jev-benchmarks
AbdelStark/jev-benchmarks
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
研究と評価Python
- スター
- 17
- フォーク
- 3
トピック
jevpythonbenchmarkingcalibrationevaluation
AbdelStark/jev-benchmarks
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.