{"id":"W4244573874","doi":"10.2196/preprints.16422","title":"Occupation Coding of Job Titles: Iterative Development of an Automated Coding Algorithm for the Canadian National Occupation Classification (ACA-NOC) (Preprint)","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Healthcare Systems and Public Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital; University of Alberta; University of New Brunswick","funders":"","keywords":"Coding (social sciences); Computer science; Algorithm; Benchmark (surveying); Search algorithm; Upload; Information retrieval; Data mining; Preprint; Matching (statistics); Mathematics; World Wide Web; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01886096,0.001394786,0.0009248693,0.008134549,0.003304925,0.003251598,0.002843006,0.0008615498,0.00910253],"category_scores_gemma":[0.09750558,0.0007312567,0.001284212,0.006465677,0.001595828,0.001616699,0.004302199,0.001817792,0.003718563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009193824,"about_ca_system_score_gemma":0.0374153,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.3483201,"about_ca_topic_score_gemma":0.3939033,"domain_scores_codex":[0.9881442,0.003485548,0.001750812,0.002064514,0.0040019,0.0005530855],"domain_scores_gemma":[0.9455315,0.01478277,0.00214121,0.002942745,0.03391412,0.0006876509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000286975,0.0002077347,0.02655536,0.001585645,0.0001229476,0.0002264105,0.0103129,0.01155786,0.009683657,0.02378702,0.08921611,0.8264574],"study_design_scores_gemma":[0.0002765764,0.0002334827,0.05082294,0.002002314,0.000226897,0.0005150146,0.01692691,0.5950503,0.03384249,0.05370173,0.2458321,0.0005690721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0224182,0.0002595189,0.9516063,0.0009705693,0.0002567524,0.005485552,0.007064611,0.006226726,0.005711774],"genre_scores_gemma":[0.02310628,0.00008589614,0.9675116,0.0001196925,0.00002099906,0.00280485,0.0042452,0.0004497596,0.001655758],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6516799,"threshold_uncertainty_score":0.6925853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1113322150339254,"score_gpt":0.4109827966512818,"score_spread":0.2996505816173564,"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."}}