Foundations of Fine-Grained Explainability

Abstract

Abstract Explainability is the process of linking part of the inputs given to a calculation to its output, in such a way that the selected inputs somehow “cause” the result. We establish the formal foundations of a notion of explainability for arbitrary abstract functions manipulating nested data structures. We then establish explanation relationships for a set of elementary functions, and for compositions thereof. A fully functional implementation of these concepts is finally presented and experimentally evaluated.