How Artificial Intelligence Leads to Knowledge Why: An Inquiry Inspired by Aristotle's Posterior Analytics
Guus Eelink, Kilian Rückschloß, Felix Weitkämper
TL;DR
The paper tackles the distinction between knowledge-that and knowledge-why in AI by formalizing Aristotle’s causal notions within a unified framework called causal systems. It critiques Bochman’s acyclic causality, extends the theory to handle cycles and interventions, and develops a probabilistic generalization using maximum entropy to model knowledge-why under uncertainty. By embedding Pearl’s structural causal models, log-linear models, and Bayesian networks into causal systems, it clarifies what kinds of knowledge these AI formalisms truly capture and how they handle external interventions. The approach yields a principled account of causal reasoning, intervention effects, and explanations, with potential to unify relational AI formalisms under a common causal-explanatory semantics.
Abstract
Bayesian networks and causal models provide frameworks for handling queries about external interventions and counterfactuals, enabling tasks that go beyond what probability distributions alone can address. While these formalisms are often informally described as capturing causal knowledge, there is a lack of a formal theory characterizing the type of knowledge required to predict the effects of external interventions. This work introduces the theoretical framework of causal systems to clarify Aristotle's distinction between knowledge that and knowledge why within artificial intelligence. By interpreting existing artificial intelligence technologies as causal systems, it investigates the corresponding types of knowledge. Furthermore, it argues that predicting the effects of external interventions is feasible only with knowledge why, providing a more precise understanding of the knowledge necessary for such tasks.