Causes and Explanations: A Structural-Model Approach, Part I: Causes

2000/11/07 by Halpern, Joseph Y., Pearl, Judea · 11 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #I.2.4

paper · doi:10.48550/arxiv.cs/0011012

Abstract

We propose a new definition of actual cause, using structural equations to model counterfactuals. We show that the definition yields a plausible and elegant account of causation that handles well examples which have caused problems for other definitions and resolves major difficulties in the traditional account.

Cited by

• Optimal Comprehensible Targeting
• Causality Without Causal Models
• TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models
• Explainability Requirements as Hyperproperties
• Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
• Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae
• A formalization of Heisenbugs and their causes in terms of hyperproperties
• Causality and Decision-making: A Logical Framework for Systems and Security Modelling
• I Am Big, You Are Little; I Am Right, You Are Wrong
• Causal Identification of Sufficient, Contrastive and Complete Feature Sets in Image Classification
• A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers

Related

• Causes and Explanations: A Structural-Model Approach --- Part 1: Causes
• Causes and Explanations: A Structural-Model Approach. Part I: Causes
• Causes and Explanations: A Structural-Model Approach. Part II: Explanations
• Causes and Explanations: A Structural-Model Approach. Part II: Explanations
• Actual causation and the art of modeling