{"id":"W2408790143","doi":"10.2139/ssrn.2777765","title":"Improving the Accuracy of Automated Occupation Coding at Any Production Rate","year":2016,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Data Processing Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Coding (social sciences); Production (economics); Computer science; Statistics; Econometrics; Mathematics; Economics; Microeconomics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001144588,0.0001100763,0.0001027672,0.00007598088,0.0001613435,0.00002069534,0.0002036748,0.00004470839,0.000005607606],"category_scores_gemma":[0.0005061869,0.00006519936,0.00003307647,0.0001551163,0.00003929783,0.0006390883,0.00003717843,0.000411539,0.00000610802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010699,"about_ca_system_score_gemma":0.0002209075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004904183,"about_ca_topic_score_gemma":0.00004277641,"domain_scores_codex":[0.998691,0.00004228338,0.0002564893,0.0001158113,0.000125112,0.0007693559],"domain_scores_gemma":[0.9994195,0.00007917703,0.0001961127,0.000195301,0.00008742819,0.00002254525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003508469,0.000007593469,0.0003409375,0.0000271754,0.00004442382,4.487005e-7,0.00006561566,0.0005066202,0.8731899,0.002149953,0.0003986241,0.1232336],"study_design_scores_gemma":[0.0006560331,0.0001754143,0.001703194,0.0003249141,0.00005151301,0.0005535212,0.0001948472,0.02553289,0.9196057,0.04939186,0.001404119,0.0004059479],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4994727,0.001088757,0.4975116,0.0003270202,0.0002688832,0.000172848,0.000005106675,0.001107165,0.00004586135],"genre_scores_gemma":[0.9959373,0.002656667,0.001147203,0.000006649328,0.0001304398,0.000007561893,0.00000276904,0.00002869647,0.00008268534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4964646,"threshold_uncertainty_score":0.2658753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007929461539594045,"score_gpt":0.2518219020341048,"score_spread":0.2438924404945107,"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."}}