PyPI page
Author:
Yuxiang Ji
Summary:
The same-configuration noise floor of an evaluation: per-item verdict flakiness, model-pair sign-stability rulings, and a CI gate, from the repeated runs you already have.
Latest version:
0.2.1
Optional dependencies:
mkdocs
|
mkdocs-material
|
mypy
|
pytest
|
ruff
Downloads last day:
1
Downloads last week:
5
Downloads last month:
44
7-day smoothing