Open Issues Need Help
View All on GitHub Docs: GitLab CI recipe 23 days ago
documentation good first issue
Statistically calibrated ship or block CI gates for LLM evals: paired bootstrap verdicts, power analysis, sequential early stopping, and a GitHub Action
Python
#ci#evals#github-actions#llm#llm-evaluation#python#quality-gate#statistics#testing
Adapter: JUnit XML results 23 days ago
enhancement good first issue
Statistically calibrated ship or block CI gates for LLM evals: paired bootstrap verdicts, power analysis, sequential early stopping, and a GitHub Action
Python
#ci#evals#github-actions#llm#llm-evaluation#python#quality-gate#statistics#testing
Adapter: DeepEval results files 23 days ago
enhancement good first issue
Statistically calibrated ship or block CI gates for LLM evals: paired bootstrap verdicts, power analysis, sequential early stopping, and a GitHub Action
Python
#ci#evals#github-actions#llm#llm-evaluation#python#quality-gate#statistics#testing