The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
The seven tools of causal inference, with reflections on machine learning
Open accessAbstract
The kind of causal inference seen in natural human thought can be "algorithmitized" to help produce human-level machine intelligence.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 cited source says what the claim attributes to it.
In the citing paper
“Causal reasoning is foundational to human intelligence, and has been conjectured to be necessary for achieving human level AI (Pearl, 2019).”
From Robust agents learn causal world models (2024) · cites this paper as Pearl, 2019
In the citing paper
“ML can play a role in causal inference [41,340,619], including in the context of policy problems [40,453] and in climate-relevant scenarios such as estimating the effects of temperature on human mortality [356] and the effects of World Bank projects on vegetative cover [883].”
From Tackling climate change with machine learning (2023) · cites this paper as [619]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The central role of the propensity score in observational studies for causal effects
ROSENBAUM, P. R., & RUBIN, D. B. (1983) · Biometrika · doi:10.1093/biomet/70.1.41 · Cited by 31,241
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
(1988) · Cited by 16,582
Self-citationAdvances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
Causality: Models, Reasoning, and Inference
Pearl, J. (2009) · doi:10.1017/cbo9780511803161 · Cited by 11,653
Self-citationCAUSALITY: MODELS, REASONING AND INFERENCE
Hitchcock, C., & Pearl, J. (2001) · The Philosophical Review · doi:10.2307/3182612 · Cited by 4,826
Self-citationCausation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (2001) · doi:10.7551/mitpress/1754.001.0001 · Cited by 4,521
Causality: models, reasoning, and inference
(2000) · Choice Reviews Online · doi:10.5860/choice.38-1494a · Cited by 2,968
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817
Causal diagrams for empirical research
PEARL, J. (1995) · Biometrika · doi:10.1093/biomet/82.4.669 · Cited by 2,355 · cited 2×
“…engine is available, called do - calculus , which predicts the effect of policy interventions whenever feasible, and exits with failure whenever predictions cannot be ascertained with the specified assumptions [Bareinboim and Pearl 2012; Pearl 1995; Shpitser and Pearl 2008; Tian and Pearl 2002].”
Self-citation
Flagged first, then by citations
Research works printed but not linked: 10
- Balke A., 1994, Proceedings of the 12th National Conference on Artificial Intelligence (Seattle, WA, July 31-Aug. 4)
- 10.5555/3086758 · DOI
- Jaber A., 2018, Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence
- Morgan S.L., 2015, Counterfactuals and Causal Inference: Methods and Principles for Social Research (Analytical Methods for Social Research)
- Pearl J., 1988, Morgan Kaufmann
- 10.5555/3202377 · DOI
- Porta M., 2014, Oct. 17
- 10.5555/1248547.1248619 · DOI
- Tian J., 2002, Proceedings of the 18th National Conference on Artificial Intelligence (Edmonton, AB, Canada, July 28-Aug. 1). AAAI Press/MIT Press
- 10.5555/3171642.3171832 · DOI
Cited by
Sorted by citations
Items 101–200 of 659
On the Interpretation of do(x)do(x)
Pearl, J. (2019) · Journal of Causal Inference · doi:10.1515/jci-2019-2002 · Cited by 30
Self-citationGlobal Earthquake Forecasting System (GEFS): The challenges ahead
Mignan, A., Ouillon, G., Sornette, D., & Freund, F. (2021) · The European Physical Journal Special Topics · doi:10.1140/epjst/e2020-000261-8 · Cited by 30
Liu, Y., Ziatdinov, M., & Kalinin, S. V. (2021) · ACS Nano · doi:10.1021/acsnano.1c09059 · Cited by 30
Digital Twin-Enhanced Incident Response for Cyber-Physical Systems
Allison, D., Smith, P., & McLaughlin, K. (2023) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3600160.3600195 · Cited by 30
“These workflow steps can be supported with a DT using a set of well-defined query types – aligned with Pearl’s hierarchy of causal inference [25] – that correspond to identified DT modes of operation.”
BackgroundMethodCausality for Trustworthy Artificial Intelligence: Status, Challenges and Perspectives
Rawal, A., Raglin, A. J., Rawat, D. B., Sadler, B. M., & McCoy, J. (2024) · ACM Computing Surveys · doi:10.1145/3665494 · Cited by 38
“Even though there are related surveys and fundamental studies on causal inference such as the ones from Judea Pearl [42, 107, 116, 117, 120, 121] which provide great overviews.”
Interpretability and Transparency in Artificial Intelligence
Mittelstadt, B. (2022) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780198857815.013.20 · Cited by 31
Towards a Taxonomy for the Opacity of AI Systems
Facchini, A., & Termine, A. (2022) · Studies in Applied Philosophy, Epistemology and Rational Ethics · doi:10.1007/978-3-031-09153-7_7 · Cited by 34
Causal Inference and Bias in Learning Analytics
Weidlich, J., Gašević, D., & Drachsler, H. (2022) · Journal of Learning Analytics · doi:10.18608/jla.2022.7577 · Cited by 27
“…is increasingly recognized in epidemiology, health care, and other fields drawing on machine learning and related technologies (Prosperi et al., 2020; Pearl, 2019), and thus, logically extends to LA, as well as Educational Data Mining and Artificial Intelligence in Education (Baker et al., 2021).”
BackgroundLiu, X., Qian, S., Teo, H., & Ma, W. (2023) · Transportation Science · doi:10.1287/trsc.2022.0195 · Cited by 27
“In recent years, advanced machine learning (ML) models empower us to infer the causal effect from observational data without intrusive experiments (Pearl 2019).”
BackgroundArtificial Intelligence and Machine Learning
Mich, L. (2020) · Springer eBooks · doi:10.1007/978-3-030-05324-6_25-1 · Cited by 31
Facing the Challenges of Developing Fair Risk Scoring Models
Szepannek, G., & Lübke, K. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.681915 · Cited by 30
“Pearl (2019) distinguishes three levels of causal inference as follows: 1) Association : Pr ( y | x ): Seeing: “ What is?, ” that is, the probability of Y (cid:1) y given that we observe X (cid:1) x .”
BackgroundEnabling causality learning in smart factories with hierarchical digital twins
Lippi, M., Martinelli, M., Picone, M., & Zambonelli, F. (2023) · Computers in Industry · doi:10.1016/j.compind.2023.103892 · Cited by 28
Quality of Experience in 6G Networks: Outlook and Challenges
Taha, A. M. (2021) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan10010011 · Cited by 28
“Instead, it is to the autonomous or algorithmized causal inference engines as described in [75].”
BackgroundConibear, L., Reddington, C. L. S., Silver, B. J., Chen, Y., Knote, C., Arnold, S. R., & Spracklen, D. V. (2021) · GeoHealth · doi:10.1029/2021gh000391 · Cited by 26
“The emulators make predictions specific to their training data without explanatory knowledge (Deutsch, 2012; Pearl, 2019).”
Mökander, J., & Schroeder, R. (2021) · AI & Society · doi:10.1007/s00146-021-01222-z · Cited by 48
“Put differently, if our AI-based systems rely solely on curve-fitting and statistical approximation, their inferences will be shallow (Pearl 2019).”
BackgroundTemporal Causal Inference in Wind Turbine SCADA Data Using Deep Learning for Explainable AI
Chatterjee, J., & Dethlefs, N. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1618/2/022022 · Cited by 26
“Actions, intervention and decisions have important consequences in data-driven decision making [7], and causal reasoning is an integral step in achieving human-level machine intelligence.”
BackgroundSun, R., Schiavon, S., Brager, G. S., Arens, E. A., Zhang, H., Parkinson, T., & Zhang, C. (2024) · Building and Environment · doi:10.1016/j.buildenv.2024.111530 · Cited by 25
A Roadmap for Reaching the Potential of Brain‐Derived Computing
Aimone, J. B. (2020) · Advanced Intelligent Systems · doi:10.1002/aisy.202000191 · Cited by 26
A Review of Causal Inference for External Comparator Arm Studies
Rippin, G., Ballarini, N. M., Sanz, H., Largent, J. A., Quinten, C., & Pignatti, F. (2022) · Drug Safety · doi:10.1007/s40264-022-01206-y · Cited by 25
“There are also other causal inference methods like machine learning methods [156] and instrumental variables [157], which are not covered in this publication.”
Health Intervention Evaluation Using Semantic Explainability and Causal Reasoning
Brenas, J. H., & Shaban-Nejad, A. (2020) · IEEE Access · doi:10.1109/access.2020.2964802 · Cited by 24
“Our method provides a semantic backbone to explain and explore questions throughout all three levels (association, intervention, and counterfactuals) of causal hierarchy [32].”
MethodQuantitative modelling of shipping freight rates: developments in the past 20 years
Ke, L., Liu, Q., Ng, A. K. Y., & Shi, W. (2022) · Maritime Policy & Management · doi:10.1080/03088839.2022.2138595 · Cited by 24
“Additionally, despite its weaknesses in parameter estimation and interpretability, theory about causal inference in machine learning is available (e.g., Pearl 2019).”
BackgroundMapping potentials and challenges of choice modelling for social science research
Liebe, U., & Meyerhoff, J. (2021) · Journal of Choice Modelling · doi:10.1016/j.jocm.2021.100270 · Cited by 27
Conibear, L., Reddington, C. L. S., Silver, B. J., Chen, Y., Knote, C., Arnold, S. R., & Spracklen, D. V. (2022) · GeoHealth · doi:10.1029/2021gh000570 · Cited by 24
“The emulators make predictions based on associa-tional knowledge, rather than explanatory knowledge (Deutsch, 2012; Pearl, 2019).”
TinyNS: Platform-aware Neurosymbolic Auto Tiny Machine Learning
Saha, S. S., Sandha, S. S., Aggarwal, M., Wang, B., Han, L., Briseno, J. D. G., & Srivastava, M. B. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3603171 · Cited by 30
“Third , ML models lack transparency and interpretability, with the decision trace (e.g., causation versus correlation) and learned features difficult to understand [63, 109, 114, 121, 147, 176].”
BackgroundMoriarity, D. P., Mengelkoch, S., & Slavich, G. M. (2023) · Brain Behavior and Immunity · doi:10.1016/j.bbi.2023.06.022 · Cited by 24
“The causal hierarchy is typically described as having three levels: association, intervention, and counterfactuals (Pearl and Machenzie, 2018; Pearl, 2019).”
BackgroundPadmanabhan, B., Fang, X., Sahoo, N., & Burton‐Jones, A. (2022) · MIS Quarterly · doi:10.25300/misq/2022/461e1 · Cited by 28
Some models are useful, but how do we know which ones? Towards a unified Bayesian model taxonomy
Bürkner, P., Scholz, M. M., & Radev, S. T. (2023) · Statistics Surveys · doi:10.1214/23-ss145 · Cited by 36
“The mathematical objects that allow for causal analysis are called structural causal models [SCMs, 237] and they comprise structural equations (what we express via P models), causal graphs, as well as interventional and counterfactual logic [239].”
BackgroundSemEval-2020 Task 5: Counterfactual Recognition
Yang, X., Obadinma, S., Zhao, H., Zhang, Q., Matwin, S., & Zhu, X. (2020) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/2020.semeval-1.40 · Cited by 25
The relevance of causation in robotics: A review, categorization, and analysis
Hellström, T. (2021) · Paladyn Journal of Behavioral Robotics · doi:10.1515/pjbr-2021-0017 · Cited by 30
“…happened if I had knocked on the closed door instead of driving against it?, ” and “ what would have been the advantages that?. ” This kind of causal reasoning is placed at the top of the three - level causal hierarchy by Judea Pearl, above the interven - tional and associational levels [ 8 ] .”
BackgroundData-driven root cause analysis via causal discovery using time-to-event data
Mbogu, H. M., & Nicholson, C. (2024) · Computers & Industrial Engineering · doi:10.1016/j.cie.2024.109974 · Cited by 22
Modelling GDPR-Compliant Explanations for Trustworthy AI
Sovrano, F., Vitali, F., & Palmirani, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58957-8_16 · Cited by 22
“In fact, Description Logic can be used for reasoning over descriptions, Causal Inference [20] for reasoning over causations, Defeasible Deontic Logic for reasoning over justifications.”
Online Child Sexual Exploitation: A New MIS Challenge
Demetis, D. S., & Kietzmann, J. (2021) · Journal of the Association for Information Systems · doi:10.17705/1jais.00652 · Cited by 26
“, 2016), machine learning (Pearl, 2019), or AI-based chatbots (Androutsopoulou et al.”
BackgroundZhong, W., & Du, L. (2023) · Sustainability · doi:10.3390/su15042944 · Cited by 22
Khuat, T. T., Kedziora, D. J., & Gabryś, B. (2023) · Foundations and Trends® in Human–Computer Interaction · doi:10.1561/1100000091 · Cited by 45
Statistical Modeling: The Three Cultures
Daoud, A., & Dubhashi, D. (2023) · Harvard Data Science Review · doi:10.1162/99608f92.89f6fe66 · Cited by 31
Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning
Li, M., Feng, F., Zhang, H., He, X., Zhu, F., & Chua, T. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.5 · Cited by 21
“Taking the hypothetical question in Figure 1 as an example, an ideal L2I should recognize the target variable ( finished goods in 2019 ), identify the corresponding fact ( $133,682 ), and replace the fact with the assumed value ( $132,935 ).”
BackgroundSCGAN: Sparse CounterGAN for Counterfactual Explanations in Breast Cancer Prediction
Zhou, S., Islam, U. J., Pfeiffer, N., Banerjee, I., Patel, B., & Iquebal, A. S. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3333788 · Cited by 26
“Counterfactual refers to a statement or situation describing an alternative outcome or event that could have occurred but did not actually happen [21], [28].”
BackgroundIntercultural Computing Education: Toward Justice Across Difference
Arawjo, I., & Mogos, A. (2021) · ACM Transactions on Computing Education · doi:10.1145/3458037 · Cited by 24
From atomically resolved imaging to generative and causal models
Kalinin, S. V., Ghosh, A., Vasudevan, R. K., & Ziatdinov, M. A. (2022) · Nature Physics · doi:10.1038/s41567-022-01666-0 · Cited by 20
Xu, P., Liu, Q., Bao, H., Zhang, R., Gu, L., & Wang, G. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3368960 · Cited by 19
“In terms of interpretable analysis, there are methods based on visualization [28], [29], methods based on knowledge representation [30] and methods based on causal inference [31], [32].”
MethodThe dispositional effects of holidays on investor sentiment: Therapeutic and hygienic
Liu, Q., Huang, M., Zhao, L., & Lee, W.-S. (2023) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2023.100358 · Cited by 19
Modeling Approaches for Residential Energy Consumption: A Literature Review
Nacht, T., Pratter, R., Ganglbauer, J., Schibline, A., Aguayo-Mendoza, A., Fragkos, P. F., & Zisarou, E. (2023) · Climate · doi:10.3390/cli11090184 · Cited by 21
Body condition loss during the dry period: Insights from feeding behavior studies
Daros, R. R., Havekes, C. D., & DeVries, T. J. (2021) · Journal of Dairy Science · doi:10.3168/jds.2020-19481 · Cited by 19
“Mediation analysis may be applied to longitudinal observational data to disentangle mechanisms of cause-effect, given that the models used represent a plausible biological rationale (Pearl, 2019).”
BackgroundToward a Theory of Causation for Interpreting Neural Code Models
Nader Palacio, D., Velasco, A., Cooper, N., Rodriguez, A., Moran, K., & Poshyvanyk, D. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3379943 · Cited by 18
“In fact, the back-door criterion uses a graphical mechanism known as d-separation , which facilitates the demonstration that causal models have testable implications in the data they generate [75].”
BackgroundSankaran, S., & Markopoulos, P. (2021) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3450613.3456820 · Cited by 18
“In his pioneering work, Pearl has argued that causal reasoning is an indispensable part of human thought and provides a structured computational framework and set of tools for causal inference [44].”
BackgroundCIPCaD-Bench: Continuous Industrial Process datasets for benchmarking Causal Discovery methods
Menegozzo, G., Dall’Alba, D., & Fiorini, P. (2022) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49997.2022.9926420 · Cited by 22
“SCM is not limited in recognizing patterns but allows to reason about the underlying structure beyond the observed correlation, such as simulating interventions with do-calculus or assuming hypothetical changes in the environments with counterfactuals [6].”
BackgroundVehicular Traffic Flow Reconstruction Analysis to Mitigate Scenarios With Large City Changes
Bellini, P., Bilotta, S., Palesi, L. A. I., Nesi, P., & Pantaleo, G. (2022) · IEEE Access · doi:10.1109/access.2022.3229183 · Cited by 18
“The architectural aspects of a future scenario traffic analysis tool should be also addressed [38].”
BackgroundGani, M. O., Kethireddy, S., Adib, R., Hasan, U., Griffin, P. M., & Adibuzzaman, M. (2022) · SSRN Electronic Journal · doi:10.1016/j.artmed.2023.102493 · Cited by 23
Time series causal relationships discovery through feature importance and ensemble models
Castro, M., Júnior, P. R. M., Soriano-Vargas, A., Werneck, R. D. O., Gonçalves, M. M., Filho, L. L., Moura, R., Zampieri, M. F., Linares, O. C., Ferreira, V. H. D. S., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-37929-w · Cited by 20
Risk, Trust, and Bias: Causal Regulators of Biometric-Enabled Decision Support
Lai, K., Oliveira, H. C. R., Hou, M., Yanushkevich, S. N., & Shmerko, V. P. (2020) · IEEE Access · doi:10.1109/access.2020.3015855 · Cited by 18
“Our contribution and goal are achieved in conjunction with the following results: − Framework of intelligent DSS ; we adopted Haykin’s fundamental results on cognitive systems [30], in particular, in modeling the DSS for multi-state intelligent checkpoint; − Taxonomical view for causal R-T-B inference; we adopted, for…”
BackgroundMethodInfluentialSakai, O., Kawaguchi, S., & Murakami, T. (2022) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ac76fa · Cited by 17
Training a Resilient Q-network against Observational Interference
Yang, C.-H. H., Hung, I.-T. D., Ouyang, Y., & Chen, P. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20862 · Cited by 34
“…Inference for Generative Reinforcement Learning: Causal inference (Greenland, Pearl, and Robins 1999; Pearl 2009; Pearl, Glymour, and Jewell 2016; Pearl 2019; Robins, Rotnitzky, and Zhao 1995) has been used to empower the learning process under noisy observation and have better interpretability…”
BackgroundMethodHan, Y., Li, V. O. K., Lam, J. C. K., & Pollitt, M. G. (2020) · Environmental Science & Policy · doi:10.1016/j.envsci.2020.10.015 · Cited by 17
Incorporating prior knowledge from counterfactuals into knowledge graph reasoning
Wang, Z., Li, L., Zeng, D. D., & Wu, X. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107035 · Cited by 17
Desiderata for Representation Learning: A Causal PerspectivePreprint
Wang, Z., & Jordan, M. I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03795 · Cited by 75
“Reducing the counterfactual quantity pns to the lower bound in Lemma 4 has climbed down one level of the ladder of causation (Pearl, 2019a); we have converted a counterfactual quantity (level three) to one with interventional distributions (level two).”
BackgroundMethodInfluentialSchwartz, M. H., Ries, A. J., & Georgiadis, A. G. (2022) · Scientific Reports · doi:10.1038/s41598-022-11875-5 · Cited by 16
CausalRD: A Causal View of Rumor Detection via Eliminating Popularity and Conformity Biases
Zhang, W., Zhong, T., Li, C., Zhang, K., & Zhou, F. (2022) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom48880.2022.9796678 · Cited by 17
Li, L., Yu, H., & Kunc, M. H. (2023) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2023.122936 · Cited by 16
“Along with many research efforts in the causal inference literature (Abadie, 2005; Pearl, 2019; Schumann et al., 2021), recent works on DMLDiD show that embedding ML techniques into the DiD estimator advances the estimator of causal inferences in the presence of high-dimensional cases (Chernozhukov…”
Developing a “Sense of Agency” in IoT Systems: Preliminary Experiments in a Smart Home Scenario
Lippi, M., Mariani, S., & Zambonelli, F. (2021) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9431003 · Cited by 16
“With reference to the “causal hierarchy” (or “ladder of causation”) introduced by Pearl [11], [12], the fact that the agent knows what it can control with its actuators makes the act of learning such causal relations not simply the learning of an association (level 1 of the ladder of causation P (y|x)) but the learnin…”
BackgroundMethodCausal inference in regression: advice to authors
Bulbulia, J. A., Schjoedt, U., Shaver, J. H., Sosis, R. H., & Wildman, W. J. (2021) · Religion Brain & Behavior · doi:10.1080/2153599x.2021.2001259 · Cited by 15
“We recommend that researchers use directed acyclic graphs (DAGs) to systematically identify and avoid collider (and other) forms of confounding (McElreath, 2020; Pearl, 2009; Pearl, 2019).”
BackgroundMethodChipidza, W., & Yan, J. (2022) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.24705 · Cited by 16
“Further, explainable machine learning models help in demonstrating the effect of a given intervention, in our case flagging (Pearl, 2019).”
BackgroundMethodInfluentialBeyond correlation: A causality-driven model for indoor temperature control
Mun, J., & Park, C. S. (2025) · Energy and Buildings · doi:10.1016/j.enbuild.2025.115739 · Cited by 17
Comorbidities and medical history essential for mortality prediction in critically ill patients
Forte, J. C., & van der Horst, I. C. C. (2019) · The Lancet Digital Health · doi:10.1016/s2589-7500(19)30030-5 · Cited by 15
Belzak, W. C. M. (2022) · Educational Measurement Issues and Practice · doi:10.1111/emip.12486 · Cited by 21
A Network Analysis of Children’s Emerging Place-Value Concepts
Bower, C. A., Mix, K. S., Yuan, L., & Smith, L. B. (2022) · Psychological Science · doi:10.1177/09567976211070242 · Cited by 15
“However, considerable biomedical research has made clear that prediction accuracy, validity, and intervenable roles in causal pathways are often at best complexly related (e.g., Hussein et al., 2018; Pearl, 2019).”
BackgroundA workflow for causal inference in cross-cultural psychology
Bulbulia, J. A. (2022) · Religion Brain & Behavior · doi:10.1080/2153599x.2022.2070245 · Cited by 15
“Causal inference requires causal assumptions (Bulbulia et al., 2021; McElreath, 2020; Pearl, 2009, 2019; VanderWeele, 2015; VanderWeele et al., 2020).”
BackgroundUnintentional Action Localization via Counterfactual Examples
Xu, J., Chen, G., Lu, J., & Zhou, J. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3166278 · Cited by 14
Why artificial intelligence needs to understand consequences
Savage, N. (2023) · Nature · doi:10.1038/d41586-023-00577-1 · Cited by 14
Furia, C. A., Torkar, R., & Feldt, R. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3611667 · Cited by 14
Jaradat, S., Nayak, R., Paz, A., & Elhenawy, M. M. Z. (2024) · Algorithms · doi:10.3390/a17070284 · Cited by 17
Causality measures and analysis: A rough set framework
Yao, N., Miao, D., Witold Pedrycz, C., Zhang, H., & Zhang, Z. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.06.004 · Cited by 14
“…Tenenbaum, and Gershman 2017) as one of the core ingredients for building AI (artificial intel- igence) systems with more human-like learning and thought, and he machine learning systems in Pearl (2019) that can reason about nterventions and counterfactuals can serve as the basis for strong I.”
BackgroundFarahmand, F. (2021) · IEEE Security & Privacy · doi:10.1109/msec.2021.3103460 · Cited by 14
Sahoh, B., Haruehansapong, K., & Kliangkhlao, M. (2022) · IEEE Access · doi:10.1109/access.2022.3155118 · Cited by 16
“Human thought is encoded in the form of assumptions based on human-like interpretation, as proposed by Pearl [32].”
BackgroundDirections for Explainable Knowledge-Enabled Systems
Chari, S., Gruen, D. M., Seneviratne, O. W., & McGuinness, D. L. (2020) · Studies on the semantic web · doi:10.3233/ssw200022 · Cited by 13
Zhang, Y., Isaacs, R., Yue, Y., Yang, J., Zhang, L., & Vigfússon, Ý. (2023) · ACM Symposium on Cloud Computing (SoCC) · doi:10.1145/3620678.3624787 · Cited by 16
“Conventional statistical and machine learning tools, relying on observational data, fall short in answering these queries due to their associative nature [60] and susceptibility to confounding variables [59].”
BackgroundUse of AI in conservation and for understanding climate change
Khaleel, M., Murtaza, N., Mueen, Q. H., Ahmad, S. A., & Qadri, S. F. I. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-24001-0.00013-0 · Cited by 14
Next Generation Computing and Communication Hub for First Responders in Smart Cities
Shaposhnyk, O. A., Lai, K., Wolbring, G., Shmerko, V. P., & Yanushkevich, S. N. (2024) · Sensors · doi:10.3390/s24072366 · Cited by 13
“In our work, we refer to an approach known as causal reasoning and Bayesian networks [67].”
BackgroundMethodModel-Agnostic Causal Embedding Learning for Counterfactually Group-Fair Recommendation
Zhang, X., Shi, T., Xu, J., Dong, Z., & Wen, J.-R. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3424906 · Cited by 13
Mokhtarian, P. L. (2024) · Transportation Research Part A Policy and Practice · doi:10.1016/j.tra.2024.104254 · Cited by 13
Landing AI on Networks: An Equipment Vendor Viewpoint on Autonomous Driving Networks
Rossi, D., & Zhang, L. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3169988 · Cited by 16
Key challenges and developments in wildlife ecological risk assessment: Problem formulation
Sample, B. E., Johnson, M. S., Hull, R. N., Kapustka, L. A., Landis, W. G., Murphy, C. A., Sorensen, M. T., Mann, G. S., Gust, K. A., Mayfield, D. B., et al. (2022) · Integrated Environmental Assessment and Management · doi:10.1002/ieam.4710 · Cited by 12
“To the extent pos - sible, data acquisition should consider evidence to support a determination of causation (see Pearl, 2019).”
BackgroundCausalOps - Towards an Industrial Lifecycle for Causal Probabilistic Graphical Models
Maier, R., Schlattl, A., Guess, T., & Mottok, J. (2023) · Information and Software Technology · doi:10.1016/j.infsof.2024.107520 · Cited by 9
“Software tools like an inference engine (Pearl, 2019; H¨unermund and Bareinboim, 2023) are essential, enabling components of CausalOps.”
MethodQuintana, R. (2020) · Sociological Methods & Research · doi:10.1177/0049124120926208 · Cited by 13
“Causal graphs encode these assumptions in an explicit manner that is a key requirement for transparency and testability (Pearl 2019).”
BackgroundKim, D., & Shin, S.-W. (2021) · International Journal of Strategic Property Management · doi:10.3846/ijspm.2021.15129 · Cited by 14
“RF cannot be applied to non-i.i.d. data, inclusive of panel datasets (Pearl, 2019; Steinwart et al., 2009).”
BackgroundRieckmann, A., Dworzyński, P., Arras, L., Lapuschkin, S., Samek, W., Arah, O. A., Rod, N. H., & Ekstrøm, C. T. (2022) · International Journal of Epidemiology · doi:10.1093/ije/dyac078 · Cited by 12
Treatment Learning Causal Transformer for Noisy Image Classification
Yang, C.-H. H., Hung, D. I.-T., Liu, Y.-C., & Chen, P. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00608 · Cited by 12
“Causation [Pearl, 2019, 2009] indicates that one event is the result of the occurrence of the other event; i.e., there is a causal relationship between the two events.”
BackgroundMethodInfluentialCausality in Islamic marketing research
Kadirov, D., Bahiss, I., & Bardakçı, A. (2020) · Journal of Islamic marketing · doi:10.1108/jima-05-2019-0113 · Cited by 19
Towards a unified framework to study causality in Earth–life systems
Dolby, G. (2021) · Molecular Ecology · doi:10.1111/mec.16142 · Cited by 9
“Causal theory has since been applied widely across disciplines, for example within the social sciences especially when variables are intangible or difficult to measure (e.g., intelligence; see references in Pearl, 1995), as well as within artificial intelligence (Pearl, 2019).”
BackgroundEmission Sector Impacts on Air Quality and Public Health in China From 2010 to 2020
Conibear, L., Reddington, C. L. S., Silver, B. J., Chen, Y., Arnold, S. R., & Spracklen, D. V. (2022) · GeoHealth · doi:10.1029/2021gh000567 · Cited by 11
“The emulators were specific to their training data, and predicted based on associational knowledge, rather than explanatory knowledge (Deutsch, 2012; Pearl, 2019).”
Causal Inference Q-Network: Toward Resilient Reinforcement LearningPreprint
Yang, C.-H. H., Hung, I.-T. D., Ouyang, Y., & Chen, P. (2021) · arXiv (Cornell University) · Cited by 12
Causal Machine Learning and Business Decision MakingPreprint
Hünermund, P., Kaminski, J., & Schmitt, C. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3867326 · Cited by 15
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAPreprint
Lachapelle, S., López, P. R., Sharma, Y., Everett, K., Priol, R. L., Lacoste, A., & Lacoste-Julien, S. (2021) · CLEaR · doi:10.48550/arxiv.2107.10098 · Cited by 211
“It has been proposed that causal reasoning will be central to move modern machine learning algorithms beyond their current shortcomings, such as their lack of robustness, transferability and interpretability (Pearl, 2019; Schölkopf, 2019; Schölkopf et al., 2021; Goyal and Bengio, 2021).”
BackgroundScheenstra, B., Bruninx, A., van Daalen, F., Stahl, N., Latuapon, E., Imkamp, M. S. V., Ippel, L., Duijsings-Mahangi, S., Smits, D., Townend, D. M. R., et al. (2022) · JMIR Cardio · doi:10.2196/37437 · Cited by 12
“In terms of statistical modelling techniques, we plan to use (1) regression models; (2) Bayesian networks, which suit well to causal graphs and provide an intuitive and explainable framework where data can be combined with expert knowledge [28]; and (3) neural networks or deep learning, which have gained popularity in…”
MethodTowards the intelligent era of spatial analysis and modeling
Zhu, D., Gao, S., & Cao, G. (2022) · ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (GeoAI) · doi:10.1145/3557918.3565863 · Cited by 11
“Moreover, the inclusion of causal inference capabilities including association, intervention and counterfactuals from econometrics would further enhance the intelligence of spatial analytics [13].”
BackgroundShao, Z., Zhang, Y., Yang, S., & Zhao, W. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3431082 · Cited by 11
“…causality from spurious correlations, thereby fundamentally solving the problem of generalization due to differences in data distribution [14], which has achieved excellent performance in many fields including computer vision [15], [16], healthcare [17], [18], recommender system [19],…”
BackgroundA Lightweight Framework for Measurement Causality Extraction and FDIA Localization
Wu, S., Yang, C., Wang, J., & Shi, D. (2025) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2025.3548097 · Cited by 11
“Several studies have suggested that the generalization and interpretability problems of correlation-based learning are partly due to the lack of causal formalism [26], [27], [28].”
Sahoh, B., & Choksuriwong, A. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03317-3 · Cited by 11
“And (2) the model must imitate the understanding of essential emergency event characters in the ways of human logical assumptions (Pearl 2019).”
BackgroundKliangkhlao, M., Limsiroratana, S., & Sahoh, B. (2022) · IEEE Access · doi:10.1109/access.2022.3199353 · Cited by 11
“CBNs are a human-like intelligent framework that encodes experience and knowledge based on cause-and-effect assumptions [27], [28].”
BackgroundA multi-sector causal network of urban heat vulnerability coupling with mitigation
Yang, S., Ding, L., & Prasad, D. K. (2022) · Building and Environment · doi:10.1016/j.buildenv.2022.109746 · Cited by 11
Exploratory pharmacovigilance with machine learning in big patient data: A focused scoping review
Kaas‐Hansen, B. S., Gentile, S., Caioli, A., & Andersen, S. E. (2022) · Basic & Clinical Pharmacology & Toxicology · doi:10.1111/bcpt.13828 · Cited by 12
“16 When appropriate, however, they need large (or information rich) data sets to be useful.”
Background
Metadata
- Authors
- Pearl, J.
- Affiliations
- University of California, Los Angeles (US)
- Corresponding author
- Pearl, Judea
- Venue
- Communications of the ACM
- Published
- 2019-02-21
- Volume
- 62
- Issue
- 3
- Pages
- 54-60
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2917286209
- Cited by
- 659
- References
- 46
- Citations by year
- 2026: 78 · 2025: 81 · 2024: 91 · 2023: 98 · 2022: 102 · 2021: 118 · 2020: 67 · 2019: 24
- FWCI
- 35.88
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- Funders
- National Science Foundation (1704932, 1302448, 1527490)
- Defense Advanced Research Projects Agency (#W911NF-16-057)
- University of California, Los Angeles
- Advanced Research Projects Agency
- Office of Naval Research (N00014-17-S-B001, N00014)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Keywords
- causal inference, causal discovery, causal discovery algorithms, machine learning, philosophy of causation
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
