| { |
| "gate": 1, |
| "phase": "Phase 1 - Subspace + faithfulness", |
| "status": "FAIL", |
| "fallback_path": null, |
| "metrics": [ |
| { |
| "name": "token_lesion_auroc_density_A", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": 0.5650, "ci95": [0.5579, 0.5720], "test": "DeLong", |
| "threshold": 0.70, "threshold_status": "CALIBRATE", |
| "passed": false, |
| "detail": "Construction A (density / kNN-sparse). AUROC 0.565, CI lower 0.558 < 0.65." |
| }, |
| { |
| "name": "token_lesion_auroc_residual_B", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": 0.5509, "ci95": [0.5440, 0.5578], "test": "DeLong", |
| "threshold": 0.70, "threshold_status": "CALIBRATE", |
| "passed": false, |
| "detail": "Construction B (normal-manifold residual). AUROC 0.551, CI lower 0.544 < 0.65." |
| }, |
| { |
| "name": "comparator_attention_saliency_auroc", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": 0.7668, "ci95": [0.7605, 0.7731], "test": "DeLong", |
| "threshold": null, "threshold_status": "comparator", |
| "passed": true, |
| "detail": "CLS-to-token attention (last block, exact). Strongly localizes lesions, confirming masks+patch alignment are valid." |
| }, |
| { |
| "name": "comparator_random_auroc", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": 0.5115, "ci95": [0.5028, 0.5201], "test": "DeLong", |
| "threshold": null, "threshold_status": "comparator", "passed": true, |
| "detail": "Random baseline ~0.5 as expected." |
| }, |
| { |
| "name": "density_A_vs_attention_delong_diff", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": -0.2018, "ci95": [-0.2094, -0.1942], "test": "DeLong_paired", |
| "threshold": 0.0, "threshold_status": "FIXED(must_exceed_0)", |
| "passed": false, |
| "detail": "A is 0.202 AUROC WORSE than attention; CI excludes 0 in the wrong direction (p~0)." |
| }, |
| { |
| "name": "residual_B_vs_attention_delong_diff", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": -0.2159, "ci95": [-0.2235, -0.2083], "test": "DeLong_paired", |
| "threshold": 0.0, "threshold_status": "FIXED(must_exceed_0)", |
| "passed": false, |
| "detail": "B is 0.216 AUROC WORSE than attention; CI excludes 0 in the wrong direction (p~0)." |
| }, |
| { |
| "name": "dice_vs_mask_density_A", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": 0.0787, "ci95": null, "test": "mean_dice@q0.9", |
| "threshold": 0.0095, "threshold_status": "CALIBRATE(2x_random)", |
| "passed": true, |
| "detail": "Dice (>3-patch lesions) 0.079 vs ~0.005 random proxy; Dice(1-3 patch) 0.023. Weak but > random." |
| } |
| ], |
| "thresholds_locked_ref": null, |
| "seeds": [0], |
| "data_gaps": [], |
| "eval_summary": { |
| "eval_split": "val", |
| "n_patches": 916496, |
| "n_lesion_patches": 4368, |
| "lesion_prevalence": 0.00477, |
| "eval_slices": 4676, |
| "pos_slices": 2338, |
| "neg_slices_sampled": 2338, |
| "token_bank": "processed/covtoken/ct_token_bank_v0.pt (2,107,392 tokens)", |
| "eval_masks": "processed/lidc_v2 (TCIA DICOM-SEG, z-ordered, self-consistent)", |
| "metrics_artifact": "processed/covtoken/gate1_metrics.json" |
| }, |
| "decision_rule": "PASS iff the better construction has AUROC>=0.70 (CI lower>0.65) AND beats attention-saliency with DeLong CI excluding 0. FAIL if neither construction beats saliency.", |
| "decision": "FAIL: neither label-free construction reaches the AUROC floor, and both are ~0.20 AUROC WORSE than the attention-saliency comparator. The load-bearing assumption (L(x) localizes lesions without labels in MedDINOv3 feature space) does not hold as specified.", |
| "post_mortem": "gate_reports/gate_1_postmortem.md", |
| "human_signoff": null |
| } |
|
|
