From 82d49f4b8b741669ab39100f4719719801064f20 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 15:08:36 -0500 Subject: results: record residual mirror full failure --- README.md | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'README.md') diff --git a/README.md b/README.md index 8fd3418..eaebb71 100644 --- a/README.md +++ b/README.md @@ -54,6 +54,11 @@ and scaling behavior. See `NOVELTY.md` for the exact prior-art boundary. synthetic variance audit, but V3-1 again failed: early alignment was `0.00714` versus matched V2's `0.00721`, although all-layer alignment rose to `0.06258`. V3 full training therefore remained closed. +- Residual response mirroring passes its short gate but fails its sole full + run at 10% with NaN validation loss. Its endpoint Q/W cosine nevertheless + reaches 0.999998, exposing final alignment as an inadequate certificate for + an intermittent tracker. The separate reciprocal KP short gate reaches + 82.66% and remains the active strong substrate. - Native author-code fidelity is complete. BurstCCN reaches `80.10%` at its validation-selected epoch versus published `82.97 +/- 0.21%`; Dual Prop reaches `92.46%` versus published `92.41 +/- 0.07%`. Their audited walls are -- cgit v1.2.3