On the Granularity of Causal Effect Identifiability

Yizuo Chen, Adnan Darwiche
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, PMLR 337:1181-1199, 2026.

Abstract

The classical notion of causal effect identifiability is defined in terms of treatment and outcome variables. In this paper, we consider the identifiability of state-based causal effects: how an intervention on a particular _state_ of treatment variables affects a particular _state_ of outcome variables. We demonstrate that state-based causal effects may be identifiable even when variable-based causal effects may not. Moreover, we show that this separation occurs only when additional knowledge — such as context-specific independencies — is available. We further examine knowledge that constrains the states of variables, and show that such knowledge can improve both variable-based and state-based identifiability when combined with other knowledge such as context-specific independencies. We finally propose an approach for identifying causal effects under these additional constraints, and conduct empirical studies to further illustrate the separations between the two levels of identifiability.

Cite this Paper

BibTeX
@InProceedings{pmlr-v337-chen26c, title = {On the Granularity of Causal Effect Identifiability}, author = {Chen, Yizuo and Darwiche, Adnan}, booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence}, pages = {1181--1199}, year = {2026}, editor = {Perković, Emilija and Malinsky, Daniel}, volume = {337}, series = {Proceedings of Machine Learning Research}, month = {17--21 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/chen26c/chen26c.pdf}, url = {https://proceedings.mlr.press/v337/chen26c.html}, abstract = {The classical notion of causal effect identifiability is defined in terms of treatment and outcome variables. In this paper, we consider the identifiability of state-based causal effects: how an intervention on a particular _state_ of treatment variables affects a particular _state_ of outcome variables. We demonstrate that state-based causal effects may be identifiable even when variable-based causal effects may not. Moreover, we show that this separation occurs only when additional knowledge — such as context-specific independencies — is available. We further examine knowledge that constrains the states of variables, and show that such knowledge can improve both variable-based and state-based identifiability when combined with other knowledge such as context-specific independencies. We finally propose an approach for identifying causal effects under these additional constraints, and conduct empirical studies to further illustrate the separations between the two levels of identifiability.} }
Endnote
%0 Conference Paper %T On the Granularity of Causal Effect Identifiability %A Yizuo Chen %A Adnan Darwiche %B Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Emilija Perković %E Daniel Malinsky %F pmlr-v337-chen26c %I PMLR %P 1181--1199 %U https://proceedings.mlr.press/v337/chen26c.html %V 337 %X The classical notion of causal effect identifiability is defined in terms of treatment and outcome variables. In this paper, we consider the identifiability of state-based causal effects: how an intervention on a particular _state_ of treatment variables affects a particular _state_ of outcome variables. We demonstrate that state-based causal effects may be identifiable even when variable-based causal effects may not. Moreover, we show that this separation occurs only when additional knowledge — such as context-specific independencies — is available. We further examine knowledge that constrains the states of variables, and show that such knowledge can improve both variable-based and state-based identifiability when combined with other knowledge such as context-specific independencies. We finally propose an approach for identifying causal effects under these additional constraints, and conduct empirical studies to further illustrate the separations between the two levels of identifiability.
APA
Chen, Y. & Darwiche, A.. (2026). On the Granularity of Causal Effect Identifiability. Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 337:1181-1199 Available from https://proceedings.mlr.press/v337/chen26c.html.

Related Material