Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations

2026-05-09

AI Summary

This work addresses the longstanding theoretical gap in explainable artificial intelligence (XAI) concerning the lack of connection between consistency-based diagnosis (CBD) and actual causality or causal responsibility. For the first time, it systematically integrates CBD with frameworks from actual causal explanation, unifying consistency-based diagnosis, actual causality analysis, and quantitative measures of causal responsibility into a coherent theoretical framework. By establishing this linkage, the study not only uncovers the complementary potential between XAI and explainable data management but also lays a novel theoretical and methodological foundation for developing more reliable and interpretable intelligent systems.

Abstract

We establish, from the point of view of Explainable AI (XAI), connections between Consistency-Based Diagnosis (CBD), on one side, and Actual Causality and Causal Responsibility, on the other. CBD has received little attention from the XAI community. Connections between these two areas could have a fruitful impact on XAI and Explainable Data Management.

Problem

• Consistency-Based Diagnosis
• Actual Causality
• Explainable AI
• Causal Responsibility
• Explainable Data Management

Innovation

• Consistency-Based Diagnosis
• Actual Causality
• Causal Responsibility
• Explainable AI
• Explainable Data Management