From 524c0704029c4b831d9f19413995e8cff1508b8b Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 16:31:15 -0500 Subject: docs: close mixed-traffic path after short failure --- README.md | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index f855473..5af05cf 100644 --- a/README.md +++ b/README.md @@ -59,7 +59,9 @@ and scaling behavior. See `NOVELTY.md` for the exact prior-art boundary. reaches 0.999998, exposing final alignment as an inadequate certificate for an intermittent tracker. The separate reciprocal KP short gate reaches 82.66%, and its frozen full gate reaches 91.26% versus matched BP's 91.62% - with 0.9997 late feedback cosine. It is the active strong substrate. + with 0.9997 late feedback cosine. The subsequent frozen mixed-traffic screen + nevertheless makes raw, norm-matched raw, and innovation all nonfinite in + epoch 1, so no full or confirmation panel opens. - 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 @@ -162,7 +164,10 @@ The stronger reciprocal Kolen--Pollack substrate is audited separately in feedback loss queries. Before that full endpoint, `MIXED_TRAFFIC.md` froze the actual Harnett-specific test: raw, norm-matched raw, and innovation under identical four-times-RMS soma-predictable apical traffic and predictor cost. -Mechanics are green and MT-1 task access is now open. +Mechanics pass, but the complete MT-1 panel fails: all three signals become +nonfinite in epoch 1 and end at 10.00% validation accuracy. MT-2 and MT-3 +remain untouched, closing this standard-ResNet recovery without a weaker +traffic intervention. The subsequent V3 mechanism estimates the required A/G matrix statistics directly by perturbing the vectorizer parameter subspace. It remains -- cgit v1.2.3