Gate completed checkpoints through training loop

docs/BELGIUM_BUILDING_TRAINING_LOOP.md

@@ -96,6 +96,11 @@ 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
 candidate weights and that exact failure-driven training input.
+An already completed out-of-band checkpoint enters the same contract with
+`--evaluate-initial-model`: the first iteration skips fitting, copies and
+hashes the checkpoint, and begins at calibration. A rejection then follows
+the identical failure-driven CUDA path and cannot open protected test evidence
+early.
 The orchestrator refuses to start unless every automated frozen-dataset gate
 passes and the corpus contains zero blank/low-variance positive tiles. The
 audit status may remain `needs_human_review` while training and objective