{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T17:04:48Z","timestamp":1779469488881,"version":"3.53.1"},"reference-count":57,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UNAM-DGAPA","award":["IT102424"],"award-info":[{"award-number":["IT102424"]}]},{"name":"AI Consortium\u2014CIMAT-CONAHCYT"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>We investigate how causal DAG learning algorithms and structural assumptions influence counterfactual decision safety. Four structure learning regimes are compared: expert-guided edge-constrained HC+BIC, unconstrained HC+BIC, MMPC+HC+BIC, and the PC-Stable algorithm. Evaluation is conducted using a leave-one-state-out protocol over a fully enumerated state\u2013action space in a controlled offline autonomous driving setting. The environment is characterized by seven Boolean state variables and six actions, allowing us to disentangle the effects of learning strategies on counterfactual decisions. All models are implemented as probabilistic logic twin networks (PLTNs), with additional sensitivity analysis across parameter configurations. The learning regimes produce markedly different counterfactual decisions. Edge-constrained HC+BIC recommends a diverse set of safe actions, while unconstrained HC+BIC yields fewer but consistently safe alternatives. MMPC+HC+BIC frequently fails to identify safe actions, often associated with weak connectivity of the outcome variable. PC-Stable produces varied recommendations but may include unsafe actions, which is linked to incorrect edge orientations between actions and outcomes. These findings show that structure learning choices and prior knowledge influence counterfactual decisions through the learned structure, affecting the identification of safe alternatives in safety-critical applications.<\/jats:p>","DOI":"10.3390\/e28050577","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:02:27Z","timestamp":1779375747000},"page":"577","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Causal Structure Learning Assumptions Shape Counterfactual Safety: Expert-Guided Constraints vs. Data-Driven DAGs with Probabilistic Logic Twin Networks"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5310-3474","authenticated-orcid":false,"given":"H\u00e9ctor","family":"Avil\u00e9s","sequence":"first","affiliation":[{"name":"Department of Information Technologies, Polytechnic University of Victoria, Ciudad Victoria 87138, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7101-6656","authenticated-orcid":false,"given":"Ingridh","family":"Gracia","sequence":"additional","affiliation":[{"name":"Department of Information Technologies, Polytechnic University of Victoria, Ciudad Victoria 87138, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafael","family":"Kiesel","sequence":"additional","affiliation":[{"name":"Institute of Computational Logic, Vienna University of Technology, 1040 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5976-9338","authenticated-orcid":false,"given":"Ver\u00f3nica","family":"Rodr\u00edguez","sequence":"additional","affiliation":[{"name":"Computer Science Institute, Technological University of the Mixteca, Huajuapan de Le\u00f3n 69004, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5731-6677","authenticated-orcid":false,"given":"Rub\u00e9n","family":"Machucho","sequence":"additional","affiliation":[{"name":"Department of Information Technologies, Polytechnic University of Victoria, Ciudad Victoria 87138, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8509-6974","authenticated-orcid":false,"given":"Alberto","family":"Reyes","sequence":"additional","affiliation":[{"name":"Control, Electronics and Communications Department, National Institute of Electricity and Clean Energies, Cuernavaca 62490, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Negrete","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, National Autonomous University of Mexico, Mexico City 04510, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Ram\u00edrez","sequence":"additional","affiliation":[{"name":"Center for Research and Advanced Studies, The National Polytechnic Institute, Tamaulipas Campus, Ciudad Victoria 87138, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicol\u00e1s","family":"Lu\u00e9vano","sequence":"additional","affiliation":[{"name":"Department of Information Technologies, Polytechnic University of Victoria, Ciudad Victoria 87138, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myriam","family":"Peque\u00f1o","sequence":"additional","affiliation":[{"name":"Department of Information Technologies, Polytechnic University of Victoria, Ciudad Victoria 87138, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0355-7755","authenticated-orcid":false,"given":"Jes\u00fas","family":"Medrano","sequence":"additional","affiliation":[{"name":"Department of Information Technologies, Polytechnic University of Victoria, Ciudad Victoria 87138, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-8279","authenticated-orcid":false,"given":"Felix","family":"Weitk\u00e4mper","sequence":"additional","affiliation":[{"name":"Statistical and Symbolic Artificial Intelligence Group, German University of Digital Science, 14482 Potsdam, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1038\/s41746-026-02370-6","article-title":"A Causal and interpretable machine learning framework for postcranioplasty risk prediction and surgical decision support","volume":"9","author":"Li","year":"2026","journal-title":"npj Digit. Med."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yacoby, Y., Green, B., Griffin, C.L., and Doshi-Velez, F. (2022, January 16\u201319). \u201cIf it didn\u2019t happen, why would I change my decision?\u201d: How Judges Respond to Counterfactual Explanations for the Public Safety Assessment. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, Pittsburgh, PA, USA.","DOI":"10.2139\/ssrn.4203996"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.jsr.2019.12.010","article-title":"Improving workplace safety by thinking about what might have been: A first look at the role of counterfactual thinking","volume":"72","author":"He","year":"2020","journal-title":"J. Saf. Res."},{"key":"ref_4","unstructured":"Sokol, K., and Flach, P. (2019, January 27). Counterfactual explanations of machine learning predictions: Opportunities and challenges for AI safety. Proceedings of the 2019 AAAI Workshop on Artificial Intelligence Safety, SafeAI 2019, CEUR Workshop Proceedings, Honolulu, HI, USA."},{"key":"ref_5","first-page":"3207","article-title":"Counterfactual reasoning and learning systems: The example of computational advertising","volume":"14","author":"Bottou","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref_6","first-page":"17","article-title":"Causal transformer and counterfactual reasoning: Deconstruction analysis of the impact of teaching strategies on academic achievement","volume":"9","author":"Zhang","year":"2026","journal-title":"Int. J. Comput. Syst. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v115.i09","article-title":"Counterfactuals: An R package for counterfactual explanation methods","volume":"115","author":"Dandl","year":"2025","journal-title":"J. Stat. Softw."},{"key":"ref_8","unstructured":"Youssef, P., Seifert, C., and Schl\u00f6tterer, J. (2024, January 12\u201316). LLMs for generating and evaluating counterfactuals: A comprehensive study. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, FL, USA."},{"key":"ref_9","first-page":"1","article-title":"A survey on graph counterfactual explanations: Definitions, methods, evaluation, and research challenges","volume":"56","author":"Prenkaj","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_10","unstructured":"Molak, A. (2023). Causal Inference and Discovery in Python: Unlock the Secrets of Modern Causal Machine Learning with DoWhy, EconML, PyTorch and More, Packt Publishing Ltd."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Balke, A., and Pearl, J. (2022). Probabilistic Evaluation of Counterfactual Queries. Probabilistic and Causal Inference: The Works of Judea Pearl, Association for Computing Machinery.","DOI":"10.1145\/3501714.3501733"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Vukovi\u0107, M., and Thalmann, S. (2022). Causal discovery in manufacturing: A structured literature review. J. Manuf. Mater. Process., 6.","DOI":"10.3390\/jmmp6010010"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Glymour, C., Zhang, K., and Spirtes, P. (2019). Review of causal discovery methods based on graphical models. Front. Genet., 10.","DOI":"10.3389\/fgene.2019.00524"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e12470","DOI":"10.1111\/phc3.12470","article-title":"Causal discovery algorithms: A practical guide","volume":"13","author":"Malinsky","year":"2018","journal-title":"Philos. Compass"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1093\/aje\/kwae338","article-title":"Can algorithms replace expert knowledge for causal inference? A case study on novice use of causal discovery","volume":"194","author":"Gururaghavendran","year":"2025","journal-title":"Am. J. Epidemiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s41937-024-00131-4","article-title":"An introduction to causal discovery","volume":"160","author":"Huber","year":"2024","journal-title":"Swiss J. Econ. Stat."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e1449","DOI":"10.1002\/widm.1449","article-title":"Methods and tools for causal discovery and causal inference","volume":"12","author":"Nogueira","year":"2022","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_18","unstructured":"Dawid, A.P. (2008, January 12). Beware of the DAG!. Proceedings of the Causality: Objectives and Assessment, PMLR, Whistler, BC, Canada."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.ijar.2022.09.004","article-title":"A survey on causal discovery: Theory and practice","volume":"151","author":"Zanga","year":"2022","journal-title":"Int. J. Approx. Reason."},{"key":"ref_20","unstructured":"Emezue, C.C., Drouin, A., Deleu, T., Bauer, S., and Bengio, Y. (2023, January 28). Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation. Proceedings of the ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling, Honolulu, HI, USA."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"108258","DOI":"10.1016\/j.engappai.2024.108258","article-title":"A survey of causal discovery based on functional causal model","volume":"133","author":"Wang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"0467","DOI":"10.34133\/research.0467","article-title":"Causal inference meets deep learning: A comprehensive survey","volume":"7","author":"Jiao","year":"2024","journal-title":"Research"},{"key":"ref_23","first-page":"100590","article-title":"A survey on causal inference for recommendation","volume":"5","author":"Luo","year":"2024","journal-title":"Innovation"},{"key":"ref_24","unstructured":"Komanduri, A., Wu, X., Wu, Y., and Chen, F. (2023). From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s11633-024-1519-z","article-title":"Counterfactual learning on graphs: A survey","volume":"22","author":"Guo","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"884","DOI":"10.1017\/S1471068423000133","article-title":"\u201cWhat if?\u201d in Probabilistic Logic Programming","volume":"23","author":"Kiesel","year":"2023","journal-title":"Theory Pract. Log. Program."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1017\/S1471068414000076","article-title":"Inference and Learning in Probabilistic Logic Programs using Weighted Boolean Formulas","volume":"15","author":"Fierens","year":"2015","journal-title":"Theory Pract. Log. Program."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Riguzzi, F. (2023). Foundations of Probabilistic Logic Programming, River Publishers.","DOI":"10.1201\/9781003427421"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1016\/j.artint.2007.11.002","article-title":"On probabilistic inference by weighted model counting","volume":"172","author":"Chavira","year":"2008","journal-title":"Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"104109","DOI":"10.1016\/j.artint.2024.104109","article-title":"aspmc: New frontiers of algebraic answer set counting","volume":"330","author":"Eiter","year":"2024","journal-title":"Artif. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Nishiyama, D., Castro, M.Y., Maruyama, S., Shiroshita, S., Hamzaoui, K., Ouyang, Y., Rosman, G., DeCastro, J., Lee, K.H., and Gaidon, A. (2020). Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation. 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), IEEE Press.","DOI":"10.1109\/ITSC45102.2020.9294715"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kirfel, L., MacCoun, R., Icard, T., and Gerstenberg, T. (2024, January 21\u201323). Anticipating the Risks and Benefits of Counterfactual World Simulation Models. Proceedings of the 2024 AAAI\/ACM Conference on AI, Ethics, and Society, San Jose, CA, USA.","DOI":"10.31234\/osf.io\/9x8rv"},{"key":"ref_33","unstructured":"Li, M., Liu, C., Li, Z., Liu, X., Yu, G., Du, B., Shen, J., and Wu, Q. (2025). CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"108447","DOI":"10.1016\/j.aap.2026.108447","article-title":"Modeling interactive car-following behaviors of automated and human-driven vehicles in safety-critical events: A multi-agent state-space attention-enhanced framework","volume":"229","author":"Pu","year":"2026","journal-title":"Accid. Anal. Prev."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Pearl, J. (2009). Causality: Models, Reasoning and Inference, Cambridge University Press. [2nd ed.].","DOI":"10.1017\/CBO9780511803161"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"108785","DOI":"10.1016\/j.ress.2022.108785","article-title":"A novel probabilistic approach to counterfactual reasoning in system safety","volume":"228","author":"Groth","year":"2022","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1146\/annurev-statistics-031017-100630","article-title":"Causal Structure Learning","volume":"5","author":"Maathuis","year":"2018","journal-title":"Annu. Rev. Stat. Its Appl."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3385","DOI":"10.1007\/s10115-023-01858-x","article-title":"The impact of prior knowledge on causal structure learning","volume":"65","author":"Constantinou","year":"2023","journal-title":"Knowl. Inf. Syst."},{"key":"ref_39","unstructured":"Rodr\u00edguez, V., Avil\u00e9s, H., Machucho, R., Reyes, A., Negrete, M., Ram\u00edrez, G., Petrilli, A., Gracia, I., De-La-Garza, G., and Rivera, K. (2024, January 12). Preventing Collisions in Self-driving Cars using Probabilistic Logic Counterfactual Reasoning. Proceedings of the Workshop on Causal Discovery (CaDis), Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Montevideo, Uruguay. Available online: https:\/\/cadisworkshop.com.mx\/wp-content\/uploads\/2024\/11\/preventing-collisions-in-self-driving-cars-using-probabilistic-logic-counterfactual-reasoning.pdf."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1007\/s11222-019-09857-1","article-title":"Learning Bayesian networks from big data with greedy search: Computational complexity and efficient implementation","volume":"29","author":"Scutari","year":"2019","journal-title":"Stat. Comput."},{"key":"ref_41","unstructured":"Heckerman, D., Meek, C., and Cooper, G. (2006). A Bayesian approach to causal discovery. Innovations in Machine Learning: Theory and Applications, Springer."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kotz, S., and Johnson, N.L. (1992). Information Theory and an Extension of the Maximum Likelihood Principle. Breakthroughs in Statistics: Foundations and Basic Theory, Springer.","DOI":"10.1007\/978-1-4612-0919-5"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Tsamardinos, I., Aliferis, C.F., and Statnikov, A. (2003, January 24\u201327). Time and sample efficient discovery of Markov blankets and direct causal relations. Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/956750.956838"},{"key":"ref_44","unstructured":"Edwards, D. (2012). Introduction to Graphical Modelling, Springer Science & Business Media."},{"key":"ref_45","first-page":"3741","article-title":"Order-independent constraint-based causal structure learning","volume":"15","author":"Colombo","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1177\/089443939100900106","article-title":"An Algorithm for Fast Recovery of Sparse Causal Graphs","volume":"9","author":"Spirtes","year":"1991","journal-title":"Soc. Sci. Comput. Rev."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1214\/aos\/1031833662","article-title":"A characterization of Markov equivalence classes for acyclic digraphs","volume":"25","author":"Andersson","year":"1997","journal-title":"Ann. Stat."},{"key":"ref_48","unstructured":"R Core Team (2021). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v035.i03","article-title":"Learning Bayesian Networks with the bnlearn R Package","volume":"35","author":"Scutari","year":"2010","journal-title":"J. Stat. Softw."},{"key":"ref_50","first-page":"153","article-title":"Maximum Likelihood: An Introduction","volume":"58","year":"1990","journal-title":"Int. Stat. Rev.\/Rev. Int. De Stat."},{"key":"ref_51","unstructured":"Dor, D., and Tarsi, M. (1992). A Simple Algorithm to Construct a Consistent Extension of a Partially Oriented Graph, Cognitive Systems Laboratory, UCLA. Available online: https:\/\/api.semanticscholar.org\/CorpusID:122949140."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Gallaire, H., and Minker, J. (1978). Negation as Failure. Logic and Data Bases, Springer.","DOI":"10.1007\/978-1-4684-3384-5"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1613\/jair.989","article-title":"A knowledge compilation map","volume":"17","author":"Darwiche","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Kiesel, R., and Eiter, T. (2023, January 2\u20138). Knowledge compilation and more with SharpSAT-TD. Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning, Rhodes, Greece. KR \u201923.","DOI":"10.24963\/kr.2023\/40"},{"key":"ref_55","unstructured":"Vlasselaer, J., Kimmig, A., Dries, A., Meert, W., and De Raedt, L. (2016, January 12). Knowledge Compilation and Weighted Model Counting for Inference in Probabilistic Logic Programs. Proceedings of the AAAI Workshop: Beyond NP, Phoenix, AZ, USA."},{"key":"ref_56","unstructured":"Eiter, T., Hecher, M., and Kiesel, R. (2021, January 20\u201321). aspmc: An Algebraic Answer Set Counter. Proceedings of the ICLP Workshops, Porto, Portugal (virtual)."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Vennekens, J., Verbaeten, S., and Bruynooghe, M. (2004). Logic programs with annotated disjunctions. International Conference on Logic Programming, Springer.","DOI":"10.1007\/978-3-540-27775-0_30"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/5\/577\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T16:08:14Z","timestamp":1779466094000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/5\/577"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":57,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["e28050577"],"URL":"https:\/\/doi.org\/10.3390\/e28050577","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]}}}