A CI trust gate for LLM judges: kappa with confidence intervals against human labels, bias probes, and a label budget calculator

ci evals llm llm-as-judge python quality-gate statistics testing
2 Open Issues Need Help Last updated: Jul 15, 2026

Open Issues Need Help

View All on GitHub
Docs: GitLab CI recipe about 4 hours ago
documentation good first issue

A CI trust gate for LLM judges: kappa with confidence intervals against human labels, bias probes, and a label budget calculator

Python
#ci#evals#llm#llm-as-judge#python#quality-gate#statistics#testing
enhancement good first issue

A CI trust gate for LLM judges: kappa with confidence intervals against human labels, bias probes, and a label budget calculator

Python
#ci#evals#llm#llm-as-judge#python#quality-gate#statistics#testing