Add analysis scripts and experiment configurations for bridge attention and sensitivity studies

- Introduced `bridge_attention_ceiling_check.py` for variance decomposition analysis on bridge attention configurations.
- Added `bridge_attention_readout.py` to perform per-tower gate and contribution readouts, including AUC sanity checks.
- Created multiple JSON configuration files for backbone replication experiments, including anonymous CV variants and basic backbones.
- Implemented sensitivity experiments to evaluate the impact of axial length inclusion and EfficientNetV2-M performance at higher resolutions.
- Added a memory probe script to assess GPU memory usage during training with EfficientNetV2-M.

v4/figures/F4_bilateral.py

@@ -58,15 +58,15 @@ SEV_LABELS = {
     "severe": "Glaucoma — severe (VF_MD < −12)",
     "unknown": "Glaucoma — VF_MD not recorded",
 }
-SEV_ORDER = ["normal", "unknown", "early", "moderate", "severe"]
+SEV_ORDER = ["severe", "moderate", "unknown", "early", "normal"]
 SEV_ALPHA = {
-    "normal": 0.40,
-    "unknown": 0.35,
+    "normal": 0.55,
+    "unknown": 0.55,
     "early": 0.55,
-    "moderate": 0.70,
-    "severe": 0.85,
+    "moderate": 0.55,
+    "severe": 0.55,
 }
-SEV_SIZE = {"normal": 6, "unknown": 6, "early": 8, "moderate": 10, "severe": 12}
+SEV_SIZE = {"normal": 8, "unknown": 8, "early": 8, "moderate": 8, "severe": 8}
 
 # Panel grid: [row][col] = (label, run_dir, eval_stage)
 GRID = [