diff --git a/giant/data/loader.py b/giant/data/loader.py
index aa7955e..a7be53c 100644
--- a/giant/data/loader.py
+++ b/giant/data/loader.py
@@ -23,7 +23,7 @@ def _df_to_dict(df: pd.DataFrame) -> dict[str, np.ndarray]:
         "pre_pos": df[["pre_x", "pre_y", "pre_z"]].to_numpy(dtype=np.float32),
         "pre_energy": df["pre_energy"].to_numpy(dtype=np.float32),
         "pre_dir": df[["pre_dir_x", "pre_dir_y", "pre_dir_z"]].to_numpy(dtype=np.float32),
-        "material": df["material"].to_numpy(dtype=np.int32),
+        "material": df["material"].to_numpy(dtype=object),
         "layer_id": df["layer_id"].to_numpy(dtype=np.int32),
         "n_sec": df["child_track_ids"].apply(len).to_numpy(dtype=np.int32),
         "step_length": df["step_length"].to_numpy(dtype=np.float32),
@@ -64,7 +64,7 @@ def _cond_df_to_dict(df: pd.DataFrame) -> dict[str, np.ndarray]:
         "pre_pos": df[["pre_x", "pre_y", "pre_z"]].to_numpy(dtype=np.float32),
         "pre_energy": df["pre_energy"].to_numpy(dtype=np.float32),
         "pre_dir": df[["pre_dir_x", "pre_dir_y", "pre_dir_z"]].to_numpy(dtype=np.float32),
-        "material": df["material"].to_numpy(dtype=np.int32),
+        "material": df["material"].to_numpy(dtype=object),
         "layer_id": df["layer_id"].to_numpy(dtype=np.int32),
         "n_sec": df["child_track_ids"].apply(len).to_numpy(dtype=np.int32),
     }
@@ -79,9 +79,9 @@ def iter_cond_chunks(path: str | Path) -> Iterator[dict[str, np.ndarray]]:
 
 def build_index_maps(
     data: dict[str, np.ndarray],
-) -> tuple[dict[int, int], dict[int, int]]:
+) -> tuple[dict[int, int], dict[str, int]]:
     pdg_vals = sorted(int(v) for v in np.unique(data["pdg"]))
-    mat_vals = sorted(int(v) for v in np.unique(data["material"]))
+    mat_vals = sorted(str(v) for v in np.unique(data["material"]))
     return (
         {v: i for i, v in enumerate(pdg_vals)},
         {v: i for i, v in enumerate(mat_vals)},
@@ -90,14 +90,14 @@ def build_index_maps(
 
 def build_index_maps_from_files(
     files: list[Path],
-) -> tuple[dict[int, int], dict[int, int]]:
+) -> tuple[dict[int, int], dict[str, int]]:
     """Scan only pdg and material columns across all files (2-column read)."""
     pdg_vals: set[int] = set()
-    mat_vals: set[int] = set()
+    mat_vals: set[str] = set()
     for path in files:
         df = pd.read_parquet(path, columns=["pdg", "material"])
         pdg_vals.update(int(v) for v in df["pdg"].unique())
-        mat_vals.update(int(v) for v in df["material"].unique())
+        mat_vals.update(str(v) for v in df["material"].unique())
     return (
         {v: i for i, v in enumerate(sorted(pdg_vals))},
         {v: i for i, v in enumerate(sorted(mat_vals))},
diff --git a/giant/data/transforms.py b/giant/data/transforms.py
index bd74970..00fe25b 100644
--- a/giant/data/transforms.py
+++ b/giant/data/transforms.py
@@ -123,7 +123,7 @@ def inv_local_frame_rotation(pre_dir: np.ndarray, post_dir_local: np.ndarray) ->
 def build_cond_features(
     data: dict[str, np.ndarray],
     pdg_map: dict[int, int],
-    mat_map: dict[int, int],
+    mat_map: dict[str, int],
     cond_normalizer: "Normalizer | None" = None,
 ) -> tuple[np.ndarray, np.ndarray]:
     """Build conditioning arrays only — no target, no post-step variables."""
@@ -136,7 +136,7 @@ def build_cond_features(
     ]).astype(np.float32)
 
     pdg_idx = np.array([pdg_map[int(p)] for p in data["pdg"]], dtype=np.int64)
-    mat_idx = np.array([mat_map[int(m)] for m in data["material"]], dtype=np.int64)
+    mat_idx = np.array([mat_map[str(m)] for m in data["material"]], dtype=np.int64)
     cond_cat = np.column_stack([pdg_idx, mat_idx])
 
     if cond_normalizer is not None:
@@ -148,7 +148,7 @@ def build_cond_features(
 def build_features(
     data: dict[str, np.ndarray],
     pdg_map: dict[int, int],
-    mat_map: dict[int, int],
+    mat_map: dict[str, int],
     cond_normalizer: Normalizer | None = None,
     target_normalizer: Normalizer | None = None,
     fit: bool = False,
@@ -175,7 +175,7 @@ def build_features(
     ]).astype(np.float32)  # (N, 9)
 
     pdg_idx = np.array([pdg_map[int(p)] for p in data["pdg"]], dtype=np.int64)
-    mat_idx = np.array([mat_map[int(m)] for m in data["material"]], dtype=np.int64)
+    mat_idx = np.array([mat_map[str(m)] for m in data["material"]], dtype=np.int64)
     cond_cat = np.column_stack([pdg_idx, mat_idx])  # (N, 2)
 
     if fit: