A software architecture for verifiable and explainable classification
Machine Learning · 2026-04 · 115 (4)
DOI: 10.1007/s10994-026-07006-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning, online erschienen am 07.04.2026. Verfasst von Raul Barbosa und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade de Coimbra.
Abstract (Originalsprache)
In the context of machine learning, classification is the procedure of predicting the class to which each element of a population belongs to. Most classification functions, for real world problems, are imperfect and thus require rigorous analysis for use in safety-critical applications such as health care. This paper proposes a software architecture for improving the trustworthiness and explainability of AI-based classifiers. The architecture combines a search-based approach with machine-learned explanations and satisfiability solving, to provide an indication of classification confidence and counterfactual explanation rules that are deductively verified to be consistent with the classifier. An implementation of the proposed architecture is evaluated on a medical case study of prognosis of Acute Coronary Syndrome (ACS). The evaluation shows that the proposed architecture is consistently able to complement each individual classification with an indication of confidence and an explanation, which is formally verified for consistency with the classifier. This contributes to foster trustworthy and explainable classification.
Förderung
- Universidade de Coimbra
Zitieren
APA
Barbosa, R., Rinzivillo, S., Robin, J., Beretta, A., & Madeira, H. (2026). A software architecture for verifiable and explainable classification. Machine Learning, 115(4). https://doi.org/10.1007/s10994-026-07006-0
Vancouver
Barbosa R, Rinzivillo S, Robin J, Beretta A, Madeira H. A software architecture for verifiable and explainable classification. Machine Learning. 2026;115(4). doi:10.1007/s10994-026-07006-0
BibTeX
@article{Barbosa2026,
author = {Barbosa, Raul and Rinzivillo, Salvatore and Robin, Jacques and Beretta, Andrea and Madeira, Henrique},
title = {A software architecture for verifiable and explainable classification},
journal = {Machine Learning},
year = {2026},
volume = {115},
number = {4},
doi = {10.1007/s10994-026-07006-0}
}
EUVIMED