Finalize

Score the best candidate on the held-out TEST split exactly once and seal the run. Use as the last evaluation step, after optimization stops. The run dir enforces the seal — a second finalize raises an error — so the headline number is produced once on data the optimizer never saw, the way an honest benchmark result must be.

skillberry-ai Updated 69 repo stars
Play the 85-second cap-evolve demo — the CLI, four real dashboard tabs, and both benchmark results

File contents

skillberry-ai/cap-evolve commit 6baeb8ad67

Frequently asked questions

npx get-skill add skillberry-ai/finalize