Minimum Satisfying Assignments for SMT

Abstract

A minimum satisfying assignment of a formula is a minimum-cost partial assignment of values to the variables in the formula that guarantees the formula is true. Minimum satisfying assignments have applications in software and hardware verification, electronic design automation, and diagnostic and abductive reasoning. While the problem of computing minimum satisfying assignments has been widely studied in propositional logic, there has been no work on computing minimum satisfying assignments for richer theories. We present the first algorithm for computing minimum satisfying assignments for satisfiability modulo theories. Our algorithm can be used to compute minimum satisfying assignments in theories that admit quantifier elimination, such as linear arithmetic over reals and integers, bitvectors, and difference logic. Since these richer theories are commonly used in software verification, we believe our algorithm can be gainfully used in many verification approaches.