{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01040329,0.0001048109,0.0003422295,0.0001856569,0.0006819675,0.0007745995,0.0007676093,0.00004995292,0.0001735967],"category_scores_gemma":[0.06395116,0.00008033809,0.00008165622,0.00006545061,0.0001116641,0.0002428289,0.00008340097,0.000231559,0.00002367881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005643456,"about_ca_system_score_gemma":0.0001497068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002211103,"about_ca_topic_score_gemma":0.00009711389,"domain_scores_codex":[0.9974273,0.0003025321,0.0008988889,0.000179377,0.001003725,0.0001881123],"domain_scores_gemma":[0.9893205,0.007918413,0.001603283,0.000351318,0.0006918933,0.0001146313],"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":[0.0005295147,0.0000975878,0.0007651415,0.00001450204,0.00002205814,0.00001952762,0.00006392911,0.003454657,0.00002344691,0.1965301,0.04512209,0.7533574],"study_design_scores_gemma":[0.001402793,0.001454685,0.04038983,0.00005789644,0.0001110472,0.000003393658,0.0002219355,0.5142961,0.0001083963,0.2615085,0.1802321,0.0002133708],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002606647,0.000005397786,0.9967695,0.0006089794,0.00111511,0.0001352428,0.0003679325,0.000005404419,0.0007317331],"genre_scores_gemma":[0.1045429,0.000006060545,0.8947085,0.0002326566,0.0003702236,0.000001884244,0.00002123178,0.00001107814,0.000105447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.753144,"threshold_uncertainty_score":0.9439336,"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."}}