Skip to content

Research

My PhD research was about evidential reasoning in criminal trials. When a judge or jury thinks about evidence (DNA-match, fingerprints) they often take a holistic perspective: how well does the evidence fit in with the scenario of what may have happened? However, an expert witness reporting on the DNA-match or fingerprints is used to taking a statistical point of view. We proposed a method that would integrate the statistical point of view (in the form of Bayesian networks) with the holistic perspective from narrative (stories or scenarios). My research was part of the project Designing and Understanding Forensic Bayesian Networks with Arguments and Scenarios (see also the project page). I defended my PhD-thesis on October 28th, 2016.

Publications:

  • Dissertation: C.S. Vlek (2016). When Stories and Numbers Meet in Court: Constructing and Explaining Bayesian Networks for Criminal Cases with Scenarios. Groningen: Rijksuniversiteit Groningen. (pdf)
  • C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Representing the quality of crime scenarios in a Bayesian network The 28th International Conference on Legal Knowledge and Information Systems (JURIX), Braga (Portugal) 2015. (pdf)
  • C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Constructing and understanding Bayesian networks for legal evidence with scenario schemes. Proceedings of the 15th International Conference on Artificial Intelligence and Law. San Diego (USA) 2015 (pp. 128-137). New York: ACM Press (2015). (pdf)
  • B. Verheij, F.J. Bex, S.T. Timmer, C.S. Vlek, J.-J. Meyer, S. Renooij & H. Prakken. Arguments, Scenarios and Probabilities: Connections Between Three Normative Frameworks for Evidential Reasoning. Law, Probability & Risk 2015. (online)
  • C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Extracting scenarios from a Bayesian network as explanations for legal evidence. The 27th International Conference on Legal Knowledge and Information Systems (JURIX), Krakow (Poland) 2014 (pp. 103-112). (pdf)
  • C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Building Bayesian networks for legal evidence with narratives: a case study evaluation. Artificial Intelligence and Law, 22(4): 375-421, 2014doi :10.1007/s10506-014-9161-7. (pdf) (online)(supplementary BN model)
  • C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Unfolding crime scenarios with variations: a method for building a Bayesian networks for legal narratives. The 26th International Conference on Legal Knowledge and Information Systems (JURIX), Bologna (Italy) 2013. IOS Press (pp. 145-154). (pdf)
  • C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Representing and evaluating legal narratives with subscenarios in a Bayesian network. 2013 Workshop on Computational Models of Narrative, Hamburg (Germany) 2013. Schloss Dagstuhl, Saarbrücken/Wadern, Germany (pp.315-332). (pdf)
  • C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Modeling crime scenarios in a Bayesian network. Proceedings of the 14th International Conference on Artificial Intelligence and Law, Rome (Italy) 2013 (pp. 150 -159). New York: ACM Press 2013. (pdf)
  • G. Barmpalias & C.S. Vlek, Kolmogorov complexity of initial segments of sequences and arithmetical definability. Theoretical Computer Science. 412 (41): pp.5656-5667, 2011.

Supplementary Bayesian network models

The following Bayesian network models were made with GeNIe, which is available for download at www.bayesfusion.com

  • Anjum case study (xdsl), supplementary to C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, Building Bayesian networks for legal evidence with narratives: a case study evaluation. Artificial Intelligence and Law, 22(4): 375-421, 2014.
  • Anjum case study (xdsl), revised for thesis.
  • Stabbing example (xdsl), supplementary to C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, A method for explaining Bayesian networks for legal evidence with scenarios. Artificial Intelligence and Law, submitted, 2016.
  • Nijmegen case study (xdsl), supplementary to C.S. Vlek, H. Prakken, S. Renooij & B. Verheij, A method for explaining Bayesian networks for legal evidence with scenarios. Artificial Intelligence and Law, submitted, 2016.