Causes and Explanations: A Structural-Model Approach. Part I: Causes
2005/11/09 by Joseph Y. Halpern, Judea Pearl · 44 citations
Computer Science · Mathematics · Arts and Humanities · #Bayesian Modeling and Causal Inference #Advanced Causal Inference Techniques #Philosophy and History of Science
paper · doi:10.1093/bjps/axi147
Abstract
We propose a new definition of actual causes, 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. 1. Introduction2. Causal models: a review2.1Causal models2.2Syntax and semantics3. The definition of cause4. Examples5. A more refined definition6. DiscussionAAppendix: Some Technical IssuesA.1The active causal processA.2A closer look at AC2(b)A.3Causality with infinitely many variablesA.4Causality in nonrecursive models
Cited by
- Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications
- Causes and Explanations: A Structural-Model Approach. Part II: Explanations
- Spreading the blame: The allocation of responsibility amongst multiple agents
- Explanation in artificial intelligence: Insights from the social sciences
- Grounding in the image of causation
- Explanatory priority monism
- Causation in terms of production
- Explanation grounds causation
- Prevention, Preemption, and the Principle of Sufficient Reason
- Explanatory circles
- Broken brakes and dreaming drivers: the heuristic value of causal models in the law
- Causality and Minimal Supports in Recursive Datalog
- A Communication-First Account of Explanation
- A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
- Optimal Comprehensible Targeting
- Causality Without Causal Models
- TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models
- Learning Causal Models of Autonomous Agents using Interventions
- Rendering Interventionism and Non-Reductive Physicalism Compatible
- From Verification to Causality-based Explications
- Security Properties as Nested Causal Statements
- Explainability Requirements as Hyperproperties
- Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
- Factual Difference-Making
- Causation
- Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae
- A formalization of Heisenbugs and their causes in terms of hyperproperties
- From Causes for Database Queries to Repairs and Model-Based Diagnosis and Back
- 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
- Program Actions as Actual Causes: A Building Block for Accountability
- Combining Probabilistic, Causal, and Normative Reasoning in CP-logic
- Reverse data management [wikipedia]
- Quantitative causal selection patterns in token causation. [europepmc]
- What Caused What? A Quantitative Account of Actual Causation Using Dynamical Causal Networks. [europepmc]
- What would have happened? Counterfactuals, hypotheticals and causal judgements. [europepmc]
- On formal limitations of causal ecological networks. [europepmc]
- Studying asphyxiation in the lab: the role of experimental evidence in cause-of-death inquiry. [europepmc]
- Challenges and Opportunities in Causality Analysis Using Large Language Models. [europepmc]
- Plural Causes. [europepmc]
- Collaborate and explain on-the-fly: knowledge-based reasoning and learning in ad hoc teamwork. [europepmc]
- Robot pouring: identifying causes of spillage and selecting alternative action parameters using probabilistic actual causation. [europepmc]
Related