Attribution Upsampling should Redistribute, Not Interpolate

ArXi:2603.16067v1 Announce Type: cross Attribution methods in explainable AI rely on upsampling techniques that were designed for natural images, not saliency maps. Standard bilinear and bicubic interpolation systematically corrupts attribution signals through aliasing, ringing, and boundary bleeding, producing spurious high-importance regions that misrepresent model reasoning.