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 --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 60fd2d2..6c69dba 100644 --- a/README.md +++ b/README.md @@ -71,9 +71,11 @@ and scaling behavior. See `NOVELTY.md` for the exact prior-art boundary. 352-step trajectory is finite, and D2 reaches `83.58%` after 20 epochs versus clean KP's `82.66%` and the failed mixed-traffic controls' `10%`, at `1.3261x` BP MACs and zero task-loss queries. This is still one short validation seed; - the predeclared 200-epoch D3 run is in progress and test remains untouched. - A paired five-seed clean-KP/dynamic D4 protocol is already frozen but remains - hard-gated on D3; no D4 test endpoint has been accessed. + the predeclared 200-epoch D3 run subsequently passes all 19 gates at `91.18%` + versus BP's `91.62%` and clean KP's `91.26%`, with `0.9994` early alignment, + zero task-loss queries, and `1.3261x` BP MACs. This raises the strict score + to 6/10. A paired five-seed clean-KP/dynamic D4 protocol is frozen and now + open; no D4 test endpoint had been accessed at the D3 audit. - 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 -- cgit v1.2.3