mlsanityData to 14 Oct 2026

Uncovering Bugs in Formal Explainers: A Case Study with PyXAI

arXiv 2511.03169 ↗First posted 5 Nov 2025cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Formal explainable artificial intelligence (XAI) offers unique theoretical guarantees of rigor when compared to other non-formal methods of explainability. However, little attention has been given to the validation of practical implementations of formal explainers. This paper develops a novel methodology for validating formal explainers and reports on the assessment of the publicly available formal explainer PyXAI. The paper documents the existence of incorrect explanations computed by PyXAI on most of the datasets analyzed in the experiments, thereby confirming the importance of the proposed novel methodology for the validation of formal explainers.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 82 references that are in the map. First posted on arXiv 5 Nov 2025.

Builds on

42 of 82 references.

References · 42

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  5. 2018Abduction-Based Explanations for Machine Learning Modelscited by 160
  6. 2017PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparisoncited by 140
  7. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 131
  8. 2020On The Reasons Behind Decisionscited by 100
  9. 2020Model Interpretability through the Lens of Computational Complexitycited by 75
  10. 2020Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delaycited by 57
  11. 2021On Explaining Random Forests with SATcited by 57
  12. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
30 more
  1. 2022Logic-Based Explainability in Machine Learningcited by 48
  2. 2022Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networkscited by 42
  3. 2021On the Computational Intelligibility of Boolean Classifierscited by 40
  4. 2021SAT-Based Rigorous Explanations for Decision Listscited by 40
  5. 2021Explanations for Monotonic Classifierscited by 39
  6. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
  7. 2022On Computing Probabilistic Explanations for Decision Treescited by 35
  8. 2021Trading Complexity for Sparsity in Random Forest Explanationscited by 32
  9. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  10. 2022ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanationscited by 26
  11. 2022On the Computation of Necessary and Sufficient Explanationscited by 23
  12. 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
  13. 2022Computing Abductive Explanations for Boosted Treescited by 23
  14. 2022Feature Necessity & Relevancy in ML Classifier Explanationscited by 23
  15. 2023Logic for Explainable AIcited by 23
  16. 2023Explainability is NOT a Gamecited by 23
  17. 2024Local vs. Global Interpretability: A Computational Complexity Perspectivecited by 23
  18. 2024Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementationcited by 21
  19. 2022On Computing Probabilistic Abductive Explanationscited by 18
  20. 2023Delivering Inflated Explanationscited by 16
  21. 2021A unified logical framework for explanations in classifier systemscited by 15
  22. 2023Disproving XAI Myths with Formal Methods -- Initial Resultscited by 12
  23. 2025On the Computational Tractability of the (Many) Shapley Valuescited by 12
  24. 2024Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretationcited by 11
  25. 2025Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanationscited by 10
  26. 2023A New Class of Explanations for Classifiers with Non-Binary Featurescited by 8
  27. 2024A Certified Proof Checker for Deep Neural Network Verification in Imandracited by 7
  28. 2025Most General Explanations of Tree Ensembles (Extended Version)cited by 7
  29. 2023Locally-Minimal Probabilistic Explanationscited by 6
  30. 2022A Logic of "Black Box" Classifier Systemscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Rigorous Explanations for Tree Ensemblescited by 0