Appendix B — Supervision

Keywords

Artificial Intelligence, Trustworthy AI, Counterfactual Explanations, Algorithmic Recourse

The author of this dissertation supervised multiple bachelor’s and master’s students at TU Delft. He also mentored external students looking to contribute to open-source software as part of Julia Seasons of Contributions and Google Summer of Code.

B.1 Master’s Students

Aleksander Buszydlik (2024). ‘Finding Recourse for Algorithmic Recourse’. Available at: https://resolver.tudelft.nl/uuid:be47ad5a-5a4b-457c-b214-35c6c78cae36

Karol Dobiczek (2024). ‘Natural Language Counterfactual Explanations in Financial Text Classification’. Available at: https://resolver.tudelft.nl/uuid:66730110-d296-4a57-b382-e9a6cc0a4aa5

Ivor Zagorac (2024). ‘A Study on Counterfactual Explanations’. Available at: https://resolver.tudelft.nl/uuid:6e2c240c-03c6-4e0e-af2c-5d257e77c77c

Marit E. Radder (2024). ‘A counterfactual-based evaluation framework for machine learning models that use gene expression data’. Available at: https://resolver.tudelft.nl/uuid:4cf92f8f-2a4c-43e8-9746-2ff33ca65de5

B.2 Bachelor’s Students

Dimitar Nikolov (2024). ‘How Does Predictive Uncertainty Quantification Correlate with the Plausibility of Counterfactual Explanations’. Available at: https://resolver.tudelft.nl/uuid:b0ecc3fe-4454-4c44-a624-5d335d108634

Rithik Appachi Senthilkumar (2024). ‘Are Neural Networks Robust to Gradient-Based Adversaries Also More Explainable? Evidence from Counterfactuals’. Available at: https://resolver.tudelft.nl/uuid:47786bb4-ae24-4972-94a0-1bd18d756486

Giacomo Pezzali (2024). ‘Do Joint Energy-Based Models Produce More Plausible Counterfactual Explanations?’. Available at: https://resolver.tudelft.nl/uuid:afe2d50d-f4b3-403f-b0e7-a0b8ede96bb0

Ali Faruk Yücel (2024). ‘Metrics to Ascertain the Plausibility and Faithfulness of Counterfactual Explanations’. Available at: https://resolver.tudelft.nl/uuid:d80b688c-b0f6-4c88-a0a2-891d738f25d4

Ipek Iscan (2024). ‘Advancing Explainability in Black-Box Models’. Available at: https://resolver.tudelft.nl/uuid:e50c1cae-d579-405a-9089-86a0ca925086

Giovan Angela (2023). ‘Endogenous Macrodynamics in Algorithmic Recourse’. Available at: https://resolver.tudelft.nl/uuid:5023154a-53c6-44ca-9d09-1670ba0ded31

Aleksander Buszydlik (2022). ‘Quantifying the Endogenous Domain and Model Shifts Induced by the DiCE Generator’. Available at: https://resolver.tudelft.nl/uuid:cb0bf4ac-4055-489b-b768-e5b53ec6fa47

Karol Dobiczek (2022). ‘Quantifying the Endogenous Domain and Model Shifts Induced by the CLUE Recourse Generator’. Available at: https://resolver.tudelft.nl/uuid:6a249d72-9e1e-4e81-abdc-463260c7d1bc

B.3 External

Google Summer of Code 2024

Together with Mojtaba Farmanbar, the author of this dissertation mentored Pasquale Caterino, who contributed support for conformalized Bayes to our ConformalPrediction.jl (Caterino 2024).

Julia Season of Contributions 2024

Together with Moritz Schauer, Patrick mentored Jorge Luiz Franco, who contributed support for causal algorithmic recourse to our CounterfactualExplanations.jl (Luiz Franco 2024).

Jorge Luiz Franco (2024). ‘JSoC: When Causality Meets Recourse’. Available at: https://www.taija.org/blog/posts/causal-recourse/

Pasquale Caterino (2024). ‘Google Summer of Code 2024 Final Report: Add support for Conformalized Bayes to ConformalPrediction.jl’. Available at: https://gist.github.com/pasq-cat/f25eebc492366fb6a4f428426f93f45f

Caterino, Pasquale. 2024. “Google Summer of Code 2024 Final Report: Add Support for Conformalized Bayes to ConformalPrediction.jl.” https://gist.github.com/pasq-cat/f25eebc492366fb6a4f428426f93f45f.

Luiz Franco, Jorge. 2024. “JSoC: When Causality Meets Recourse.” https://www.taija.org/blog/posts/causal-recourse/.