related_work: log 12b_adaptive outcome as confirmation of the anchoring account

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Nils
2026-07-14 12:57:08 +02:00
co-authored by Claude Fable 5
parent e152a91c05
commit f2cbce5a03
+8
View File
@@ -158,3 +158,11 @@ directly to Lys's distribution-shift account and predicts the queued
auto-alignment (adaptive η, training-free) is the natural fallback if no auto-alignment (adaptive η, training-free) is the natural fallback if no
fixed α transfers. Worth a paragraph in Paper A (design justification + fixed α transfers. Worth a paragraph in Paper A (design justification +
12B analysis) and Paper B (stability mechanism). 12B analysis) and Paper B (stability mechanism).
**Outcome (2026-07-14, prediction confirmed):** the `12b_adaptive` MBPP
arm (adaptive anchoring, 2×/8× H100 fleet) recovers the substrate —
k=0/2/4 = 72.4/70.8/69.4 overall vs 72.6/54.6/43.0 under fixed α=0.3,
with hard monotone 11.4→18.2→27.3. The tolerable-loop-share account
called this shape in advance: stability restored by weakening the loop
share, hard gains preserved and k-monotone, residual easy erosion
(98.9→92.2) to be handled by the gate.