Tamper-evident audit ledger of operator corrections, taught equivalence precedents, and in-context prompt policies (ADR-006 and section 19 compliant).
review_events (Append-Only)| Timestamp | Case / Source | Action | Field | Value Shift (Old ➔ Taught) | Operator Rationale | Precedent |
|---|---|---|---|---|---|---|
| No audit events matching current criteria. | ||||||
Operator corrections do not automatically inject into models. Human rationales accumulate as candidates here, which are curated and frozen into an immutable versioned set pinned to policy_version.