Spaces:

vxa8502
/

Sage

Running

App Files Files Community

Sage / data /eval_results

Commit History

Calibrate evidence quality gate thresholds

fbc14e7

vxa8502 commited on Mar 6

Add bootstrap confidence intervals to evaluation metrics

ca96fbf

vxa8502 commited on Mar 5

Fix eval workflow and align README metrics with eval_results JSON

ae4342a

vxa8502 commited on Feb 10