From 5cfce81898d1a8ca08beac2c68f73dfb9f6447d5 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 19:55:38 -0500 Subject: docs: register oral B structural recovery --- ROADMAP.md | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index 67f0b31..a8de7d2 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -32,6 +32,17 @@ preregistered stop rule, environment seeds 10--15 and all confirmation model see untouched. This falsifies the current model's claimed emergence of the Harnett derivative signature; it cannot be repaired by reporting only its successful learning or decoder results. +**Oral-B recovery R0 status: mechanics passed, task gate sealed.** Reinspection +of Fig. 5 and Extended Data Fig. 13 identifies a structural target conflict: +the failed vectorizer regressed `e_t s_i`, so its role contrast encoded current +error magnitude rather than the sign of error change. `ORAL_B_RECOVERY.md` +factorizes a new candidate into a perturbation-learned causal role and the +within-episode performance innovation `|e_(t-1)|-|e_t|`. Deterministic checks +recover the role at cosine `0.9963` and change the controlled sign index from +negative to `+0.100`. This is mechanics only; no BCI endpoint, development +seed, or confirmation seed is touched. The learning gate remains sealed until +D4 closes and a separate R1 protocol is committed. + ## Frozen accept claims and gates ### C1. Innovation is necessary under naturally mixed apical traffic -- cgit v1.2.3