Zenodo | Github

Abstract

We verify the outcome of the methodology proposed in the article, which attempts to provide post-hoc causal explanations for black-box classifiers through causal reference. This is achieved by replicating the code step by step, according to the descriptions in the paper. All the claims in the paper have been examined, and we provide additional metric to evaluate the portability, expressive power, algorithmic complexity and the data fidelity of their framework. We have further extended their analyses to consider all benchmark datasets used, confirming results.

Citation

 1@article{verhoevenReReplicationStudy2021,
 2  title = {[{{Re}}] {{Replication Study}} of '{{Generative}} Causal Explanations of Black-Box Classifiers'},
 3  author = {Verhoeven, Ivo and Chen, Xinyi and Hu, Qingzhi and Holubar, Mario},
 4  year = {2021},
 5  month = may,
 6  journal = {ReScience C},
 7  volume = {7},
 8  number = {2},
 9  pages = {\#23},
10  doi = {10.5281/zenodo.4835600},
11}