PyPI page
Home page
Author:
yongzhe2160cs
License:
MIT
Summary:
Statistical validation for LLM/ML eval comparisons: paired delta CIs, multiple-testing correction, deflated significance, power analysis, and noise diagnostics. Most reported eval deltas are noise — this gates them.
Latest version:
0.1.1
Required dependencies:
numpy
Optional dependencies:
pytest
|
ruff
Downloads last day:
0
Downloads last week:
8
Downloads last month:
430