From e189c8027c0ebb70d68eac630b6e50a23bb0ee0b Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 02:19:35 -0500 Subject: results: freeze single-direction calibration --- ROADMAP.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index 886e73c..e7a7bd6 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -65,7 +65,9 @@ must hold in a hardware-independent cost coordinate as well as GTX-1080 wall tim The validation screen is frozen to CIFAR-10 d20/w64, five epochs, seed 0, and compares the current `K=16/every=4` reference with `K/every` pairs `1/4`, `2/8`, `4/16`, `1/8`, `1/16`, and `2/32`, plus DFA. Selection uses final validation accuracy and logical batch loss queries; the test split is not -evaluated. The chosen low-query protocol then receives a multi-seed frozen confirmation. +evaluated. `K=1/every=4` was selected: it used 16x fewer batch loss queries and retained 177.5% of +the reference gain over DFA. This selection is now frozen; the protocol receives a five-seed test +confirmation with no further tuning before C3 can be declared passed. ### C4. The comparison set contains the closest alternatives -- cgit v1.2.3