budget-CoT per-item: paired ties with latent arms confirmed (p>=0.69)

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

PAPER.md

@@ -247,7 +247,10 @@ samples, so the comparison is exact), best-of-3 is statistically
 indistinguishable from the latent arms overall, *behind* them
 directionally on the hard bucket, and pays ≈3× visible tokens and serial
 decode for it. Budget-CoT-50 remains the strongest honest token baseline
-(53.8% overall, hard 40.0%). The implant's advantages at matched compute
+(53.8% overall, hard 40.0%; per-item rerun 53.8/38.2) — and the paired
+tests confirm it is a *tie* with the latent arms on both axes (p≥0.69 vs
+loop and distill), at the price of 50 visible tokens and their serial
+decode latency. The implant's advantages at matched compute
 without a verifier: zero visible tokens, zero decode overhead, and the
 hard-slice crown under distillation (46%). Where a task *does* come with a
 cheap verifier, oracle-style sampling is the better overall-accuracy