From f55872beaee658ff76ac15fd421b73017820c320 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Sat, 1 Aug 2026 13:52:45 -0500 Subject: experiment: open complete A6000 matrix --- README.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 5d9b4ff..666ecd0 100644 --- a/README.md +++ b/README.md @@ -153,8 +153,12 @@ nonfinite at VGG16. Dual Propagation reaches `92.38%` on VGG16 but takes `5.97` hours versus SDIL's `1.24`; clean KP slightly dominates SDIL there at `90.86%` in `1.08` hours. Thus the first family supports scaling and a cost advantage over iterative strong baselines, but not global Pareto -dominance. ResNet and Transformer crossover cells remain gated on their -complete validation-only selectors. +dominance. The ResNet and Transformer crossover cells were gated on their +complete validation-only selectors; both gates have now passed and are +tracked. ResNet is complete at 19/19 candidates and Transformer at 27/27, +with all nine selected rates frozen before the full-size endpoints. The +GTX-1080 ResNet R2 panel is active, and the independent A6000 81-cell run +packet is open at tag `a6000-x1-v1`. ## Publication-facing artifacts -- cgit v1.2.3