gate_reports/gate_3_kits.json

{
  "gate": 3, "phase": "Phase 3 - Core falsification (KiTS23 kidney tumors) [block-3]",
  "modality": "KiTS23", "status": "PASS",
  "metrics": [
    {"name": "small_lesion_sensitivity_delta", "budget": 0.25, "value": 0.0736,
     "ci95": [0.0414, 0.1052], "test": "paired_bootstrap_n2000", "threshold": 0.05,
     "threshold_status": "CALIBRATE->effect>=5pts_OR>=20%missred", "passed": true,
     "detail": "Small-lesion recall: coverage 0.887 vs saliency 0.814 = +7.36 pts; miss-rate rel. reduction 40%; CI excludes 0. n=559."},
    {"name": "small_lesion_sensitivity_delta", "budget": 0.5, "value": 0.0155,
     "ci95": [0.0080, 0.0230], "test": "paired_bootstrap_n2000", "threshold": 0.05,
     "threshold_status": "CALIBRATE->effect>=5pts_OR>=20%missred", "passed": true,
     "detail": "Small-lesion recall: coverage 0.998 vs saliency 0.983 = +1.55 pts BUT miss-rate rel. reduction 91% (>=20%); CI excludes 0."}
  ],
  "eval_summary": {"eval_split": "test", "layer": 3, "n_small_lesion_slices": 559,
    "coverage_pruning": "top-k by block-3 density-A", "saliency_pruning": "top-k final-block attention",
    "metrics_artifact": "processed/covtoken/gate3_kits_metrics.json"},
  "decision_rule": "PASS iff coverage beats saliency by >=5 small-lesion pts OR >=20% miss-rate reduction, CI excludes 0, at BOTH budgets.",
  "decision": "PASS. Coverage-constrained pruning beats saliency pruning on small kidney-tumor recall at both budgets (+7.4 pts @0.25; +91% miss-rate reduction @0.5). 2nd PASS dataset after LIDC. The win holds even though Gate 1 only TIES attention -- evidence the constraint, not token ranking, drives it.",
  "human_signoff": null
}