On Pearl’s Hierarchy and the Foundations of Causal Inference
Abstract
chapter Share on On Pearl's Hierarchy and the Foundations of Causal Inference Authors: Elias Bareinboim Columbia University Columbia UniversitySearch about this author , Juan D. Correa Columbia University Columbia UniversitySearch about this author , Duligur Ibeling Stanford University Stanford UniversitySearch about this author , Thomas Icard Stanford University Stanford UniversitySearch about this author Authors Info & Claims Probabilistic and Causal Inference: The Works of Judea PearlFebruary 2022 Pages 507–556https://doi.org/10.1145/3501714.3501743Online:04 March 2022Publication History 0citation26DownloadsMetricsTotal Citations0Total Downloads26Last 12 Months26Last 6 weeks6 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The causal hierarchy theorem states that an oracle for L1 queries (observational) is almost always insufficient to evaluate all L2 queries (interventional).
“We can compare to the causal hierarchy theorem (CHT) (Bareinboim et al., 2022), which states that an oracle for L1 queries (observational) is almost always insufficient to evaluate all L2 queries (interventional).”
From Robust agents learn causal world models (2024) · cites this paper as Bareinboim et al., 2022
The necessity of causal models for solving causal inference tasks has been established.
“And while the necessity of causal models for solving causal inference tasks has been established (Bareinboim et al., 2022), their role in decision tasks such as classification and reinforcement learning is less clear.”
From Robust agents learn causal world models (2024) · cites this paper as Bareinboim et al., 2022
The CHT is concerned with the collapse (or lack thereof) of the causal hierarchy; for example, that observational data is insufficient for identifying all causal queries.
“Secondly, the CHT is concerned with the collapse (or lack thereof) of the causal hierarchy. For example, that observational data is insufficient for identifying all causal queries.”
From Robust agents learn causal world models (2024) · cites this paper as Bareinboim et al., 2022
The approximate world model P̂ is identifiable given the agent's policy and the paper's assumptions.
“Formally, the approximate world model ˆ P ss ′ ( a ) is identifiable given the agent's policy and our assumptions (see for example Bareinboim et al. (2022)).”
From General agents contain world models (2025) · cites this paper as Bareinboim et al. (2022)
Different agent capabilities, such as domain or task generalization, provably require different degrees of causal knowledge.
“This hints at an agential version of Pearl's causal hierarchy (Bareinboim et al., 2022), where different agent capabilities (like domain or task generalization) provably require different degrees of causal knowledge.”
From General agents contain world models (2025) · cites this paper as Bareinboim et al., 2022
The citation lists haven’t been fetched yet
References 51 · Cited by 174
- Authors
- Bareinboim, E., Correa, J. D., Ibeling, D., & Icard, T.
- Affiliations
- Columbia University (US)
- Stanford University (US)
- ORCID
- Correa, Juan D.
- Venue
- Probabilistic and Causal Inference
- Publisher
- ACM
- Published
- 2022-02-28
- Pages
- 507-556
- OpenAlex
- W4220858968
- Cited by
- 174
- References
- 51
- Citations by year
- 2026: 35 · 2025: 41 · 2024: 33 · 2023: 37 · 2022: 21 · 2021: 7
- FWCI
- 61.28
- Type
- book chapter
- Language
- en
- Open access
- closed
- Locations
- ACM eBooks (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Philosophy and History of Science
- Keywords
- causal inference, causal discovery, causal models, Judea Pearl
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
