From 1a89eb386830171f13b8a9a88916633db80d8922 Mon Sep 17 00:00:00 2001 From: Mathias Date: Fri, 2 Oct 2026 08:01:31 +0200 Subject: [PATCH] docs(adr-034): record the first blind check; bar ambiguity and the unanswered second condition Co-Authored-By: Claude Sonnet 5.5 --- DECISIONS.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/DECISIONS.md b/DECISIONS.md index 4171b02..420e550 100644 --- a/DECISIONS.md +++ b/DECISIONS.md @@ -1641,6 +1641,13 @@ recording. ~30 disputes where the reconciled text differs from pianissimo alone. Keep the feature only if the reconciled reading is right at least 85% of the time **and** no worse than the better single engine. If not, switch it off (config) and keep the single-engine path. + **First result, 2026-10-02, before merge** (`docs/research/reconcile-blind-check-2026-10-02.md`): 30 + random replacement spots on the real 63.6-minute recording, judged blind by Opus from text (not by the + speaker, who delegated it): 21 right, 1 worse than pianissimo, 3 neither reading right, 5 undecidable. + That is 95% of decided items but 70% of all 30; the bar did not say how ties count, so it is **met on + one reading and missed on the other**, and the speaker has not ruled. The second condition, no worse + than the better single engine, is **not answered**: kept-base spots are not stored, so kb-whisper alone + cannot be compared. Left `Proposed`; the feature stays off by default. - Reconcile time above 25 minutes per hour of audio: drop to a smaller adjudicator or skip more disputes automatically. - A different recording or speaker in which the engines agree far less (or far more): re-measure before