{"schema":"voidly-sentinel-al-loop-status/v1","generated_at":"2026-11-18T04:33:00.025742Z","loop_state":"plumbed_idle","loop_note":"The loop is wired end to end (queue -> submit-label -> aggregate -> promote -> retrain) and is idle until reviewers label candidates at /atlas/active-learning.","stages":{"1_queue":{"queue_size":527,"endpoint":"/v1/sentinel/active-learning-queue"},"2_labels_submitted":{"audit_log_exists":false,"endpoint":"/v1/sentinel/active-learning-submit-label"},"3_consensus":{"consensus_threshold":null,"last_aggregated_at":null,"aggregator":"aggregate-active-learning-labels.py"},"4_promoted_to_training":{"corpus":"labeled_incidents_v3.3.json","promotion_script":"promote-al-labels-to-training.py"},"5_retrain":{"last_retrain_included_al_labels":null,"note":"Timestamp of the last corpus promotion — the most recent point at which a v3.3 retrain would have consumed active-learning labels. Null = no promotion has happened yet.","retrain_queue":{"queued":true,"trigger":"concept-drift","triggers":["concept-drift"],"active_learning_in_trigger":false,"queued_at":"2026-11-17T05:20:18.013528+00:00","scheduled_for":"next 02:00 UTC weekly cron","note":"A retrain is queued. weekly-retrain.sh (cron 02:00 UTC Sun) consumes this file and deletes it after a successful retrain. If 'active-learning' is in triggers, the next retrain will learn from promoted human-consensus labels."}}},"simulated_f1_lift":{"f1_median_delta":-0.0696,"f1_mean_delta":-0.0111,"baseline_f1_median":0.8695652173913043,"augmented_f1_median":0.8,"simulated_with_top_n_candidates":42,"generated_at":"2026-11-17T04:30:02.273017+00:00"},"honest_caveats":["Active-learning value depends on humans actually labelling. loop_state plumbed_idle means no human labels yet.","simulated_f1_lift uses PROXY labels (incident-table positives within +/-3 days, else negative), not human labels. It is an optimistic estimate; treat it as \"is the queue surfacing learnable rows\", not a promotion signal."],"internal_operator_metric":true,"surface":"active_learning_label_submissions","note":"Usage and adoption counts are internal operator metrics and are not published. This public response is intentionally count-free: a missing count is not zero and does not mean the service is down."}