From 7eb40a516849cbc3e93540d4fdf40366f6a8df9e Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 03:59:52 -0500 Subject: results: close context-vectorizer C2 recovery --- ROADMAP.md | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index 7079f2d..256c8fe 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -140,6 +140,14 @@ be positive; its d4 lesion must lose at least 2 points on average and harm at le Failure closes this recovery. Passing freezes a single test confirmation over task seeds 0--5, student seeds 0--4, all four methods, and d1/d4, retrained on the unchanged 8,000-example subsets. +**Context-vectorizer recovery status: failed validation on 2026-07-22; test remains unevaluated.** +Context-SDIL recovered `53.0%` of BP's depth gain (`+15.143` versus `+28.553` points), below 70%, +and its d4 endpoint trailed FA by `1.643` points. One d4 trajectory had nonfinite final loss. +Positive depth gains and positive lesion effects each occurred in exactly 10/15 runs, so those +secondary conditions passed at the boundary. Context conditioning improves substantially over +linear SDIL's 21.0% recovery but does not make causal-feedback learning reliable enough. The +predeclared mechanism-recovery branch is closed and no C2 test panel will run. + ### 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