Files
geointel/backend/tests
JensandClaude Opus 5 f6eced1b94 rank model variants on average precision, and say when they are not comparable
The workbench ranks model variants by a stored F1, each measured at that
variant's own confidence threshold. A conservatively calibrated detector then
looks worse than a liberal one without detecting anything differently: the
number says as much about the threshold as about the model. POST
/detection/runs/compare ranks on average precision instead, which describes the
whole ranking a model produced, and keeps each run's own-threshold F1 visible
next to it so the difference between the two readings is auditable.

Comparability comes before the ranking. Runs over different source rasters,
scored against different references, without a proven inference footprint, or
covering a different evaluated population are not alternatives to one another,
and no metric makes them so. The report names which of those applies and still
returns the numbers — they are simply not a ranking.

Each run is scored through the same QA path the workbench uses, so a comparison
and the persisted quality checks cannot drift apart.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-22 19:47:14 +02:00
..
2026-06-16 23:36:32 +02:00
2026-07-27 18:38:52 +02:00
2026-07-27 18:38:52 +02:00