AI RESEARCH
$\phi$-Table: A Statistical Explanation for Global SHAP
arXiv CS.LG
•
ArXi:2512.07578v3 Announce Type: replace-cross Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but do not indicate whether their effects admit clear directional summaries, how uncertain those summaries are, or how faithfully they represent the fitted response. This paper proposes the $\phi$-table, a SHAP-based statistical explanation table for tabular black-box regression models.