fidelity factorial arms (randk / noises0 / hidden-capacity) + pre-registration item 15

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-15 02:47:14 +02:00
parent d39e02f4b9
commit 0e6d6adcb9
4 changed files with 60 additions and 9 deletions
@@ -196,3 +196,24 @@ independent dials (fig_phase.png); the Parcae constraint delivers exactly
 what it promises (robust training, convergence, certified tail gradients)
 and exactly nothing more. Item 14 (tied-alpha) is the causal isolation of
 the fidelity dial.
+
+15. **Fidelity factorial + capacity control + seed (pre-registered
+    2026-07-15 ~03:15, before any of these arms ran; overnight batch).**
+    The fidelity loss of both rec arms (easy 88.5 -> ~71%) confounds three
+    deltas from the winning merge: (i) learned B, (ii) random-depth
+    training instead of the difficulty->depth curriculum, (iii) noise s0.
+    Item 14 (tied-alpha) tests (i) with anchoring. New single-variable
+    cells, everything else = standard merge recipe (fixed B, band(e) s0,
+    curriculum, e400, eval ks 0,2,4,8 on 250 items):
+      a. merge+randk  — only (ii) changed (log-uniform k in [1,16], bptt 4).
+      b. merge+noises0 — only (iii) changed.
+      c. merge h=2048 — capacity control for the per-depth arm (6.4M
+         shared vs 6.4M depth-indexed): if per-depth beats the ceiling
+         but h2048 does not, time-variation (not capacity) is credited;
+         if both do, it was capacity all along.
+      d. parcae seed 1 — robustness of the fidelity refutation.
+    Predictions: (a) and (b) each cost a few points of easy at most
+    (anchored fixed point dominates); neither reproduces the ~17-point
+    drop — the culprit is the learned/free B (with item 14 as the
+    positive control). h2048 stays at the ceiling (hard <=46%), fidelity
+    intact. parcae s1 reproduces easy ~71% within seed noise.