| { |
| "gate": 1, |
| "phase": "Phase 1 - Subspace + faithfulness (mid-layer re-evaluation)", |
| "variant": "block6_midlayer", |
| "supersedes_record": "gate_1.json was the final-layer run (FAIL); kept as a layer-ablation control.", |
| "status": "QUALIFIED", |
| "status_detail": "Subspace-validity (absolute) PASS; comparator clause (beat attention) NOT met (tie).", |
| "metrics": [ |
| { |
| "name": "token_lesion_auroc_density_A", |
| "modality": "LIDC-IDRI(val)", "layer": 6, "budget": null, |
| "value": 0.7693, "ci95": [0.7630, 0.7755], "test": "DeLong", |
| "threshold": 0.70, "threshold_status": "CALIBRATE", |
| "passed": true, |
| "detail": "Construction A (density/kNN) at block 6. Clears AUROC floor 0.70 and CI-lower 0.763 > 0.65. Final-layer was 0.565." |
| }, |
| { |
| "name": "token_lesion_auroc_residual_B", |
| "modality": "LIDC-IDRI(val)", "layer": 6, "budget": null, |
| "value": 0.7431, "ci95": [0.7366, 0.7495], "test": "DeLong", |
| "threshold": 0.70, "threshold_status": "CALIBRATE", |
| "passed": true, |
| "detail": "Construction B (residual) at block 6. Clears the AUROC floor." |
| }, |
| { |
| "name": "comparator_attention_saliency_auroc", |
| "modality": "LIDC-IDRI(val)", "layer": "final", "budget": null, |
| "value": 0.7668, "ci95": [0.7605, 0.7731], "test": "DeLong", |
| "threshold": null, "threshold_status": "comparator", "passed": true, |
| "detail": "Best attention (final block) used as the conservative comparator." |
| }, |
| { |
| "name": "density_A_vs_attention_delong_diff", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": 0.0025, "ci95": [-0.0045, 0.0094], "test": "DeLong_paired", |
| "threshold": 0.0, "threshold_status": "FIXED(must_exceed_0)", |
| "passed": false, |
| "detail": "TIE: CI includes 0 (p=0.49). density-A matches but does not beat best attention." |
| }, |
| { |
| "name": "residual_B_vs_attention_delong_diff", |
| "modality": "LIDC-IDRI(val)", "budget": null, |
| "value": -0.0237, "ci95": [-0.0315, -0.0160], "test": "DeLong_paired", |
| "threshold": 0.0, "threshold_status": "FIXED(must_exceed_0)", "passed": false, |
| "detail": "B is slightly below attention." |
| }, |
| { |
| "name": "dice_vs_mask_density_A", |
| "modality": "LIDC-IDRI(val)", "layer": 6, "budget": null, |
| "value": 0.1835, "ci95": null, "test": "mean_dice@q0.9", |
| "threshold": 0.0095, "threshold_status": "CALIBRATE(2x_random)", "passed": true, |
| "detail": "Dice(>3-patch) 0.183, Dice(1-3 patch) 0.054 vs ~0.005 random proxy. ~2.3x the final-layer Dice." |
| } |
| ], |
| "thresholds_locked_ref": null, |
| "seeds": [0], |
| "data_gaps": [], |
| "eval_summary": { |
| "eval_split": "val", "layer": 6, |
| "n_patches": 916496, "n_lesion_patches": 4368, |
| "token_bank": "processed/covtoken/ct_token_bank_block5.pt (2,107,392 mid-layer tokens)", |
| "metrics_artifact": "processed/covtoken/gate1_block5_metrics.json", |
| "diagnostic_sweep": "processed/covtoken/diagnostic_sweep.json" |
| }, |
| "decision_rule": "PASS iff better construction AUROC>=0.70 (CI lower>0.65) AND beats attention by DeLong CI excluding 0.", |
| "decision": "QUALIFIED. The load-bearing assumption (L(x) localizes lesions without labels) HOLDS at block 6: density-A=0.769 clears the AUROC floor and Dice >> random, reversing the final-layer FAIL (0.565). However density-A TIES the best attention comparator (diff +0.0025, p=0.49), so the strict 'beats saliency' clause is not met. The method is competitive with, but not superior to, attention as a localizer.", |
| "open_question": "The formalization's contribution is the CONSTRAINT (coverage floor + interpretable dual + per-image certificate), not the localizer ranking. A subspace that TIES attention may still yield a constrained pruner that BEATS saliency pruning on small-lesion miss-rate (Gate 3) -- that is the decisive test, not the Gate-1 localizer comparison.", |
| "human_signoff": null |
| } |
|
|
