https://pypi.org/project/eval-integrity/ Recent updates to the Python Package Index for eval-integrity en https://pypi.org/project/eval-integrity/0.4.1/ Dependency-free statistical checks for AI eval claims (multiple-comparisons, judge-bias, resolution, fragility) — as a CLI and an MCP server an agent calls before trusting a benchmark number. Thu, 23 Jul 2026 12:57:16 GMT https://pypi.org/project/eval-integrity/0.4.0/ Dependency-free statistical checks for AI eval claims (multiple-comparisons, judge-bias, resolution, fragility) — as a CLI and an MCP server an agent calls before trusting a benchmark number. Thu, 23 Jul 2026 12:26:36 GMT