{"id":"W2591159053","doi":"10.1515/jos-2017-0006","title":"Three Methods for Occupation Coding Based on Statistical Learning","year":2017,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Coding (social sciences); Computer science; Respondent; Statistical learning; German; Artificial intelligence; Machine learning; Data mining; Statistics; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01435736,0.001088303,0.001473047,0.008333919,0.001347872,0.002892242,0.004581873,0.001788323,0.00296944],"category_scores_gemma":[0.08516278,0.0006730368,0.001363801,0.005877513,0.002248091,0.004363639,0.004165878,0.002486736,0.001289896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00235792,"about_ca_system_score_gemma":0.003446348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007773832,"about_ca_topic_score_gemma":0.00704816,"domain_scores_codex":[0.9812979,0.00878223,0.001503105,0.00244902,0.005387619,0.0005801504],"domain_scores_gemma":[0.9198611,0.05101637,0.004463986,0.01024311,0.01340944,0.001006041],"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":[0.0003696233,0.0004075393,0.01888875,0.000297791,0.0002569122,0.0001422919,0.001043496,0.07355724,0.00224282,0.04511144,0.006284544,0.8513975],"study_design_scores_gemma":[0.0000389694,0.00004587773,0.002547578,0.00005590318,0.00004229261,0.0001301232,0.0002935224,0.9462501,0.003499197,0.04470794,0.00231923,0.00006916406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01002081,0.0001466647,0.9876513,0.0002791467,0.0000491675,0.000147595,0.0001339611,0.000733115,0.0008381747],"genre_scores_gemma":[0.1548135,0.0001293047,0.8417178,0.0001358688,0.0001219789,0.0004572481,0.0006515344,0.0001864348,0.001786278],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01435736,"threshold_uncertainty_score":0.07592988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3572853652668075,"score_gpt":0.5651666475921359,"score_spread":0.2078812823253283,"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."}}