diff --git a/docs/research/kimodo-cpp-probe-2026-10.md b/docs/research/kimodo-cpp-probe-2026-10.md
index f4b749a..3bfb892 100644
--- a/docs/research/kimodo-cpp-probe-2026-10.md
+++ b/docs/research/kimodo-cpp-probe-2026-10.md
@@ -159,3 +159,5 @@ layer by layer and needs about 2 GiB resident, so it would fit Raven on CPU.
 - **Yggdrasil scratch** is `~/scratch/kimodo-cpp-probe` (39 GiB: weights,
   checkouts, outputs). The probe's containers are all removed. Delete the scratch
   directory once nobody needs to rerun the probe.
+
+**Correction, 2026-10-23.** The "MNTP missing" diagnosis in this document is wrong. The MNTP adapter is applied in both loads (the cut measured a q_proj difference of 0.0117 for repo ids and snapshot paths alike). What separates A from B is the Llama-3 chat header: Kimodo's `LLM2Vec.prepare_for_tokenization` wraps the text in it only when the model's `_name_or_path` is the repo id `meta-llama/Meta-Llama-3-8B-Instruct`, which a load from a snapshot path silently drops (`motion-pipeline:finding:cut-vili-cpu-body.s1.ab-premise-inverted`). B's weights with the bare header give cosine 0.9977 to A, and without it 1.0 to B; the header plus LLM2Vec's instruction marker, which keeps the header out of the pooling as Kimodo's encode path does, gives 1.0 to A (checked 2026-10-23). Vili now applies the header explicitly (`motion-pipeline:ruling:encoder-chat-header-on`). The measurements above stand as measured; read "MNTP" in the A/B account as "the chat header".
diff --git a/docs/research/vili-on-yggdrasil-cpu-2026-10.md b/docs/research/vili-on-yggdrasil-cpu-2026-10.md
index 5b351e1..47bab9b 100644
--- a/docs/research/vili-on-yggdrasil-cpu-2026-10.md
+++ b/docs/research/vili-on-yggdrasil-cpu-2026-10.md
@@ -180,3 +180,5 @@ finger joints only coarsely.
 - **Scratch:** `~/scratch/vili-ygg-cpu` holds the scripts, logs (`run*.log`, `out/*.log`),
   vectors, joints and BVH files, plus 18 GiB of weights. Delete it once nobody reruns this.
   All its containers are removed.
+
+**Correction, 2026-10-23.** The "MNTP missing" diagnosis in this document is wrong. The MNTP adapter is applied in both loads (the cut measured a q_proj difference of 0.0117 for repo ids and snapshot paths alike). What separates A from B is the Llama-3 chat header: Kimodo's `LLM2Vec.prepare_for_tokenization` wraps the text in it only when the model's `_name_or_path` is the repo id `meta-llama/Meta-Llama-3-8B-Instruct`, which a load from a snapshot path silently drops (`motion-pipeline:finding:cut-vili-cpu-body.s1.ab-premise-inverted`). B's weights with the bare header give cosine 0.9977 to A, and without it 1.0 to B; the header plus LLM2Vec's instruction marker, which keeps the header out of the pooling as Kimodo's encode path does, gives 1.0 to A (checked 2026-10-23). Vili now applies the header explicitly (`motion-pipeline:ruling:encoder-chat-header-on`). The measurements above stand as measured; read "MNTP" in the A/B account as "the chat header".