refactor RnnModel: multi-unit delay training and unified vc interface

- Add batch_delay() to shift visible input per unit index
- Unify forward_step() to work with combined vc matrix
- Fix split() to always slice on axis=1
- Add index param to Entity for readable naming
- Rename test_xor.py to xor.py, replace Mat with np.array

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/stack/rnn_helper.py

@@ -37,7 +37,7 @@ def concat(v: np.ndarray, c: np.ndarray, axis=0) -> np.ndarray:
 
 def split(vc: np.ndarray, h_size: int, axis=0) -> tuple[np.ndarray, np.ndarray]:
 	v_len = vc.shape[axis]-h_size
-	return vc[0:v_len], vc[v_len:]
+	return vc[:, 0:v_len], vc[:, v_len:]
 
 def shift_right(m: np.ndarray, amount: int = 1) -> np.ndarray:
 	return np.hstack([np.zeros((m.shape[0], amount)), m[:, :-amount]])