train-clean bounded tanh CTT 2026-07-03 workspace/reports/draft_audit_ctt.md

workspace/reports/draft_audit_ctt.md

@@ -530,7 +530,7 @@ Current missing:
   This remains a prerequisite blocker for interpreting clipped rollout results
   as deployment evidence.
 - Real robot near-miss recovery audit.
-- A dominance model that materially closes the selected-success selector gap. The current
+- A dominance model that materially reduces the selected-success selector gap. The current
   learned ridge row only marginally beats the base, and the full train-only
   utility-energy checkpoints do not beat base. Coarse context metadata also
   does not beat the best learned ridge row.