fix: complete models table with real param counts (9.33M/34.2M/25.86M/8.94M)

README.md

@@ -156,19 +156,20 @@ results = yolo("path/to/print_image.png", conf=0.3)
 
 | File | Description | AUROC | Params |
 |---|---|---|---|
-| `models/cdm_v3_yolo_bbox.pt` | **CDM λ=0.01, YOLO bbox** (thesis proposed) | 0.8603 single-split | 9.3 M |
-| `models/cdm_v3_baseline.pt` | CDM λ=0 baseline | 0.8673 ± 0.023 CV | 9.3 M |
-| `models/cdm_v3_test.pt` | Development checkpoint | — | 9.3 M |
-| `models/yolo_best.pt` | YOLOv8 feature detector | mAP@50=0.950 | — |
-| `models/semantic_mismatch_angle_model.pt` | Per-feature: angle | — | — |
-| `models/semantic_mismatch_dist1_model.pt` | Per-feature: dist1 | — | — |
-| `models/semantic_mismatch_dots_model.pt` | Per-feature: dots | — | — |
+| `models/cdm_v3_yolo_bbox.pt` | **CDM λ=0.01, base_ch=64 (proposed)** | 0.8603 single-split | **9.33 M** |
+| `models/cdm_v3_baseline.pt` | CDM λ=0, base_ch=128 (thesis CV result) | 0.8673 ± 0.023 CV | **34.2 M** |
+| `models/cdm_v3_test.pt` | CDM λ=0.01, base_ch=64 (dev checkpoint) | ≈0.85 | 9.33 M |
+| `models/yolo_best.pt` | YOLOv8 feature detector (8 print features) | mAP@50=0.950 | **25.86 M** |
+| `models/semantic_mismatch_angle_model.pt` | Per-feature CDM: angle (~9.67:1 imbalance) | ~0.82 | **8.94 M** |
+| `models/semantic_mismatch_dist1_model.pt` | Per-feature CDM: dist1 | ~0.89 | **8.94 M** |
+| `models/semantic_mismatch_dots_model.pt` | Per-feature CDM: dots (best feature) | ~0.96 | **8.94 M** |
 
 ### Which model should I use?
 
-- **Quick evaluation:** `cdm_v3_yolo_bbox.pt` — the thesis "proposed CDM", trained with separation loss λ=0.01
-- **Reproducing the thesis CV result:** Use `cdm_v3_baseline.pt` (λ=0) — the 5-fold CV AUROC 0.8673 ± 0.023 comes from the baseline
-- **YOLO feature detection only:** `yolo_best.pt`
+- **Quick evaluation:** `cdm_v3_yolo_bbox.pt` — the thesis "proposed CDM", λ=0.01, base_ch=64 (**9.33 M params**)
+- **Reproducing the thesis CV result:** `cdm_v3_baseline.pt` — λ=0, base_ch=128 (**34.2 M params**); the 5-fold CV AUROC 0.8673 ± 0.023 comes from this wider model
+- **YOLO feature detection only:** `yolo_best.pt` (25.86 M params, YOLOv8-based)
+- **Per-feature analysis:** `semantic_mismatch_*.pt` — one model per feature, 8.94 M each, trained with a DiffGuard-style contrastive approach
 
 > **Why does the baseline win on CV?** On this small dataset (~1330 samples), the 5-fold CV shows λ=0 and λ=0.01 are statistically indistinguishable (0.8673 vs 0.8628). The single-split evaluation clearly favors λ=0.01 (+2.8 pp AUROC, −19 pp FPR@95). The thesis reports the CV result as the primary finding since it is more reliable.