Software and data underlying the publication: Explaining Black-Box Models through Counterfactuals

DOI:10.4121/975d2c39-f78e-45d8-a46a-a61e441b1d53.v1
The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
DOI: 10.4121/975d2c39-f78e-45d8-a46a-a61e441b1d53

Datacite citation style

Altmeyer, Patrick; van Deursen, A. (Arie); Liem, Cynthia (2025): Software and data underlying the publication: Explaining Black-Box Models through Counterfactuals. Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/975d2c39-f78e-45d8-a46a-a61e441b1d53.v1
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite

Software

Code and publication-relevant data for our JuliaCon (JCon) Proceedings paper, Explaining Black-Box Models through Counterfactuals, and the corresponding open-source software package: CounterfactualExplanations.jl (CE.jl).


Results ("results_jcon2023.zip") for the paper include:

  1. Images (PNG) that are included in the paper.
  2. Serialized Julia objects (.jls) for classification models ("*_classifier.jls") and variational autoencoders ("*_vae*.jls") used in the paper.


The code base ("CounterfactualExplanations.jl-juliacon-proceedings-jan-2023.tar.gz") corresponds to the release of the CE.jl that was explicitly linked to the JCon publication in 2023. Just like current versions of the package, it contains the Julia code base and test suite (.jl files), along with the documentation (.qmd and .md files). The #paper branch of the repository contains a paper/ subfolder that was used to compile the paper in 2023. All code used to produce the results in the paper leveraged the package itself at the time of publication and can be found in paper/_paper.qmd.


CE.jl is still actively maintained and therefore the most up-to-date reference for this work.

History

  • 2025-07-15 first online, published, posted

Publisher

4TU.ResearchData

Format

png; jls (serialized Julia objects); jl (Julia code scripts); qmd (Quarto documents); md (Markdown)

Associated peer-reviewed publication

Explaining Black-Box Models through Counterfactuals

Organizations

TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Intelligent Systems, Multimedia Computing;
ING Bank

DATA

To access the source code, use the following command:

git clone https://data.4tu.nl/v3/datasets/61a8469b-e56d-48b8-9bfc-1018b2a8ce1a.git "CounterfactualExplanations.jl"

Or download the latest commit as a ZIP.

Files (2)