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.
- 星标
- 0
- 派生
- 1
收录依据
README 报告了一项预注册的 Jev 概率排序评测,使用 360 条人工标注数据;结果为作者报告,本次未复现。