C+E: stage 2 builder (mask, 48k, CLAS cap, family split, hook), private HF dataset, bf16 mixed training script with memory test, memory table, ratio proposal

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

train/hooks_example.py

@@ -0,0 +1,28 @@
+"""Hooks for train/build_stage2.py (--hook hooks_example:own_test_weight). A hook gets one sample (a dict) and returns
+None / False (drop), a number (repeat weight), or {"keep": bool, "weight": float, "extra": {...}}."""
+import json
+import os
+
+ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+def identity(row):
+    return 1.0
+
+
+def own_test_weight(row):
+    """Item D (own-test mutation score, metadata only for now): reads runs/traj/<run>/own_test_mutation.json when it exists,
+    stores it as extra data and does NOT drop or reweight (Kral + Opus 2026-10-06: do not change the acceptance yet)."""
+    run = row["id"].split("_r")[-1]
+    for d in os.listdir(os.path.join(ROOT, "runs", "traj")):
+        if d.startswith(run + "_"):
+            p = os.path.join(ROOT, "runs", "traj", d, "own_test_mutation.json")
+            if os.path.exists(p):
+                m = json.load(open(p))
+                return {"keep": True, "weight": 1.0, "extra": {"own_test_mutation": m.get("score"), "own_test_mutants": m.get("mutants")}}
+    return {"keep": True, "weight": 1.0}
+
+
+def repair_up(row):
+    """Example of a weight: a trajectory with a repair counts twice."""
+    return 2.0 if row.get("repair") else 1.0