diff --git a/DECISIONS.md b/DECISIONS.md
index dfdf5c9..4171b02 100644
--- a/DECISIONS.md
+++ b/DECISIONS.md
@@ -1554,8 +1554,10 @@ against the speaker's answers: **`gemma4-31b` 97% and `gemma4-26b` 92%** passed
 **Unknowns, stated.** The adjudicator evidence is 30 items from one speaker and one domain, chosen by
 Opus as decidable; the other ~350 disagreements (fillers, compounds, small words) have no ground
 truth. Whether a *merged* transcript is better than the better single engine has not been measured.
-Reconcile time per hour is estimated, not measured. `gemma4-31b`'s slowness is unexplained (Low Power
-Mode on iguana is the unproven suspect).
+Reconcile time per hour is estimated, not measured. `gemma4-31b`'s slowness was Low Power Mode on
+iguana: with it off the 31B decodes at 22.3 tok/s, not 7.9 (2026-10-02, same-machine before/after on
+a different synthetic prompt; see the research note). The reconciler default `gemma4-26b` was chosen
+on the slow numbers and is reopened: 31B scored 97% against 92%.
 
 **Decision.**