We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas of the input feature space. To automatically generate space explanations, we leverage a range of flexible Craig interpolation algorithms and unsatisfiable core generation. Based on real-life case studies, ranging from small to medium to large size, we demonstrate that the generated explanations are more meaningful than those computed by state-of-the-art.
@article{arxiv.2511.22498,
title = {Space Explanations of Neural Network Classification},
author = {Faezeh Labbaf and Tomáš Kolárik and Martin Blicha and Grigory Fedyukovich and Michael Wand and Natasha Sharygina},
journal= {arXiv preprint arXiv:2511.22498},
year = {2025}
}