Project description

Solvability-Based Explainer (solvex)

This package implements the model-agnostic explainer introduced in the EACL 2023 (Findings) paper The Solvability of Interpretability Evaluation Metrics.

This package can be installed with pip install solvex.

Please refer to the project homepage for toturials and documentation. In addition, sample jupyter notebooks are available in the examples folder.

These details have not been verified by PyPI

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

This version

1.0.3

Feb 6, 2023

1.0.2

Feb 3, 2023

1.0.1

Feb 3, 2023

1.0.0

Feb 3, 2023

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Uploaded Feb 6, 2023 Source

Uploaded Feb 6, 2023 Python 3

Hashes for solvex-1.0.3.tar.gz
Algorithm	Hash digest
SHA256	`89bc55d8eb942fa9712d78cc9396685eb7d1e2bd39f19ca6251b7bf80fcc0d5a`
MD5	`a6304b86b004a4d02ff4e22240b7f486`
BLAKE2b-256	`9c477d3a27d5805067b17e62edb976d3c6a232f1224f7bdb9470550b3c64ab49`

Hashes for solvex-1.0.3-py3-none-any.whl
Algorithm	Hash digest
SHA256	`97e8acd76a0844b628f2294b9b00c199ee2e38bcaab34ac78dfd50e9a2bcfc64`
MD5	`0cdf0cb1649d82b5ab96aef1640b3b04`
BLAKE2b-256	`94fa612fa7e4ddce0e6fca3bafef6b27efddf889c4ae4b16efb98d2bb0351bf8`