BeClaude
Research2026-05-06

The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy

Source: Arxiv CS.AI

arXiv:2605.02177v1 Announce Type: cross Abstract: Pearl's causal hierarchy shows that observational, interventional, and counterfactual queries are qualitatively distinct. We ask a quantitative version of this question: how many additional bits are needed to specify higher-rung causal answers once...

arxivpapers