The paper introduces causal foundation models that can bound the effects of interventions and counterfactuals using only observational data. It defines a canonical prior with full support over structural causal models with discrete observables, enabling the translation of counterfactual bounding into learning distributions over functions that map data and structural assumptions to causal queries. This approach extends causal foundational modelling to partially-identifiable causal effects, where unobserved confounding leads to multiple compatible values for the effect.
By Alexis Bellot, Anish Dhir
arXiv:2505. 15274v4 Announce Type: replace Abstract: Probabilities of causation (PoCs) are fundamental quantities for counterfactual analysis and personalized decision making.
By Xin Shu, Shuai Wang, Ang Li
arXiv:2606. 19361v1 Announce Type: cross Abstract: Identification conditions describe the computability of a target query or parameter of interest as a function of the type and amount of information available.
By Lucius E. J. Bynum, Rajesh Ranganath, Kyunghyun Cho
The paper tackles selecting a cost‑constrained set of experiments that most effectively tighten bounds on a partially identifiable causal query. It formalizes this as the NP‑hard max‑potency problem, introduces efficient graphical pruning rules to reduce the search space, and demonstrates the approach on synthetic graphs and real NHANES data to estimate the effect of physical activity on diabetes.
By Tobias Maringgele, Jalal Etesami
The paper studies observational dominance among causal structures with latent variables, defining one structure as dominating another if it can realize all distributions that the other can over the same visible variables. It provides a full characterization of this dominance partial order for three visible variables and a partial one for four, and shows that many equivalence classes are distinguished by nontrivial inequality constraints similar to Bell or instrumental inequalities. The authors also demonstrate that constraint‑based causal discovery algorithms relying only on conditional independence are much less powerful than those incorporating nested Markov and inequality constraints.
By Marina Maciel Ansanelli, Elie Wolfe, Robert W. Spekkens
arXiv:2602. 14972v2 Announce Type: replace Abstract: Estimating causal quantities traditionally relies on bespoke estimators tailored to specific assumptions.
By Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, Bernhard Sch\"olkopf
arXiv:2608. 12657v1 Announce Type: new Abstract: Probabilities of causation (PoCs) characterize individual causal responses that cannot be directly observed and therefore generally require partial identification.
By Xin Shu, Zhen Lei, Ang Li
arXiv:2602. 16481v2 Announce Type: replace Abstract: Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of interventions.
By Zihao Li, Fabrizio Russo
arXiv:2607. 11816v1 Announce Type: new Abstract: Causal discovery algorithms learn a network that describes the causal dependencies among random variables.
By Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler
The paper introduces a formal framework that uses symmetries in data to keep causal mechanisms invariant, providing a simple and general mathematical language for causal reasoning. It outlines how to describe models and queries, and presents strategies for rigorously identifying causal effects from data within this framework. The approach reproduces known results for IID data and extends causal analysis to non‑IID settings, complex queries beyond do‑ or soft‑interventions, and incorporates missing data, transfer, and robustness considerations.
By Martin Rabel, Jakob Runge
arXiv:2606. 19594v1 Announce Type: new Abstract: Causal abstractions formalize when a high-level structural causal model (SCM) captures the interventional behavior of a lower-level SCM.
By Th\'eo Saulus, Simon Lacoste-Julien, Dhanya Sridhar
CausalProfiler is a synthetic benchmark generator designed to evaluate causal machine learning (Causal ML) methods more rigorously and transparently. It randomly samples causal models, data, queries, and ground truths based on explicit design choices across observation, intervention, and counterfactual reasoning levels, providing coverage guarantees and transparent assumptions. The authors demonstrate its utility by testing several state‑of‑the‑art methods under diverse conditions, both within and outside the identification regime, highlighting the insights CausalProfiler can reveal.
By Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Marc Schoenauer, \"Ozg\"ur \c{S}im\c{s}ek