{"id":"W3035066987","doi":"10.2196/16422","title":"Occupation Coding of Job Titles: Iterative Development of an Automated Coding Algorithm for the Canadian National Occupation Classification (ACA-NOC)","year":2020,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital; University of Alberta; University of New Brunswick","funders":"WorkSafe Victoria","keywords":"Coding (social sciences); Computer science; Algorithm; Benchmark (surveying); Search algorithm; Data mining; Information retrieval; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00223085,0.0001117483,0.0001359322,0.0001624652,0.000722317,0.00004353157,0.0002570615,0.00008018802,0.0002202064],"category_scores_gemma":[0.000335988,0.00009381836,0.00003184254,0.0005525462,0.0002720044,0.0006575157,0.00008720834,0.0002351123,0.00009510054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001284033,"about_ca_system_score_gemma":0.0004645458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002108922,"about_ca_topic_score_gemma":0.007234662,"domain_scores_codex":[0.9976642,0.0002901593,0.000449756,0.0002754498,0.0009820185,0.0003384053],"domain_scores_gemma":[0.9987357,0.0005105623,0.0002217964,0.0001289317,0.0002209854,0.0001820256],"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":[0.0002291839,0.0003819026,0.02368612,0.0005234302,0.0001645192,0.000002015774,0.2329429,0.001742195,0.04418738,0.002923888,0.007346834,0.6858696],"study_design_scores_gemma":[0.0003587285,0.0001439395,0.3077784,0.00005537157,0.000003653219,5.478843e-7,0.003373657,0.6734524,0.01283812,0.00007825063,0.001808151,0.0001087931],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6787484,0.00001781161,0.3065014,0.001604575,0.00008955547,0.00441183,0.0004699768,0.00009341504,0.008063097],"genre_scores_gemma":[0.9899987,0.000009220313,0.009338222,0.0001193616,0.00002821404,0.0002897821,0.0001807766,0.00001298331,0.00002274497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6857608,"threshold_uncertainty_score":0.5555552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1304285435754554,"score_gpt":0.4237081831491167,"score_spread":0.2932796395736613,"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."}}