A claim-centric perspective on abstract argumentation semantics: Claim-defeat, principles, and expressiveness

Abstract

Dung's abstract argumentation frameworks (AFs) are a key formalism in AI research nowadays. Claims are an inherent part of each argument; they substantially determine the structure of the abstract representation. Nevertheless, they are often not taken into account on the abstract level, which restricts the modeling capacities of AFs to problems that do not involve claims in the evaluation. In this work, we address this shortcoming and conduct a structural analysis of claim-based argumentation semantics utilizing claim-augmented argumentation frameworks (CAFs) which extend AFs by assigning a claim to each argument. Our main contributions are as follows: We first propose novel variants for preferred, naive, stable, semi-stable, and stage semantics based on claim-defeat and claim-set maximization, complementing existing CAF semantics. Among our findings is that for a certain subclass, namely well-formed CAFs, the different versions of preferred and stable semantics coincide, which is not the case for the other semantics. We then conduct a principle-based analysis of the semantics with respect to general and well-formed CAFs. Finally, we study the expressiveness of the semantics by characterizing their signatures. In summary, this paper provides a thorough analysis of fundamental properties of abstract argumentation semantics (along the lines of existing results for AFs) but from the perspective of the claims the arguments represent. This shift of perspective provides novel results which we deem relevant when abstract argumentation is used in an instantiation-based setting.