Metadata-Version: 2.4
Name: human-movement-bench
Version: 0.1.2
Summary: Independent reproducible evaluation of timed human input traces
Author: Karim Galal
License-Expression: MIT
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.12
Classifier: Typing :: Typed
Requires-Dist: numpy>=2.1
Requires-Dist: scipy>=1.14
Requires-Dist: scikit-learn>=1.5
Requires-Dist: joblib>=1.4
Requires-Dist: pytweening==1.2.0 ; extra == 'baselines'
Requires-Dist: selenium>=4.25 ; extra == 'baselines'
Requires-Dist: pillow>=11 ; extra == 'datasets'
Requires-Dist: pyarrow>=19 ; extra == 'datasets'
Requires-Dist: torch>=2.6 ; extra == 'detectors'
Maintainer: Karim Galal
Requires-Python: >=3.12
Provides-Extra: baselines
Provides-Extra: datasets
Provides-Extra: detectors
Description-Content-Type: text/markdown

# Human Movement Benchmark

Independent evaluation of timed mouse, click, keyboard and scroll traces. Developed and maintained solely by Karim Galal.

```sh
pip install human-movement-bench
human-movement-bench --help
```

Install `human-movement-bench[detectors]` to use the optional PyTorch detector. This evaluator does not import the movement generator. Headline scores require matched independent data, detector controls and successful functional checks; synthetic fixtures only validate the implementation.

Licensed under MIT. See the included LICENSE file.
