{"id":"W3211267634","doi":"10.1136/oem-2021-epi.453","title":"S-499 The application of artificial intelligence in the coding of occupational information","year":2021,"lang":"en","type":"article","venue":"","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Benchmarking; Coding (social sciences); Computer science; Matching (statistics); Artificial intelligence; Information retrieval; Machine learning; Data science; Data mining; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0007843816,0.00004112547,0.00005169769,0.00001768998,0.00005316756,0.000007917097,0.0001442464,0.00002200766,0.00045314],"category_scores_gemma":[0.0001240841,0.00002659846,0.00001861747,0.0002890125,0.0001215379,0.0002193553,0.00006235263,0.00007653174,0.00009989511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005365353,"about_ca_system_score_gemma":0.00001938106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002969209,"about_ca_topic_score_gemma":0.0003050506,"domain_scores_codex":[0.9991496,0.00009402975,0.0003006459,0.00008956438,0.0002817401,0.00008443268],"domain_scores_gemma":[0.9994695,0.0002101874,0.0001171403,0.0001819097,0.00000972053,0.00001154347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003722235,0.0002122958,0.1140458,0.00003957931,0.000006658033,7.151571e-7,0.01065388,0.01341327,0.0222672,0.06757608,0.0001108114,0.7716365],"study_design_scores_gemma":[0.00006395992,0.0000251634,0.8587714,0.00001547778,0.000007536969,0.000004117073,0.008409161,0.06407429,0.06085125,0.005524294,0.002157172,0.00009611381],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5409583,0.000006061873,0.4466322,0.0009279943,0.00002125402,0.0003312018,0.000006116884,0.000004367138,0.01111243],"genre_scores_gemma":[0.9982545,0.00001548841,0.001113456,0.0005671747,0.000007407609,0.00002175023,0.00001244765,0.000001443956,0.000006325363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7715404,"threshold_uncertainty_score":0.4961566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03609584047434831,"score_gpt":0.3084710642013997,"score_spread":0.2723752237270514,"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."}}