Model Checking Causality - Université d'Artois
Communication Dans Un Congrès Année : 2024

Model Checking Causality

Résumé

We present a novel modal language for causal reasoning and interpret it by means of a semantics in which causal information is represented using causal bases in propositional form. The language includes modal operators of conditional causal necessity where the condition is a causal change operation. We provide a succinct formulation of model checking for our language and a model checking procedure based on a polysize reduction to QBF. We illustrate the expressiveness of our language through some examples and show that it allows us to represent and to formally verify a variety of concepts studied in the field of explainable AI including abductive explanation, intervention and actual cause.
Fichier non déposé

Dates et versions

hal-04695194 , version 1 (12-09-2024)

Identifiants

Citer

Tiago de Lima, Emiliano Lorini. Model Checking Causality. 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), Aug 2024, Jeju, South Korea. pp.3324--3332, ⟨10.24963/ijcai.2024/368⟩. ⟨hal-04695194⟩
89 Consultations
0 Téléchargements

Altmetric

Partager

More