Structural Compactness as a Complementary Criterion for Explanation Quality

Computer Science > Artificial Intelligence [Submitted on 31 Mar 2026] Structural Compactness as a Complementary Criterion for Explanation Quality Mohammad Mahdi Mesgari, Jackie Ma, Wojciech Samek, Sebastian Lapuschkin, Leander Weber In the evaluation of attribution quality, the quantitative assessment of explanation legibility is particularly difficult, as it is influenced by varying shapes and internal organization of attributions not captured by simple statistics. To address this issue, we introduce Minimum Spanning Tree Compactness (MST-C), a graph-based structural metric that captures higher-order geometric properties of attributions, such as spread and cohesion. These components are combined into a single score that evaluates compactness, favoring attributions with salient points spread across a small area and spatially organized into few but cohesive clusters. We show that MST-C reliably distinguishes between explanation methods, exposes fundamental structural differences between models, and provides a robust, self-contained diagnostic for explanation compactness that complements existing notions of attribution complexity. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.29491 [cs.AI]   (or arXiv:2603.29491v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.29491 Focus to learn more Submission history From: Mohammad Mahdi Mesgari [view email] [v1] Tue, 31 Mar 2026 09:36:52 UTC (23,903 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)