No AI summary available for this article.
Why It Matters
Formal explainability provides mathematically grounded justifications for individual predictions.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human cognitive limits by involving too many features, while probabilistic relaxations have remained largely limited to categorical classification. We present a unified framework for probabilistic explainability based on sparse, anchored linear models, applicable to both binary classification and continuous regression. By mapping instances to the Boolean hypercube, our linear explanations strictly generalize subset-based approaches: they capture both th...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.19077v1 · Indexed about 1 hour ago