From c27e0824a41e6c54dd9079f17c20c306c5f2e9c9 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 13:28:23 -0500 Subject: results: close hierarchical task-scalar calibration gate --- ROADMAP.md | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index d6bfa83..c84293d 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -404,6 +404,15 @@ subspace in one antithetic pair and subtracts locally computed prediction moments. Its causal JVP and exact symmetric-limit delta rule pass, but it has no task claim until a frozen-forward alignment gate is preregistered and audited. +**Hierarchical task-scalar V4 status: causal-capture gate failed.** Stable +etaA 0.1 changes early/all-layer alignment from `-0.000263/0.011279` to only +`-0.000180/0.017336`. EtaA 1 reaches early `0.000348` but produces a 58.48x +feedback norm ratio; etaA 10 becomes nonfinite. All substantive gates fail, +so no accuracy run opens. This closes simultaneous global scalar calibration +of the full 267,904-parameter feedback path at 400 events. The next branch must +use richer local child-response information and include learned FA/weight +mirroring as an explicit inherited baseline before adding innovation. + 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