From 6fa80efc1c53905b6328c5b44df3db4e4da34dfe Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 12:59:25 -0500 Subject: results: close Oral-A v3 causal-capture gate --- ROADMAP.md | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index 2ad919f..4f6c315 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -373,6 +373,16 @@ reaches `0.00721`. Naive local-average/channel-context fields fall slightly to sample efficiency and feedback context; simply lowering `eta_A`, adding the tested fields, or reopening V2-2 is not justified. +**Vectorizer-space V3 status: causal-capture gate failed.** Directly estimating +the A/G matrix target passed exact mechanics and reduced matched synthetic +one-query MSE to `0.03381x`, but its selected real early alignment was +`0.007139` versus the matched V2 reference's `0.007209`. All-layer alignment +rose from `0.052740` to `0.062579`; three early/oracle checks failed and only +the all-layer check passed. V3 full training was not launched, and test access +remains sealed. This closes learning-rate tuning of the same output-error-only +channel-gated family; a further branch must make a substantive feedback-context +or cross-layer-noise change. + Prepare convolutional local-update primitives and ResNet-20/32/56 protocols early. Queue frozen runs opportunistically on authorized idle GPUs. Because BurstCCN already reports CIFAR-10 and ImageNet scaling, dataset scale alone is not novel. The oral-level target is a memorable joint -- cgit v1.2.3