Add new regression and ensemble experiment configurations for V2-M and OrthoBridge

- Introduced multiple regression experiment configurations targeting vf_md, including:
  - cd_solo_reg_set.json: CD tower only regression setup.
  - img_solo_reg_set.json: Image tower only regression setup.
  - reg_head_epoch_sweep.json: Baseline regression sweeps at different epochs (50, 75, 100).
  - reg_head_set.json: Various regression setups including baseline and OrthoBridge configurations.
  - single_eye_reg.json: Single-eye regression setup for worst-eye aggregation analysis.

- Added ensemble configurations for OrthoBridge with different inner bridges:
  - ortho_alts_ensemble.json: Ensemble tests with ConcatBridge, PairwiseAdditiveBridge, and GatedAdditiveBridge.
  - ortho_alts_tritower.json: Tritower tests with the same inner bridges.

- Created V2-M specific configurations:
  - baseline_reg_nt50.json: Regression baseline with V2-M backbone.
  - geom_vec_gt.json and geom_vec_unet.json: Geometry vector injection experiments with V2-M.
  - single_l1_bridges.json: Single-eye ensemble experiments with various bridge types.
  - tritower_geom_gt.json: Tritower setup with GT contour-rasterized masks.

- Promoted existing experiments to higher repetitions for robustness.

v4/scripts/experiments/phase2_v4/papila_backbones.json

@@ -0,0 +1,37 @@
+[
+  {
+    "_note": "PAPILA paper backbone replication — VGG16, single-eye img-only, ImageNet-pretrained (no fundus pretraining). For Figure 2 anchor row.",
+    "run_name": "experiments/phase2_v4/papila_backbones/vgg16",
+    "reps": 10,
+    "tower_overrides": {
+      "img": { "args": { "backbone": "vgg16", "freeze_ratio": 0.0 } }
+    }
+  },
+
+  {
+    "_note": "DenseNet121 ImageNet-pretrained, no fundus.",
+    "run_name": "experiments/phase2_v4/papila_backbones/densenet121",
+    "reps": 10,
+    "tower_overrides": {
+      "img": { "args": { "backbone": "densenet121", "freeze_ratio": 0.0 } }
+    }
+  },
+
+  {
+    "_note": "MobileNetV2 ImageNet-pretrained, no fundus.",
+    "run_name": "experiments/phase2_v4/papila_backbones/mobilenet_v2",
+    "reps": 10,
+    "tower_overrides": {
+      "img": { "args": { "backbone": "mobilenet_v2", "freeze_ratio": 0.0 } }
+    }
+  },
+
+  {
+    "_note": "InceptionV3 ImageNet-pretrained, no fundus. (Note: 299x299 native; pipeline uses 224 — note in figure caption.)",
+    "run_name": "experiments/phase2_v4/papila_backbones/inception_v3",
+    "reps": 10,
+    "tower_overrides": {
+      "img": { "args": { "backbone": "inception_v3", "freeze_ratio": 0.0 } }
+    }
+  }
+]