{"id":"W4378364755","doi":"10.1109/icsmdi57622.2023.00089","title":"Utilising Deep Learning as a Law Enforcement Ally","year":2023,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Law enforcement; Acknowledgement; Upload; Cloud computing; Computer science; Enforcement; Face (sociological concept); Construct (python library); Computer security; Population; Deep learning; Artificial intelligence; Internet privacy; Political science; Law; Sociology; World Wide Web; Social science","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":[0.001104365,0.0004581917,0.0003725935,0.001013233,0.0005403754,0.001451468,0.0009706828,0.001105003,0.003844353],"category_scores_gemma":[0.002261398,0.0002970168,0.0003379674,0.0006926714,0.000872543,0.00187866,0.001321774,0.001511743,0.001319513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009473405,"about_ca_system_score_gemma":0.00141414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007346981,"about_ca_topic_score_gemma":0.008529047,"domain_scores_codex":[0.9993809,0.000116128,0.00003437587,0.0001245029,0.0002067014,0.0001373242],"domain_scores_gemma":[0.9992341,0.0002203771,0.00009535674,0.0001524606,0.0002425723,0.00005515841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002076797,0.0006297233,0.009119356,0.0001463354,0.00009014345,0.0002497498,0.0001955528,0.09366052,0.02132546,0.01789614,0.01033147,0.8461479],"study_design_scores_gemma":[0.00001296,0.00008201092,0.001289461,0.00003767686,0.00001942956,0.00007552599,0.00009547854,0.9679621,0.01490311,0.00825395,0.007251557,0.00001668139],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1173402,0.0008354957,0.8351262,0.004080682,0.0003077807,0.0002340996,0.0003091468,0.006729255,0.03503719],"genre_scores_gemma":[0.8590307,0.0005294,0.1213166,0.0008209412,0.00007254245,0.00007809464,0.0002795938,0.0001070171,0.01776518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007346981,"threshold_uncertainty_score":0.01460844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01842957004269632,"score_gpt":0.2657403514667077,"score_spread":0.2473107814240113,"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."}}