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/classes/dataset.py

@@ -208,10 +208,22 @@ class HTDataset(Dataset):
 
     def __getitem__(self, idx: int) -> dict[str, Any]:
         entry  = self.entries[idx]
-        sample = {
+        sample: dict[str, Any] = {
             "label":     torch.tensor(entry.label, dtype=torch.long),
             "entity_id": entry.entity_id,
         }
+        # Any per-entry auxiliary fields the profile attached via meta
+        # (e.g. vf_md for regression heads) flow into the batch dict
+        # alongside `label` and tower inputs.
+        for k, v in entry.meta.items():
+            if k in sample:
+                continue   # don't overwrite primary fields
+            if isinstance(v, torch.Tensor):
+                sample[k] = v
+            elif isinstance(v, (int, float)):
+                sample[k] = torch.tensor(v, dtype=torch.float32)
+            else:
+                sample[k] = v
         for name, tower in self.towers.items():
             sample[name] = tower.get_sample(entry)
         return sample