AI RESEARCH
GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation
arXiv CS.LG
•
ArXi:2605.05480v1 Announce Type: new The main XAI attribution methods for deep neural networks -- GradCAM, SHAP, LIME, Integrated Gradients -- operate on separate theoretical foundations and are not formally comparable. We present GRALIS (Gradient-Riesz Averaged Locally-Integrated Shapley), a mathematical framework establishing a representation theory for attributions: every additive, linear, and continuous attribution functional on L^2(Q,mu) admits a unique canonical representation (Q, w, Delta), proved necessary by the Riesz Representation Theorem.