{"id":"W7125831461","doi":"10.21428/594757db.4d4509de","title":"Experimental Analysis of Large Language Models in Crime Classification and Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Crime analysis; Law enforcement; Transformative learning; Adaptability; Focus (optics); Domain (mathematical analysis); Generative grammar; Enforcement","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002111268,0.00002403206,0.00005593645,0.0001987541,0.00003431148,0.00003049108,0.00002860483,0.00002441537,0.001280203],"category_scores_gemma":[0.000005037264,0.00002212912,0.00005122153,0.0003425141,0.00002790779,0.0001744258,0.00001060486,0.00002513417,0.00000269023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003242484,"about_ca_system_score_gemma":0.000009445403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003692949,"about_ca_topic_score_gemma":0.002384858,"domain_scores_codex":[0.999624,0.00003434164,0.0001068872,0.00009104201,0.00008341819,0.00006031942],"domain_scores_gemma":[0.9999009,0.00001473853,0.00001138073,0.00004489593,0.0000101812,0.00001786844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009483781,0.0005039831,0.0413218,0.00004178559,0.0003665773,0.000003416814,0.1662774,0.00008135914,0.04690077,0.7380067,0.002393517,0.004093189],"study_design_scores_gemma":[0.0002327149,0.00006449782,0.2528023,0.00007389249,0.0003171746,2.258677e-7,0.1886901,0.5493297,0.005465193,0.0007526854,0.002136076,0.0001354748],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.950703,0.0007867618,0.004150748,0.0001256909,0.00005703079,0.00005653893,0.00003454557,0.00003263353,0.04405303],"genre_scores_gemma":[0.9985222,0.00002188011,0.00003555852,0.00001042861,0.00001647912,0.000007095486,0.00001623267,0.000001804558,0.001368371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.737254,"threshold_uncertainty_score":0.9996328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06609552712876222,"score_gpt":0.4163797179679329,"score_spread":0.3502841908391707,"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."}}