Remove legacy event and mixed distribution paths

eval_data.py

@@ -151,6 +151,33 @@ def build_model_from_dataset(
             f"{model_target_mode!r}"
         )
     model_architecture = resolve_model_architecture(cfg, state_dict)
+    continuous_value_center = None
+    continuous_value_scale = None
+    if dataset.n_cont_types > 0:
+        scaling = str(cfg.get("continuous_value_scaling", "")).lower()
+        if scaling != "robust":
+            raise RuntimeError(
+                "Continuous-variable checkpoints must declare "
+                "continuous_value_scaling='robust'; unscaled checkpoints are "
+                "not supported"
+            )
+        if state_dict is None:
+            raise RuntimeError(
+                "A checkpoint state_dict is required to restore RobustScale buffers"
+            )
+        center_key = "tokenizer.continuous_value_center"
+        scale_key = "tokenizer.continuous_value_scale"
+        missing = [
+            key for key in (center_key, scale_key)
+            if key not in state_dict
+        ]
+        if missing:
+            raise RuntimeError(
+                "Checkpoint is missing required RobustScale buffers: "
+                + ", ".join(missing)
+            )
+        continuous_value_center = state_dict[center_key]
+        continuous_value_scale = state_dict[scale_key]
     return DeepHealth(
         vocab_size=dataset.vocab_size,
         n_embd=int(cfg_get(args, cfg, "n_embd", 120)),
@@ -161,9 +188,8 @@ def build_model_from_dataset(
         n_categories=dataset.n_categories,
         cont_type_ids=dataset.cont_type_ids,
         n_bins=int(cfg_get(args, cfg, "n_bins", 16)),
-        continuous_value_scaling=str(
-            cfg_get(args, cfg, "continuous_value_scaling", "none")
-        ),
+        continuous_value_center=continuous_value_center,
+        continuous_value_scale=continuous_value_scale,
         extra_pool_reduce=str(
             cfg_get(args, cfg, "extra_pool_reduce", "mean")
         ),
@@ -251,9 +277,9 @@ class AllFutureSequenceEvalDataset:
     Eval-only sequence view for all-future checkpoints.
 
     All-future training uses the observed history without reusing the
-    next-step view that contains imputed <NO_EVENT> gap tokens. CHECKUP is
-    retained only when the experiment selects at least one extra-info type;
-    an explicitly empty selection is a disease-only history.
+    next-step view that contains imputed <NO_EVENT> gap tokens. Legacy label-1
+    assessment events are removed by the shared base dataset for every
+    extra-info selection.
     """
 
     def __init__(