docs(adr): ADR-034 records the first live smoke, including the wrong call

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-01 23:27:22 +02:00
co-authored by Claude Sonnet 5.5
parent c3c9b1e48a
commit 2497554683
+7
View File
@@ -1627,6 +1627,13 @@ Mode on iguana is the unproven suspect).
the wrong one (it was right 92% on a hand-picked set, ~97% for 31b). the wrong one (it was right 92% on a hand-picked set, ~97% for 31b).
- Reading the page takes more words: the reconciliation summary is new surface to keep honest. - Reading the page takes more words: the reconciliation summary is new surface to keep honest.
**First live smoke (2026-10-01, synthetic audio, 3 disputes):** all 3 were changed to the
alternative's reading; against the known script 2 were right and **1 was wrong** (a name replaced by a
pronoun, a correct base reading lost). That is one run of three, not a measurement, but it is the failure
this design must expect: the reconciler can overwrite a correct reading, which is why changed spots, not
only uncertain ones, are listed on the page, and why the decision below is a blind check on a real
recording.
**Validation / resolution triggers.** **Validation / resolution triggers.**
- **The test that decides it:** re-upload the same real recording after merge; the speaker judges, blind, - **The test that decides it:** re-upload the same real recording after merge; the speaker judges, blind,
~30 disputes where the reconciled text differs from pianissimo alone. Keep the feature only if the ~30 disputes where the reconciled text differs from pianissimo alone. Keep the feature only if the