Update README: mark CheXpert densenet as pending retrain (batch_size 64→128)

README.md

@@ -93,7 +93,7 @@ insurance_paper_weights/
 
 | Experiment | Description | Model | Config | # Checkpoints | HF path | Available? |
 |------------|-------------|-------|--------|---------------|---------|------------|
-| **exp0** | Baselines (CheXpert/MIMIC) | All 3 | — | 6 | `exp0/{dataset}/{model}.pt` | Yes |
+| **exp0** | Baselines (CheXpert/MIMIC) | All 3 | — | 5 (of 6) | `exp0/{dataset}/{model}.pt` | CheXpert/densenet.pt pending retrain (batch_size fix) |
 | **exp0-2** | Random Initialisation | SwinT | — | 1 | `exp0-2/swinTF_random.pt` | Yes |
 | **exp1-1** | Patch keep/remove | MedMamba | 9 patches x 2 | 18 | `exp1-1/mamba_{keep/remove}/patch{N}.pt` | Yes |
 | **exp1-2** | Patch keep/remove | DenseNet + SwinT | 9 patches x 2 x 2 | 36 | `exp1-2/{densenet,swinTF}_{keep/remove}/patch{N}.pt` | Yes |
@@ -179,11 +179,11 @@ Weights in JAMA_codes were trained on ORCD. Weights marked with (*) were trained
 
 ## Bootstrap Evaluation Status
 
-All 153 bootstrap evaluations complete (n_bootstrap=20, sample_size=1000, seed=42).
+152 of 153 bootstrap evaluations complete (n_bootstrap=20, sample_size=1000, seed=42).
 
 | Experiment | Evaluations | Status |
 |-----------|-------------|--------|
-| **exp0** | 6 (3 models x 2 datasets) | Done |
+| **exp0** | 5 of 6 (3 models x 2 datasets) | CheXpert densenet pending retrain (batch_size 64→128) |
 | **exp0-2** | 1 | Done |
 | **exp1-1** | 18 (mamba keep + remove x 9 patches) | Done |
 | **exp1-2** | 36 (densenet keep/remove + swinTF keep/remove x 9 patches) | Done |