What it does
It analyses exported decisions rather than calling TypeSafe Jev.
- Primitives
- Not stated
- Platform
- Python
- Added
- Project created
- GitHub stars
- 18 · snapshot 2026-09-25
Source checked 2026-09-25 — opened the primary source directly.
Benchmarks & research
jeval
Evaluates whether classifier confidence is calibrated and derives human-review thresholds from the cost of mistakes.
Screenshot unavailable. Open the experiment ↗