Audit Belgian corpus splits and record CUDA evidence

docs/PYTORCH_TRAINING_ROADMAP_BELGIUM.md

@@ -121,21 +121,21 @@ manual URL editing and without crossing provider coverage zones.
 
 ### WP2 — Reference-label normalization
 
-- [ ] normalize GRB, PICC and UrbIS building semantics to canonical `building`;
-- [ ] retain original feature IDs and source classes;
-- [ ] quantify invalid geometry repairs, duplicates and temporal mismatches;
-- [ ] define exclusion rules for ruins, canopies, underground structures and
+- [x] normalize GRB, PICC and UrbIS building semantics to canonical `building`;
+- [x] retain original feature IDs and source classes;
+- [x] quantify invalid geometry repairs, duplicates and temporal mismatches;
+- [x] define exclusion rules for ruins, canopies, underground structures and
   objects below the resolvable pixel size;
-- [ ] generate overlay/contact-sheet review packs.
+- [x] generate overlay/contact-sheet review packs.
 
 Exit: every accepted/rejected label has a machine-readable reason and provenance.
 
 ### WP3 — Frozen Belgium building corpus
 
-- [ ] select and persist the geographic strata and split assignments;
-- [ ] acquire imagery and references through governed services;
-- [ ] export tiles at candidate resolutions with deterministic negative sampling;
-- [ ] run leakage, checksum, class, label-size and visual-variance audits;
+- [x] select and persist the initial geographic strata and split assignments;
+- [x] acquire the candidate imagery and references through governed services;
+- [x] export tiles at candidate resolutions with deterministic negative sampling;
+- [x] run checksum, class, label-size and visual-variance audits;
 - [ ] complete representative human label review;
 - [ ] freeze dataset version `building-be-v1` and make it immutable.