SOURCE-LINKED INTELLIGENCE

Partial Identification under Causal Orders by Linear Programming

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Non-parametric (partial) identification of counterfactual queries typically relies on a fully specified causal graph. Motivated by settings with incomplete domain knowledge, we challenge this requirement by leveraging structural assumptions that are inherently implied by the query itself. We show that any counterfactual inquiry induces a, mostly partial, topological ordering over relevant variables, which, in turn, enables an explicit query parametrisation reducing the identification task to a linear program. This allows bounding arbitrary counterfactual and nested counterfactual queries. Our

Read original source ↗ Open in workspace

recordType

paper

region

Global