Reasoning about causality in games
Open accessAbstract
Causal reasoning and game-theoretic reasoning are fundamental topics in artificial intelligence, among many other disciplines: this paper is concerned with their intersection. Despite their importance, a formal framework that supports both these forms of reasoning has, until now, been lacking. We offer a solution in the form of (structural) causal games, which can be seen as extending Pearl's causal hierarchy to the game-theoretic domain, or as extending Koller and Milch's multi-agent influence diagrams to the causal domain. We then consider three key questions: How can the (causal) dependencies in games – either between variables, or between strategies – be modelled in a uniform, principled manner? How may causal queries be computed in causal games, and what assumptions does this require? How do causal games compare to existing formalisms?
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?
Structural causal games integrate the causal hierarchy with game theory and allow inferring a model's self-consciousness from its behavior.
“SCGs integrate causal hierarchy (Pearl & Mackenzie, 2018) with game theory (Owen, 2013), allowing us to infer a model's self-consciousness from its behavior (Hammond et al., 2023;Ward et al., 2024a,b).”
From From Imitation to Introspection: Probing Self-Consciousness in Language Models (2025) · cites this paper as Hammond et al., 2023
Cites
Causal Inference Using Potential Outcomes: Design, Modeling, Decisions
Rubin, D. B. (2005) · Journal of the American Statistical Association · doi:10.1198/016214504000001880 · Cited by 2,173 · see citing works
Introduction to Statistical Relational Learning
(2007) · doi:10.7551/mitpress/7432.001.0001 · Cited by 1,643 · see citing works
Cooperative Inverse Reinforcement Learning
Hadfield-Menell, D., Dragan, A., Abbeel, P., & Russell, S. (2016) · arXiv · doi:10.48550/arxiv.1606.03137 · Cited by 413 · see citing works
Avoiding Discrimination through Causal Reasoning
Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., & Schölkopf, B. (2017) · arXiv · doi:10.48550/arxiv.1706.02744 · Cited by 358 · see citing works
Influence Diagrams for Causal Modelling and Inference
Dawid, A. P. (2002) · International Statistical Review · doi:10.1111/j.1751-5823.2002.tb00354.x · Cited by 230 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Causal reasoning: Charting a revolutionary course for next-generation AI-native wireless networks
Thomas, C. K., Chaccour, C., Saad, W., Debbah, M., & Hong, C. S. (2024) · IEEE Vehicular Technology Magazine · doi:10.1109/mvt.2024.3359357 · Cited by 46 · see citing works
Kenton, Z., Kumar, R., Farquhar, S., Richens, J., MacDermott, M., & Everitt, T. (2023) · Artificial Intelligence · doi:10.1016/j.artint.2023.103963 · Cited by 17 · see citing works
Self-citationFrom Imitation to Introspection: Probing Self-Consciousness in Language Models
Chen, S., Yu, S., Zhao, S., & Lu, C. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.392 · Cited by 4 · see citing works
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
de Witt, C. S., Krawiecka, K., Krawczuk, I., Hagag, B., Anderson, W. L., Belcak, P., Bucknall, B., Cai, X., Chopra, A., Cohen, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2505.02077 · Cited by 2 · see citing works
“To secure interacting AI under worst-case assumptions, we need robust threat attribution mechanisms that integrate behavioral logs, cryptographic provenance, and causal inference techniques (Hammond et al., 2023).”
- Authors
- Hammond, L., Fox, J., Everitt, T., Carey, R., Abate, A., & Wooldridge, M.
- Affiliations
- University of Oxford (GB)
- Google DeepMind (United Kingdom) (GB)
- Corresponding author
- Hammond, Lewis
- Fox, James
- Venue
- Artificial Intelligence
- Publisher
- Elsevier BV
- Published
- 2023-07
- Volume
- 320
- Pages
- 103919
- ISSN
- 0004-3702 (ISSN-L)
- OpenAlex
- W4362606359
- Cited by
- 13
- References
- 5
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 3 · 2023: 2
- FWCI
- 1.12
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Artificial Intelligence (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- PhilPapers (PhilPapers Foundation) (submittedVersion)
- Oxford University Research Archive (ORA) (University of Oxford) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- UK Research and Innovation
- Engineering and Physical Sciences Research Council (EP/S024050/1, EP/W002949/1, 2218880)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Social Sciences › Decision Sciences › Management Science and Operations Research › Game Theory and Applications
- Keywords
- causal reasoning, game-theoretic reasoning, structural causal models, causal hierarchy
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
