Events and identity in probabilistic models of legal evidence
Downloads
Abstract
This paper examines whether Bayesian networks are expressive enough to model reasoning with evidence in legal cases. Bayesian networks can represent many familiar patterns of evidential reasoning, including inferences from evidence to hypotheses, cumulative support from multiple items of evidence, and chains of inferences linking intermediate hypotheses to ultimate guilt. However, other forms of evidential reasoning commonly found in legal cases are more difficult to model. Focusing on a real criminal case, the paper distinguishes between identity-level and event-level inferences. Event-level inferences explain why certain actions constitute guilty conduct, whereas identity-level inferences connect the defendant to those actions. The paper argues that the main challenge for Bayesian network models of legal evidence is to represent how identity-level and event-level inferences interact and mutually reinforce each other. Addressing this challenge requires extending Bayesian networks beyond a purely propositional language.
Keywords
Bayesian networks, likelihood ratio, probability, criminal lawDownloads
References
Allen, R. J., & Pardo, M. S. (2007). The Problematic Value of Mathematical Models of Evidence. Journal of Legal Studies, 36(1), 107–140.
Bozza, S., Taroni, F., & Aitken, C. (2026). The Myth of Judicial Objectivity: Why Subjectivity Is the Only Path to a Transparent Trial. Quaestio Facti. Revista Internacional Sobre Razonamiento Probatorio, 11.
Dahlman, C., & Kolflaath, E. (2022). Causal Models versus Reason Models in Bayesian Networks for Legal Evidence. Synthese, 200, 477.
Fenton, N., Neil, M., & Lagnado, D. A. (2013). A General Structure for Legal Arguments about Evidence Using Bayesian Networks. Cognitive Science, 37(1), 61–102.
Fenton, N., Neil, M., Yet, B., & Lagnado, D. A. (2020). Analyzing the Simonshaven Case Using Bayesian Networks. Topics in Cognitive Science, 12(4), 1092–1114.
Hampson, L., & van Leeuwen, L. (2025). Investigating the Value of Qualitative Bayesian Networks of Complete Cases as “Double-Check” Tools on Traditional Judicial Reasoning: An Exploratory Study. Proceedings of the Workshop on AI for Evidential Reasoning, 4157, 40–71.
Kadane, J. B., & Schum, D. A. (1996). A Probabilistic Analysis of the Sacco and Vanzetti Evidence. John Wiley & Sons.
Lagnado, D. A. (2021). Explaining the Evidence: How the Mind Investigates the World. Cambridge University Press.
Laskey, K. B. (2008). MEBN: A Language for First-Order Bayesian Knowledge Bases. Artificial Intelligence, 172(2–3), 140–178.
Mackor, A. R. (2026). Bayesian Modelling of Criminal Cases as a Whole: A Philosophical Reflection on Dutch Case Law. Quaestio Facti. Revista Internacional Sobre Razonamiento Probatorio, 10, 363–384.
Stacey, J., Opperman, S., Curran, J. M., & Harbison, S. A. (2025). Current State and Barriers to Global Adoption of Forensic Evaluative Reporting of Findings Given Activity-Level Propositions. Science & Justice, 65(6), 101336.
Taroni, F., Biedermann, A., Bozza, S., Garbolino, P., & Aitken, C. (2014). Bayesian Networks for Probabilistic Inference and Decision Analysis in Forensic Science (2nd ed.). John Wiley & Sons.
Taylor, D., Biedermann, A., Hicks, T., & Champod, C. (2018). A Template for Constructing Bayesian Networks in Forensic Biology Cases when Considering Activity-Level Propositions. Forensic Science International: Genetics, 33, 136–146.
Tribe, L. H. (1971). Trial by Mathematics: Precision and Ritual in the Legal Process. Harvard Law Review, 84(6), 1329–1393.
Vlek, C. S., Prakken, H., Renooij, S., & Verheij, B. (2014). Building Bayesian Networks for Legal Evidence with Narratives: A Case Study Evaluation. Artificial Intelligence and Law, 22(4), 375–421.
DOI
https://doi.org/10.33115/udg_bib/qf.i11.23278Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Marcello Di Bello
This work is licensed under a Creative Commons Attribution 4.0 International License.