{"id":"W3181834696","doi":"10.1186/s40537-021-00489-9","title":"Examining the impact of cross-domain learning on crime prediction","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland; Dalhousie University","keywords":"Computer science; Generalization; Perspective (graphical); Domain (mathematical analysis); Transfer of learning; Data science; Domain knowledge; Task (project management); Machine learning; Baseline (sea); Crime analysis; Demographics; Artificial intelligence; Subject-matter expert; Data mining; Expert system","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001654054,0.00004085381,0.0001001224,0.0000462985,0.0002454574,0.0001192092,0.0003732542,0.00003021223,0.0006675819],"category_scores_gemma":[0.0008896161,0.00002645536,0.0001096939,0.000138107,0.00009262469,0.0003047726,0.0001037437,0.0002273115,0.000005514125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005132078,"about_ca_system_score_gemma":0.0001858153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004971015,"about_ca_topic_score_gemma":0.00009236884,"domain_scores_codex":[0.9989937,0.0002510396,0.0002833169,0.00007678652,0.0002927743,0.0001023733],"domain_scores_gemma":[0.9990803,0.0001418248,0.0003039333,0.0002343382,0.0001937507,0.00004588187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001585393,0.0007740671,0.7584571,0.00003448391,0.0006123444,0.0001069901,0.01840889,0.001238589,0.01630148,0.001251073,0.08493681,0.1177196],"study_design_scores_gemma":[0.0004952573,0.0006789095,0.9398753,0.0003637566,0.00005270277,0.00004677548,0.01187967,0.000166187,0.0005898556,0.000472606,0.04530273,0.00007624715],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875492,0.0002296683,0.0009099895,0.0002804456,0.0005352041,0.0000258475,0.00008560921,0.000003960343,0.01038009],"genre_scores_gemma":[0.9985142,0.0001010577,0.00005706086,0.00001491553,0.0006879074,1.683499e-7,0.00001508208,0.000003858496,0.0006057372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1814182,"threshold_uncertainty_score":0.7309554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.34207003076943,"score_gpt":0.4718022365358112,"score_spread":0.1297322057663812,"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."}}