item 22 scored: ladder breaks at d=1 (57.4->31.6), plateaus ~19 at d=2/3 — 2x cold floor (d=3 vs base McNemar p=0.0025); latent loop trades easy reliability for hard/drop reach

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-16 15:29:42 +02:00
parent 4e744e7d94
commit 7d60f37cf1
7 changed files with 9355 additions and 0 deletions
@@ -555,3 +555,31 @@ if it survives pairing, is the strongest argument for continuing.
    this recurrence budget to absorb computation. Job:
    scripts/jobs/zzz_m_gsm_rungb.sh (single submit, ~3x(40min train +
    eval) on the Spark).
 --- Outcome, item 22 (scored 2026-07-16 ~15:30). k=0 sanity row
 reproduced base exactly in all three rung evals (10.9/93.1/0.8/0.0).
 Ladder (best cell overall, n=256): rung A 57.4 -> d=1 31.6 (2:12) ->
 d=2 18.4 (2:26) -> d=3 19.1 (2:32). (a) FAILED, decisively: the break
 rung is d=1 — deleting ONE compute-matched step costs 25.8 points
 (easy 83->62, hard 64->36, drop 45->17); the recurrence cannot absorb
 even one step's computation at this budget/recipe. (b) monotone
 through d=2, then a plateau (d=2 18.4 -> d=3 19.1, within n=256
 noise): the decay bottoms out ABOVE the floor rather than collapsing
 to it. (c) CONFIRMED: d=3 (pause-only for ~87% of items) = 19.1 vs
 base 10.9 — paired McNemar 33-12 discordants, p=0.0025 — and vs cold
 answer-only carry 9.4: the curriculum-reached latent loop DOUBLES the
 cold-trained equivalent. Composition of the d=3 edge: easy is
 DAMAGED (58.6 vs 93.1 base) while hard (18.9 vs 0.8) and drop (8.0
 vs 0.0) are lifted — the latent loop trades easy-bucket reliability
 for reach, echoing item 21's drop-bucket signature in latent form.
 Deliverable: measured capacity of this recurrence budget = a plateau
 at ~19% overall / ~2x the cold floor; the visible scratchpad carried
 the other ~38 points. Val-loss note: hard val rose with d (0.36 ->
 0.56 -> 0.59) while easy fell (d=3 0.13, mostly answer-line targets)
 — CE fit does not track eval accuracy at deep rungs. Interpretation
 for the plan: rung C' (no pauses) is moot as a capability claim — C
 already plateaued at 19; the E2-L line's value is now the 2x-over-cold
 curriculum effect + the reach trade, not scratchpad-free parity. Next
 knobs if the line continues: longer per-rung retraining, finer
 deletion schedule (fractional rungs), or E2-N noise-hardening stacked
 on the rungs.