{"id":"W2809472587","doi":"10.1093/annweh/wxy052","title":"Development of a Coding and Crosswalk Tool for Occupations and Industries","year":2018,"lang":"en","type":"article","venue":"Annals of Work Exposures and Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Cancer Research Society","keywords":"Schema crosswalk; Coding (social sciences); Computer science; Population; Statistics; Medicine; Engineering; Mathematics; Transport engineering; Environmental health","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004158898,0.00006601674,0.0002490202,0.00005307222,0.0001404949,0.00001074484,0.00002147764,0.00003506324,0.000007825124],"category_scores_gemma":[0.00009152073,0.00005688647,0.00001356361,0.00009443775,0.0001571244,0.00004129371,0.00003430944,0.00003561233,1.952629e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004119947,"about_ca_system_score_gemma":0.0001875277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002638092,"about_ca_topic_score_gemma":0.00008136639,"domain_scores_codex":[0.9993324,0.0000130565,0.0002954319,0.0001294277,0.00008500265,0.0001446944],"domain_scores_gemma":[0.9994351,0.00005504981,0.0001367333,0.00009925124,0.0001639601,0.0001098877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005283011,0.00007708482,0.7514316,0.0006668857,0.00007479414,5.086816e-7,0.00264687,1.249623e-7,0.0001279599,0.0008939853,0.0300596,0.2134922],"study_design_scores_gemma":[0.0006027557,0.0004233845,0.9730672,0.000338846,0.000007245622,0.000001945088,0.000214888,0.00000616305,0.0009586963,0.00008787039,0.02423421,0.00005680266],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946697,0.002183185,0.0002655775,0.002368657,0.00002259578,0.000319502,0.0001076864,0.000009784224,0.00005336365],"genre_scores_gemma":[0.9935842,0.0004378074,0.005235232,0.0005856255,0.00005034866,0.00001052168,0.0000400158,0.000005814863,0.00005043746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2216356,"threshold_uncertainty_score":0.2319763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.170146835240855,"score_gpt":0.4260737662538271,"score_spread":0.2559269310129721,"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."}}