| { |
| "_meta": { |
| "phase": "1b", |
| "purpose": "Replace [CALIBRATE] convention thresholds with data-driven values derived from the saliency/random baselines, per IMPLEMENTATION_SPEC Phase 1b. [FIXED] thresholds are unchanged. Locked; immutable thereafter.", |
| "operating_layer": "block 3 (mid-layer)", |
| "calibration_date": "2026-06-20", |
| "baselines_used": { |
| "random_localizer_auroc": {"value": 0.5115, "ci95": [0.5028, 0.5201], "source": "gate1 random comparator"}, |
| "attention_saliency_auroc": {"value": 0.7668, "ci95": [0.7605, 0.7731], "source": "gate1 attention comparator (LIDC)"}, |
| "gate2_null_coupling_rho": {"value": 0.0, "std_analytic": 0.0102, "n": 9520, "note": "Spearman of a random per-(slice,ratio) score vs detection drop ~ N(0, 1/sqrt(n)); 99th pct ~ 0.024."}, |
| "gate3_null_effect": {"value": 0.0, "note": "saliency-vs-saliency paired difference is 0 by construction."} |
| } |
| }, |
| "gate1": { |
| "auroc_floor": { |
| "calibrated": 0.767, "was_convention": 0.70, "status": "CALIBRATE->locked", |
| "derivation": "Set to the attention-saliency baseline: a label-free localizer must be at least as good as the best label-free alternative (attention). STRICTER than the 0.70 convention.", |
| "binding_clause": "AND must beat attention with DeLong CI excluding 0 (significance)." |
| }, |
| "ci_lower_min": {"calibrated": 0.70, "was_convention": 0.65, "status": "CALIBRATE->locked", |
| "derivation": "CI lower bound must exceed the attention point estimate minus a small margin."} |
| }, |
| "gate2": { |
| "spearman_rho_min": { |
| "calibrated": "BASELINE: saliency-score coupling under the identical random protocol", |
| "was_convention": 0.50, "status": "CALIBRATE->LOCKED (baseline-coupling experiment done)", |
| "calibrated_bar": "coverage coupling > saliency coupling (CI excl 0)", |
| "result": "FAIL on superiority: coverage rho 0.480 vs saliency 0.479, diff +0.0013 CI [-0.005,+0.007] (includes 0). Coverage is NOT a superior proxy vs saliency; both capped at ~0.48 by small-lesion combinatorics. GUARD (not-blind) satisfied.", |
| "experiment_ref": "gate_reports/gate_2_baseline.json" |
| } |
| }, |
| "gate3": { |
| "small_lesion_effect_min_points": {"calibrated": 5.0, "was_convention": 5.0, "status": "FIXED-clinical", |
| "derivation": "Clinical effect-size floor retained; null effect is 0 so any significant positive gain is meaningful."}, |
| "miss_rate_rel_reduction_min": {"calibrated": 0.20, "was_convention": 0.20, "status": "FIXED-clinical"} |
| }, |
| "gate4": { |
| "cohens_d_min": {"calibrated": 0.5, "was_convention": 0.5, "status": "convention-retained"}, |
| "constraint_satisfaction_min": {"value": 0.95, "status": "FIXED"} |
| }, |
| "gate5": { |
| "rankme_ratio_min": {"value": 0.90, "status": "CALIBRATE->N/A (FALLBACK: inference-time, no pretraining run)"}, |
| "linear_probe_within_points": {"value": 2.0, "status": "CALIBRATE->N/A (FALLBACK)"} |
| } |
| } |
|
|
