From c27e0824a41e6c54dd9079f17c20c306c5f2e9c9 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 13:28:23 -0500 Subject: results: close hierarchical task-scalar calibration gate --- THEORY.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'THEORY.md') diff --git a/THEORY.md b/THEORY.md index 1c4f5d0..14c585f 100644 --- a/THEORY.md +++ b/THEORY.md @@ -247,7 +247,11 @@ The executable audit checks the complete BatchNorm-coupled antithetic JVP to predicted Q/R moments equal the exact causal delta-rule targets to `2.3e-16` relative error. Actual training never performs that copy. These identities establish mechanics only; a frozen-forward causal-capture gate must pass before -any task-scale endpoint is opened. +any task-scale endpoint is opened. That empirical V4 gate subsequently failed: +the stable rate left early alignment near zero, while larger rates caused a +58.5x feedback norm ratio or nonfinite state. The unbiased identity therefore +does not imply usable finite-budget signal in the 267,904-dimensional joint +parameter space. ## 2. What is sufficient for a descent step -- cgit v1.2.3