jev-orderby-bench
yodablocks/jev-orderby-bench
Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.
Research & evaluationPython
- Stars
- 1
- Forks
- 1
Review source
View cited sourceTopics
jevbenchmarkcalibrationduckdbinformation-retrievalllm-evaluationpythonranking