per-depth outcome scored (depth-stranded content, shared-tail rescue); kcurves updated with k=8

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-15 03:20:49 +02:00
parent 82cc1b85b8
commit b53538e82c
2 changed files with 13 additions and 0 deletions
@@ -217,3 +217,16 @@ the fidelity dial.
    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.
 --- Outcome, item 13a (scored 2026-07-15): prediction CONFIRMED — per-depth
 lands below/at the ceiling, never above. Detail is instructive: fidelity
 preserved throughout (easy 88.5/89.3/86.9 at k=2/4/8 — anchored B), but
 hard-bucket content is DEPTH-STRANDED: 17.9% at k=2 (adapters 3-4, which
 hold the hard-trained content, never execute), 35.7% at k=4, 42.9% at k=8
 — where depths 5-8 reuse adapter 4, i.e. the architecture reverts to
 shared-map iteration and the fixed-point mechanism collects the remaining
 gain. Time-variation adds a fragility (content unavailable except at its
 training depth) and no capability; map-sharing is load-bearing for the
 anytime-usable gain. Depth-4 adapter overfit visible in val (hard k4 CE
 0.188@99 -> 0.371@599) — LTV concentrates small-pool overfitting into
 single depths.