From 380a2a5e56c8edaecb2e0cc1a0bfc592e5b0f72c Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 16:56:13 -0500 Subject: docs: close one-sided stability branch --- STABLE_INNOVATION.md | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'STABLE_INNOVATION.md') diff --git a/STABLE_INNOVATION.md b/STABLE_INNOVATION.md index d499dc5..ecaf224 100644 --- a/STABLE_INNOVATION.md +++ b/STABLE_INNOVATION.md @@ -64,3 +64,19 @@ one-sided predictor branch without extending the grid. A pass only authorizes writing a separately frozen validation protocol with a new evaluation boundary; it supplies no accuracy claim and leaves the paper score at 5/10. +## Audited S0 outcome + +S0 fails with no eligible margin. `delta=0.001` and `0.003` first make +BatchNorm running variances nonfinite at steps 252 and 301; their maximum +forward/feedback weights reach `8.16e16` and `1.48e17`. `delta=0.01` and +`0.03` keep every tensor finite for 352 steps but have maximum minibatch losses +of `1.40e5` and `4.97e6`, maximum used/instruction RMS ratios of 538.4 and +6.59, and maximum weights of `8.83e6` and `1.19e8`. All four pass the +one-sided slope certificate, frozen-predictor, traffic-calibration, loader, and +zero-held-out-evaluation checks. + +The result shows that sign control alone is insufficient: a discrete momentum +mode also has a lower stability boundary, and time-varying deep covariances can +drive an initially negative effective mode beyond it. The grid is closed +without another margin. No validation protocol is opened and the reviewer +score remains 5/10. -- cgit v1.2.3