TY - GEN
T1 - Actual causality canvas
T2 - 24th European Conference on Artificial Intelligence, ECAI 2020, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020
AU - Ibrahim, Amjad
AU - Klesel, Tobias
AU - Zibaei, Ehsan
AU - Kacianka, Severin
AU - Pretschner, Alexander
N1 - Publisher Copyright:
© 2020 The authors and IOS Press.
PY - 2020/8/24
Y1 - 2020/8/24
N2 - The rapid deployment of digital systems into all aspects of daily life requires embedding social constructs into the digital world. Because of the complexity of these systems, there is a need for technical support to understand their actions. Social concepts, such as explainability, accountability, and responsibility rely on a notion of actual causality. Encapsulated in the Halpern and Pearl's (HP) definition, actual causality conveniently integrates into the socio-technical world if operationalized in concrete applications. To the best of our knowledge, theories of actual causality such as the HP definition are either applied in correspondence with domain-specific concepts (e.g., a lineage of a database query) or demonstrated using straightforward philosophical examples. On the other hand, there is a lack of explicit automated actual causality theories and operationalizations for helping understand the actions of systems. Therefore, this paper proposes a unifying framework and an interactive platform (Actual Causality Canvas) to address the problem of operationalizing actual causality for different domains and purposes. We apply this framework in such areas as aircraft accidents, unmanned aerial vehicles, and artificial intelligence (AI) systems for purposes of forensic investigation, fault diagnosis, and explainable AI. We show that with minimal effort, using our general-purpose interactive platform, actual causality reasoning can be integrated into these domains.
AB - The rapid deployment of digital systems into all aspects of daily life requires embedding social constructs into the digital world. Because of the complexity of these systems, there is a need for technical support to understand their actions. Social concepts, such as explainability, accountability, and responsibility rely on a notion of actual causality. Encapsulated in the Halpern and Pearl's (HP) definition, actual causality conveniently integrates into the socio-technical world if operationalized in concrete applications. To the best of our knowledge, theories of actual causality such as the HP definition are either applied in correspondence with domain-specific concepts (e.g., a lineage of a database query) or demonstrated using straightforward philosophical examples. On the other hand, there is a lack of explicit automated actual causality theories and operationalizations for helping understand the actions of systems. Therefore, this paper proposes a unifying framework and an interactive platform (Actual Causality Canvas) to address the problem of operationalizing actual causality for different domains and purposes. We apply this framework in such areas as aircraft accidents, unmanned aerial vehicles, and artificial intelligence (AI) systems for purposes of forensic investigation, fault diagnosis, and explainable AI. We show that with minimal effort, using our general-purpose interactive platform, actual causality reasoning can be integrated into these domains.
UR - http://www.scopus.com/inward/record.url?scp=85091766860&partnerID=8YFLogxK
U2 - 10.3233/FAIA200472
DO - 10.3233/FAIA200472
M3 - Conference contribution
AN - SCOPUS:85091766860
T3 - Frontiers in Artificial Intelligence and Applications
SP - 2978
EP - 2985
BT - ECAI 2020 - 24th European Conference on Artificial Intelligence, including 10th Conference on Prestigious Applications of Artificial Intelligence, PAIS 2020 - Proceedings
A2 - De Giacomo, Giuseppe
A2 - Catala, Alejandro
A2 - Dilkina, Bistra
A2 - Milano, Michela
A2 - Barro, Senen
A2 - Bugarin, Alberto
A2 - Lang, Jerome
PB - IOS Press BV
Y2 - 29 August 2020 through 8 September 2020
ER -