EXP - DOC - Record refuted window-kink prediction; mark morning questions superseded

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LzbLFQKyuRE5DYZmLokKmk

Author: logan-nc

handoff/issue376/RESULTS.md

@@ -1257,6 +1257,11 @@ full-grid DIII-D kinetic answer is therefore converged in kernel tolerance (2.7e
 equilibrium grid (1.6e-4); the certified grid's 14–17% deviation is unambiguously certification
 error.
 
+Refuted along the way (recorded per the pre-registration discipline): the reviewer-model
+prediction that the residual certified-run steps sit on rational-window kinks (J ~ rtol/Δψ³ in the
+kept-dense windows). The ψ-distribution and rtol-invariance rule it out — the steps are near-axis
+real structure, in the rational-free span.
+
 **Why the certificate is blind to it (the design flaw, now precisely identified)**: the residual
 test is `max-element residual ≤ tol · max|T|` with max|T| the family's GLOBAL maximum. For G that
 scale is 6.7e6 (edge/rational-dominated), while the near-axis increment is ~1e3 — only 1.6e-4 of

handoff/issue376/morning_questions.md

@@ -1,3 +1,5 @@
+> **Superseded by RESULTS.md §28** — the user answered these on 2026-08-19; the decisions and their consequences (PR split, seed rework, DIII-D survival-test verdict) are recorded there.
+
 # Questions for the morning
 
 1. **PR #408 review-package sharing worked?** (You flipped both; reviewers should confirm access.)