Models: comparison to an evidence-backed decision

00:00:00.000 — Compare the candidate evidence
Compare the baseline and two candidates against the same predictive evaluation. Aggregate quality alone does not establish readiness.

00:00:09.847 — Inspect the slice that fails
Trial 3 has hazardous-load recall of 0.84 against a minimum of 0.90. A stronger overall score does not remove this failed guardrail.

00:00:21.687 — Retain the next decision
Continue study preserves the decision and its reason. No new model release is selected by this comparison.