{"id":"W6944136180","doi":"10.17632/d7vzpcdzcw.4","title":"CrimeDataBD: A Standard Dataset of Crime Records in Bangladesh for Machine Learning Tasks","year":2025,"lang":"en","type":"dataset","venue":"Mendeley Data","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Data source; Crime analysis; Socioeconomic status; Crime scene; Random forest; Distribution (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009550483,0.002311151,0.001200709,0.004171474,0.0008713188,0.001184414,0.00290818,0.001847596,0.0346067],"category_scores_gemma":[0.006100371,0.0006814536,0.0008857328,0.00747673,0.0004927915,0.001324247,0.001602715,0.001788738,0.04837818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002340923,"about_ca_system_score_gemma":0.00328951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07262981,"about_ca_topic_score_gemma":0.1039504,"domain_scores_codex":[0.998726,0.0001987903,0.0002322845,0.0002774532,0.0003850499,0.0001804932],"domain_scores_gemma":[0.9971424,0.0005143014,0.0002453761,0.0006997092,0.001096801,0.0003014835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009230978,0.00006242777,0.002403013,0.000414437,0.00003034378,0.00005349801,0.00004043379,0.000753487,0.000153867,0.0003694927,0.9908988,0.004727884],"study_design_scores_gemma":[0.0003850942,0.00009070631,0.03414745,0.0004130177,0.00007125625,0.000268665,0.0005298283,0.004144468,0.001845857,0.001602433,0.9563683,0.0001329856],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0007368854,0.00004224675,0.0001309456,0.00008622168,0.00002543786,0.00004316697,0.9977275,0.0004511502,0.0007564846],"genre_scores_gemma":[0.001088609,0.0000366241,0.0003019648,0.00002171248,0.000003879561,0.000107983,0.9978497,0.00003254738,0.0005569396],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.07262981,"threshold_uncertainty_score":0.1444141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06910668295656398,"score_gpt":0.3673507676158333,"score_spread":0.2982440846592693,"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."}}