{"id":"W4200619950","doi":"10.1371/journal.pone.0260365","title":"Re-assessing measurement error in police calls for service: Classifications of events by dispatchers and officers","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Policing Practices and Perceptions","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Sample (material); Clearance; Service (business); Type of service; Police department; Psychology; Computer security; Computer science; Medicine; Criminology; Business","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":[0.1274876,0.0007432869,0.001081513,0.004715685,0.002088542,0.003514605,0.002547306,0.001119659,0.0009126016],"category_scores_gemma":[0.4020734,0.0006336886,0.001079049,0.006041492,0.003073413,0.003642407,0.004496781,0.001947334,0.0004148251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002153141,"about_ca_system_score_gemma":0.002467018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02048244,"about_ca_topic_score_gemma":0.02171016,"domain_scores_codex":[0.8276976,0.1147186,0.01938846,0.009144043,0.02600206,0.003049028],"domain_scores_gemma":[0.5333591,0.2733879,0.09017964,0.05768434,0.04354055,0.001848442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002126563,0.00009381956,0.9261448,0.0003593567,0.0005880127,0.00009020087,0.03172946,0.001033942,0.0006851661,0.002295901,0.001690164,0.03507643],"study_design_scores_gemma":[0.0000191799,0.0001864807,0.9600853,0.0003728787,0.0001530065,0.0001695731,0.02139982,0.006207741,0.001756082,0.004660132,0.004883695,0.0001060707],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9543806,0.0006935321,0.03737368,0.001161758,0.0002483829,0.0004904516,0.0009197096,0.00008035218,0.004651532],"genre_scores_gemma":[0.9876925,0.0001696578,0.01023936,0.0002396946,0.0000838689,0.0003573165,0.0006194884,0.00004309529,0.0005550568],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1274876,"threshold_uncertainty_score":0.6742269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2901502799184016,"score_gpt":0.3996893188108428,"score_spread":0.1095390388924412,"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."}}