Published September 11, 2025 | Version v1.1.1-DOI

Replication code: Class-Dependent Perturbation Effects in Evaluating Time Series Attributions

Authors/Creators

  • 1. ROR icon Eindhoven University of Technology

Description

This repository contains the code and experiment results for our paper:

Baer, G., Grau, I., Zhang, C., & Van Gorp, P. (2025). 
Class-Dependent Perturbation Effects in Evaluating Time Series Attributions.
Accepted at The World Conference on eXplainable Artificial Intelligence (XAI-2025).
Preprint available at: https://arxiv.org/abs

This release corresponds to the camera-ready version of our paper "Class-Dependent Perturbation Effects in Evaluating Time Series Attributions" accepted at The World Conference on eXplainable Artificial Intelligence (XAI-2025).

This release is identical to v1.1.0. This release was only made to connect and create DOI with Zenodo integration.

Files

gregorbaer/class-perturbation-effects-v1.1.1-DOI.zip

Files (71.4 MB)

Name Size
md5:ad74f8072b6dfe75782942272bf46000
71.4 MB Preview Download

Additional details

Related works

Software

Repository URL
https://github.com/gregorbaer/class-perturbation-effects
Programming language
Python
Development Status
Inactive