diff --git a/TODO.impl/11-static-int8-framing.md b/TODO.impl/11-static-int8-framing.md
index a76ef84..c1dd9bc 100644
--- a/TODO.impl/11-static-int8-framing.md
+++ b/TODO.impl/11-static-int8-framing.md
@@ -37,10 +37,31 @@ If A and B clear: re-export all quantized artifacts through the static
 path (modal_export gains the calibration stage), index-v6, golden rows
 regenerate, framing claim added to the contract.
 
+## Verdict (2026-09-12, final): framing gate FAILED for the node fix — the instability is the node build itself
+
+The test run at every endpoint (RESULTS.md, PR #214):
+
+- Python ORT: 480/480 framing-stable at fp32, dynamic int8, AND
+  static int8
+- onnxruntime-node: 89-101/485 UNSTABLE at every precision INCLUDING
+  fp32 — batch-shape-dependent kernel numerics before quantization
+  enters; static scales cannot repair what is not a scale computation
+- static int8 byproduct: quality-clean on sample (0/480 drift vs
+  fp32) and ~8% faster than dynamic on CPU — stays a candidate for
+  the export path on its own merits, gated by full-set DER, NOT by
+  framing
+
+Re-scoped conclusion: framing stability is a property of the runtime
+distribution. Shipped TS paths are single-framing by construction, so
+published byte parity is unaffected; framing is the parity variable
+of mixed-shape serving (why the speculative tier degraded and was
+pulled — TODO.impl/01).
+
 ## Status
 
 - [x] Pre-registered (this file)
 - [x] fp32 artifact fetched, sha-verified against index-v5
 - [x] Calibration corpus collected (365 feeds, both framings)
-- [ ] quantize_static result measured (A/B/C)
-- [ ] Verdict recorded in RESULTS.md; ledger cross-links updated
+- [x] quantize_static measured (A/B/C) across BOTH runtime builds
+- [x] Verdict recorded in RESULTS.md + Paper C 5.1; framing-fix
+      closed negative; static-int8 speed/quality kept open
diff --git a/TODO.impl/README.md b/TODO.impl/README.md
index cdf4493..60da5c5 100644
--- a/TODO.impl/README.md
+++ b/TODO.impl/README.md
@@ -24,7 +24,7 @@ Priorities:
 | 08 | golden-closeout.md | golden test PR, paper-c wording, release README note | P0 | closed 2026-09-12 (PR #211 merged) |
 | 09 | doc-corrections.md | Engram mechanism fix, mHC single-pass note | P2 | landed in PR #95 |
 | 10 | engram-lexical-memory.md | hashed n-gram memory module | P3 | gated behind 04 |
-| 11 | static-int8-framing.md | static activation scales: fix framing at the source | P0 | pre-registered; experiment running |
+| 11 | static-int8-framing.md | static scales as the framing fix | P0 | closed: node-kernel finding; static stays open on speed |
 
 Standing rules that apply to every item: full-set measurement or no
 claim; quantized parity is quality-level, not byte-level; LLM teachers