Target regional training failures by context

docs/BELGIUM_BUILDING_TRAINING_LOOP.md

@@ -92,6 +92,13 @@ recall are repeated, while true negative train tiles are repeated when a
 regional precision gate or the pure-background gate fails. Calibration, test,
 background-test and validation AOIs are excluded by their frozen corpus split;
 the generated evidence records that no protected sample entered training.
+Per-AOI calibration evidence also identifies failed region/context pairs.
+Train-only AOIs with the same governed context receive a stronger repeat factor
+than the remaining failed region, so correction rounds target distinct failure
+modes without copying a protected AOI into training. The sampling evidence
+records both context sets and repeat factors. When no matching train context
+exists, regional sampling remains active and the missing context becomes a
+concrete input for the next immutable corpus expansion.
 The checkpointed orchestrator invokes this builder after every rejected
 iteration, stores its checksum in `training-loop-state.json`, and uses the
 resulting dataset YAML for the next checkpoint. A restart resumes both the

docs/CODEX_EXECUTION_LOG.md

@@ -1,3 +1,12 @@
+## 2026-07-29 - Context-aware Belgian training correction
+
+- Audited the active closed-loop calibration trend and confirmed that the
+  remaining Flemish failure cannot be solved by confidence-threshold selection.
+- Extended failure-driven sampling with region-plus-context weighting from
+  per-AOI calibration evidence. Protected calibration, test, background-test
+  and validation tiles remain excluded; manifests now record targeted contexts
+  and their stronger repeat factors for reproducible follow-up iterations.
+
 ## 2026-07-27 - Guest demo and product professionalization
 
 - Audited the access experience, workbench information density, responsive