.6741, "per_category": { "alias_paraphrase": { "n": 25, "auc": null, "mean_pos": 0.8255, "mean_neg": null }, "long_fact": { "n": 25, "auc": null, "mean_pos": 0.7631, "mean_neg": null }, "multi_entity": { "n": 25, "auc": null, "mean_pos": 0.7077, "mean_neg": null }, "multi_hop": { "n": 25, "auc": null, "mean_pos": 0.7697, "mean_neg": null }, "near_miss": { "n": 25, "auc": null, "mean_pos": 0.7452, "mean_neg": null }, "noise_context": { "n": 25, "auc": null, "mean_pos": 0.6853, "mean_neg": null }, "unknown_attribute": { "n": 25, "auc": null, "mean_pos": null, "mean_neg": 0.7149 }, "update_conflict": { "n": 25, "auc": null, "mean_pos": 0.7203, "mean_neg": null } }, "best_threshold": { "margin": 0.02, "refused_unknown_pct": 40.0, "false_refusal_pct": 3.43 }, "auc": { "max": 0.6741, "margin": 0.9413, "zscore": 0.1767 } }