Add data-integrity guards against silent NaN/Inf propagation and races

- log_transform / _validate_unit_pre_dir now raise on non-finite input
  instead of letting a NaN row silently poison the persisted normalizer
  cache (norm < 1e-6 was always False for NaN, so the existing guard
  never caught it).
- encode_secondaries warns when a row's secondary energies cumulatively
  exceed e_sec, instead of silently saturating the overflowing slot's
  stick-breaking logit via the _EPS floor.
- EVENT_ID_FILE_STRIDE overflow now raises instead of silently colliding
  two files' event ids together (reintroducing train/val leakage).
- make_event_split(val_fraction=0.0) now actually holds out nothing,
  instead of always forcing at least 1 validation event.
- setup_cache.save() is now serialized with a flock, since two
  concurrent writers (a real scenario on this repo's shared
  portal/condor machines) could otherwise race and silently drop one
  writer's freshly-computed cache section.
- Documented (no behavior change) the pre_dir ≈ -ẑ antipodal rotation
  singularity in _rodrigues_axis, which is real but inherent to any
  single-valued local-frame convention.

Each fix has a regression test.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

giant/data/loader.py

@@ -27,6 +27,26 @@ def event_id_offset(file_index: int) -> int:
     return file_index * EVENT_ID_FILE_STRIDE
 
 
+def _offset_event_id(raw_ids: np.ndarray, offset: int) -> np.ndarray:
+    """Add this file's `event_id_offset`, after checking the raw ids fit in one stride block.
+
+    Without this check, a file whose own raw event_id numbering reaches
+    `EVENT_ID_FILE_STRIDE` (an unusually large job, or non-contiguous
+    numbering) would silently collide into the next file's offset block,
+    merging unrelated events across files — reintroducing exactly the
+    train/val event leakage this offset scheme exists to prevent.
+    """
+    raw_ids = np.asarray(raw_ids, dtype=np.int64)
+    if raw_ids.size and int(raw_ids.max()) >= EVENT_ID_FILE_STRIDE:
+        raise ValueError(
+            f"event_id {int(raw_ids.max())} >= EVENT_ID_FILE_STRIDE "
+            f"({EVENT_ID_FILE_STRIDE}) — this file has a larger event_id "
+            "than the per-file offset scheme can support without colliding "
+            "with the next file's id block."
+        )
+    return raw_ids + offset
+
+
 def _read_manifest(path: Path) -> list[Path]:
     files = []
     for line in path.read_text().splitlines():
@@ -98,7 +118,7 @@ def _df_to_dict(df: pd.DataFrame, offset: int = 0) -> dict[str, np.ndarray]:
     has_sec_lists = "sec_E_list" in df.columns
 
     d: dict[str, np.ndarray] = {
-        "event_id": df["event_id"].to_numpy().astype(np.int64) + offset,
+        "event_id": _offset_event_id(df["event_id"].to_numpy(), offset),
         "pdg": df["pdg"].to_numpy(dtype=np.int32),
         "pre_pos": df[["pre_x", "pre_y", "pre_z"]].to_numpy(dtype=np.float32),
         "pre_E": df["pre_E"].to_numpy(dtype=np.float32),
@@ -142,7 +162,7 @@ def load_steps(path: str | Path, offset: int = 0) -> dict[str, np.ndarray]:
 def load_event_ids(path: str | Path, offset: int = 0) -> np.ndarray:
     """Read only the event_id column — cheap scan for split assignment."""
     ids = pd.read_parquet(path, columns=["event_id"])["event_id"].to_numpy()
-    return ids.astype(np.int64) + offset
+    return _offset_event_id(ids, offset)
 
 
 def iter_file_chunks(
@@ -173,7 +193,7 @@ _COND_COLS = [
 
 def _cond_df_to_dict(df: pd.DataFrame, offset: int = 0) -> dict[str, np.ndarray]:
     return {
-        "event_id": df["event_id"].to_numpy().astype(np.int64) + offset,
+        "event_id": _offset_event_id(df["event_id"].to_numpy(), offset),
         "pdg": df["pdg"].to_numpy(dtype=np.int32),
         "pre_pos": df[["pre_x", "pre_y", "pre_z"]].to_numpy(dtype=np.float32),
         "pre_E": df["pre_E"].to_numpy(dtype=np.float32),