Model card

astris-feedback-loop-v1

Continuous feedback loop across four channels — match rating, placement outcome, parse correction, and translation correction. Every event updates a learner: placement outcomes flow into the governance window and move the retention-ensemble weights, while parse/translation corrections feed the extraction retrieval store. Exposed at POST /api/v1/feedback.

At a glance

Kindreasoning llm
Version1.0.0
StatusActive — contributing to scores
Ensemble weight0
Trained atNot trained yet
Trained onn/a
ArtifactNo artifact (heuristic or pre-training)

Metrics

{
  "channels": [
    "match_rating",
    "placement_outcome",
    "parse_correction",
    "translation_correction"
  ],
  "endpoint": "POST /api/v1/feedback",
  "validation": "synthetic_seed",
  "real_cohort": "pending"
}

Notes

Orchestration layer that routes feedback to the right learner; not itself a retention voter — weight 0. See api/ml/feedback.py and governance.py.