{"id":"W1976129119","doi":"10.1002/ajim.22005","title":"Performance of automated and manual coding systems for occupational data: A case study of historical records","year":2011,"lang":"en","type":"article","venue":"American Journal of Industrial Medicine","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Heart, Lung, and Blood Institute; National Institute for Occupational Safety and Health; U.S. Public Health Service; National Institutes of Health","keywords":"Coding (social sciences); Medicine; Census; Software; Environmental health; Computer science; Statistics; Population; Mathematics; Programming language","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":[0.00203816,0.0001121849,0.0005070148,0.0001156019,0.00006497808,0.000001944403,0.0002090572,0.00003994805,0.00006525051],"category_scores_gemma":[0.0005773219,0.000086486,0.00001893035,0.0002391814,0.000392709,0.0002166854,0.00009546651,0.0002188111,5.43053e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002755807,"about_ca_system_score_gemma":0.00005782047,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00779499,"about_ca_topic_score_gemma":0.00003365444,"domain_scores_codex":[0.9980891,0.0002055911,0.0008941705,0.0002054599,0.0004414365,0.0001642509],"domain_scores_gemma":[0.9979131,0.0003690768,0.001301085,0.0002123394,0.00004218218,0.0001621984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001296867,0.0004959014,0.8650199,0.00002441862,0.0001134918,0.0002294052,0.005709435,0.00009416355,0.0005699993,0.000001600244,0.002244875,0.1242],"study_design_scores_gemma":[0.04362587,0.1586205,0.4942187,0.003442064,0.002162026,0.01492164,0.2015023,0.07594424,0.0006831005,0.000007996019,0.003558628,0.001312901],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9987474,0.0000405459,0.0002753385,0.00005837383,0.0003752962,0.0003991708,0.00001514575,0.000006064331,0.00008264574],"genre_scores_gemma":[0.9991078,0.00006347142,0.0005349787,0.00002340126,0.0002448398,0.00000511885,0.000002290875,0.000009787676,0.000008357001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3708012,"threshold_uncertainty_score":0.9988122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.169129915408648,"score_gpt":0.3482634161337277,"score_spread":0.1791335007250797,"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."}}