Actual Causality
Overview
Actual causality asks which events made a particular outcome happen, rather than merely predicting outcomes or finding correlations. Common approaches use Halpern–Pearl definitions in structural causal models, testing counterfactual interventions and refining but-for tests to handle preemption and overdetermination. These methods support explanations and responsibility judgments in settings such as image classifiers, system failures, and multi-agent decisions, with algorithms increasingly designed to find minimal causes at practical scales. A central tension is balancing formal properties and computational efficiency while ensuring that model-based attributions capture relevant dependencies and match intuitive or human judgments.
Latest papers
18 papers4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.