From dafbd8fd2578cbd76d358422dfa3bda9679c3d43 Mon Sep 17 00:00:00 2001 From: Nils Date: Wed, 15 Jul 2026 23:42:31 +0200 Subject: [PATCH] item 18 scored (uniform-depth collapse, CE depth-flatness mechanism); item 19 E1b pre-registered Co-Authored-By: Claude Fable 5 --- results-loop/PROTOCOL_UNIFIED.md | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/results-loop/PROTOCOL_UNIFIED.md b/results-loop/PROTOCOL_UNIFIED.md index 95a069c..46d87e1 100644 --- a/results-loop/PROTOCOL_UNIFIED.md +++ b/results-loop/PROTOCOL_UNIFIED.md @@ -383,3 +383,28 @@ is fully supported. arm (lambda=1e-3, seed 1) is added for immediate seed replication of the expected-winner penalty. Spark's queued gate jobs will be dropped to avoid duplication. Everything else per registration. + +--- Outcome, item 18 (scored 2026-07-16 ~00:40): predictions (b), (c) +REFUTED, (a) marginal miss, (d) trivial pass. All arms converge to +UNIFORM depth (lambda 0/1e-3/1e-2 -> E[k] 4/2-or-4/1; the two 1e-3 seeds +picked different plateaus — degenerate penalty landscape), r = 0.000 +everywhere. Mechanism identified and consistent with prior findings: +teacher-forced CE is depth-flat (stationarity), so CE provides no +per-item depth gradient; the penalty alone cannot teach selectivity. +The state DOES carry the signal (E0 probe: train acc 1.0) — the failure +is the training signal, not the representation. E1-as-designed is dead; +kill criterion NOT fully triggered (E2 untested, and the mechanism +points at a repair). + +19. **E1b: label-supervised halting head (pre-registered 2026-07-16 + ~00:45, before running).** Freeze the curriculum merge (adapter_code + s0); train ONLY the halting head (BCE): target halt=0 at iterations + below the label's depth (easy->1, hard->4, per STaR label), halt=1 at + or above it. 300 steps, mixed batches, head-only params. Eval: gated + eval as item 18, n=250. Predictions: (a) r(k*, hard) > 0.5 (the head + is a trained difficulty classifier now); (b) easy >= 95% at k*=1 + (near-E0's 97.5); (c) hard >= 35.7% (>= best uniform arm, via better + recall than E0's frozen probe: more than 18/28 hard items routed + deep); (d) overall >= 52.0 at E[k] <= 2.2. If (c) fails while (a,b) + hold, halting-head recall saturates at probe level and gate quality, + not gate training, is the binding constraint.