From 0008f2cd96c06bea98f43560867d93967c597711 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 19:45:46 -0500 Subject: docs: promote full dynamic ResNet result --- ROADMAP.md | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index ac3914c..67f0b31 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -538,6 +538,14 @@ hard-gated on a complete D3 pass, evaluates test exactly once per run, and can raise 6-to-7 only through its predeclared accuracy, paired noninferiority, alignment, leakage, query, and cost checks. +**Dynamic neutral projection D3: passed.** The sole frozen 200-epoch record +passes all 19 gates at source revision `d945c42`: `91.18%` validation versus +BP's `91.62%` and clean KP's `91.26%`, `0.999353` early alignment, `0.999663` +late feedback cosine, zero task-loss queries, and `1.3261x` BP MACs. Exactly +one validation and zero test evaluations occur. Per the frozen rule, the +strict reviewer score rises from 5 to 6 and the already committed D4 paired +five-seed test panel is now open. + 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