# Better Paracoherent Answer Sets with Less Resources

## TL;DR

This paper introduces an efficient method for computing improved paracoherent answer sets in ASP, enabling meaningful reasoning from incoherent programs with reduced computational resources.

## Contribution

It presents a novel evaluation technique for split semi-equilibrium semantics that improves the efficiency of computing paracoherent answer sets.

## Key findings

- Better paracoherent answer sets are computed with less resources.
- The method outperforms existing approaches on hard benchmarks.
- It extends ASP's applicability to incoherent programs effectively.

## Abstract

Answer Set Programming (ASP) is a well-established formalism for logic programming. Problem solving in ASP requires to write an ASP program whose answers sets correspond to solutions. Albeit the non-existence of answer sets for some ASP programs can be considered as a modeling feature, it turns out to be a weakness in many other cases, and especially for query answering. Paracoherent answer set semantics extend the classical semantics of ASP to draw meaningful conclusions also from incoherent programs, with the result of increasing the range of applications of ASP. State of the art implementations of paracoherent ASP adopt the semi-equilibrium semantics, but cannot be lifted straightforwardly to compute efficiently the (better) split semi-equilibrium semantics that discards undesirable semi-equilibrium models. In this paper an efficient evaluation technique for computing a split semi-equilibrium model is presented. An experiment on hard benchmarks shows that better paracoherent answer sets can be computed consuming less computational resources than existing methods. Under consideration for acceptance in TPLP.