From 2f7a093deec83dc6f972d4aaff3f3d55e8327925 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 05:01:49 -0500 Subject: experiments: freeze feedback-first C2 screen --- ROADMAP.md | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index 60591c9..677243e 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -185,6 +185,15 @@ context-gated simultaneous K1/e4 joint phase. The prefix uses layerwise K4 targe `eta_A=0.01`; its length grid and selection rule must be committed before any run. This tests the specific coupled-basin diagnosis without increasing vectorizer capacity or changing the task. +The frozen prefix-length grid is `{0, 100, 400}` A-only minibatches, crossed with d1/d4 and model +seeds 0--2. Warmup consumes an isolated RNG stream and restores the loader generator, so every +candidate's subsequent joint phase receives the same minibatch order and perturbation randomness. +A prefix is development-eligible only if all six final losses are finite, mean d4 validation is at +least 90%, at least 2/3 paired depth gains are positive, and the d4 lesion loses at least 2 points +on average with at least 2/3 positive lesions. Among eligible prefixes, select the highest mean d4 +endpoint, choosing the shortest prefix within one point. If none is eligible, the feedback-first +branch closes without using task seeds 6--8. + ### C3. Causal calibration is genuinely amortized **Status: passed on 2026-07-22.** The frozen five-seed confirmation retained 112.9% of the K16/e4 -- cgit v1.2.3