Automate failure-driven training continuation

2026-07-29 15:34:09 +02:00
parent e8530ae476
commit b5155c702f
5 changed files with 71 additions and 1 deletions
@@ -92,6 +92,10 @@ 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.
+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.
 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