summaryrefslogtreecommitdiff
path: root/ROADMAP.md
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 19:55:38 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-07-22 19:55:38 -0500
commit5cfce81898d1a8ca08beac2c68f73dfb9f6447d5 (patch)
tree31ee85d010c7a992f6529038716d0217a4240b1e /ROADMAP.md
parent661496c172a53d09c59951c642f1a468abb7f07e (diff)
docs: register oral B structural recovery
Diffstat (limited to 'ROADMAP.md')
-rw-r--r--ROADMAP.md11
1 files changed, 11 insertions, 0 deletions
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