eval-harness

metric

class_match

better
higher
kind
quality: measured against a reference or by a judge
decides
no goal
weighed by
no goal
recorded on
fleet_dedup_v1

01what it measures, and how

1 when all three flags (operational, test, low_signal) are the pinned code's, else 0.

A project explains its own metric at length with METRIC_DESCRIPTIONS = {"class_match": {"summary": "…", "details": "…"}}.

02on fleet_dedup_v1

scored against silverscored by a judgewrote the reference it is scored againstscored against a label set, not a reference setunmarked rows are scored against gold

armmean class_matchitemsscored against
dedup_guard_v11.000100silver/fleet_dedup_v1 silver