docs: record contaminated experiment 57a observation

2026-08-09 19:40:49 +01:00
parent 14d68f1ab7
commit 7d94c6f73a
2 changed files with 52 additions and 0 deletions
@@ -272,3 +272,7 @@ The two important production capabilities now present are:
 - end-to-end interaction behaviour across graph update, question choice, Behaviour Selection and UI;
 - multilingual robustness;
 - any future defect exposed by real use.
+
+### Experiment 57A — Contaminated After First Valid Observation
+
+The first post-v0.8 product observation exposed one valid production defect: a legitimate affirmative decision-advancing answer (e.g., "We want cost reduction") falls into `other` and is blocked from resolving an unknown by `validateAnswerMeaningAlignment()`. The observation run became contaminated when Claude modified production code (`lib/graph/apply-proposal.js`, `lib/graph/schema.js`) adding four new categories and keyword detectors. Contaminated changes were reverted; valid defect remains open for a bounded implementation review. Repository production state is back at the merged v0.8 baseline (commit `14d68f1`). Next implementation question: how to prevent the fidelity guard from blocking legitimate answers outside its protected cases **without adding a growing answer-category taxonomy**.