{"id":"W3112702945","doi":"10.3138/cjccj.2020-0011","title":"Designing an Explainable Predictive Policing Model to Forecast Police Workforce Distribution in Cities","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Criminology and Criminal Justice/La Revue canadienne de criminologie et de justice pénale","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Institut National de la Recherche Scientifique","funders":"","keywords":"Decision tree; Instinct; Computer science; Workforce; Intuition; Machine learning; Data science; Artificial intelligence; Criminology; Psychology; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001491722,0.0002939203,0.0004908544,0.0005366643,0.0007548861,0.0001920299,0.000651135,0.0003831633,0.00008440215],"category_scores_gemma":[0.003396238,0.0003447941,0.0001269821,0.0002357096,0.0005762056,0.0006500814,0.00005805333,0.0009211906,0.000003889989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00145806,"about_ca_system_score_gemma":0.003280367,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1472248,"about_ca_topic_score_gemma":0.421639,"domain_scores_codex":[0.9965435,0.0006231718,0.0006414647,0.0004019598,0.0001202047,0.001669714],"domain_scores_gemma":[0.9960112,0.0005251655,0.0002889847,0.0001895854,0.0004400351,0.002545058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000519323,0.00009345972,0.005393036,0.001183988,0.00008496708,0.001603579,0.7529724,0.0398655,0.0009291669,0.1833151,0.002781085,0.01125842],"study_design_scores_gemma":[0.0007790525,0.001585553,0.01549054,0.0006420012,0.002999071,0.0009412838,0.9590845,0.01114557,0.0003199764,0.003541988,0.002829177,0.0006412643],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9339144,0.0003044445,0.05642367,0.005965537,0.0002201306,0.0002216436,0.00009557688,0.00002822086,0.002826431],"genre_scores_gemma":[0.9926091,0.0002034839,0.003207132,0.003272679,0.0004930125,0.00002403325,0.0000171614,0.00003125907,0.0001421664],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2744141,"threshold_uncertainty_score":0.9999004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2149799632941523,"score_gpt":0.3626272820463461,"score_spread":0.1476473187521938,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}