{"id":"W4283574083","doi":"10.1016/j.jclinepi.2022.06.006","title":"Record linkage and big data—enhancing information and improving design","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Linkage (software); Record linkage; Computer science; Data science; Observational study; Population; Value (mathematics); Data mining; Medicine; Statistics; Mathematics; Environmental health; Biology","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":["metaresearch"],"category_scores_codex":[0.2358633,0.00008251047,0.001042559,0.0002206078,0.0001940132,0.00006809966,0.0009193707,0.00008157671,0.0000846136],"category_scores_gemma":[0.2750651,0.00005749149,0.00009379388,0.0001827425,0.0001553712,0.001056422,0.001807282,0.0007144938,0.00001024156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000152178,"about_ca_system_score_gemma":0.0001370536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005309696,"about_ca_topic_score_gemma":0.00002482028,"domain_scores_codex":[0.9824036,0.01004512,0.006466303,0.0003176793,0.0005349781,0.0002322729],"domain_scores_gemma":[0.8851509,0.1068659,0.006622736,0.0008431491,0.0002198672,0.0002973977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001634278,0.00002485718,0.01227859,0.000009186863,0.00002416267,0.000007445038,0.00008579362,0.0001510274,0.000003573229,0.001128277,0.02523854,0.9608851],"study_design_scores_gemma":[0.001219249,0.001463429,0.07758433,0.00001921505,0.00005764367,0.000134053,0.001872057,0.02437746,0.000001882634,0.1063393,0.7867826,0.0001487863],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09185232,0.0004296252,0.8900619,0.01409085,0.003186614,0.0001378312,0.00004529113,0.000007787535,0.00018776],"genre_scores_gemma":[0.7693223,0.003288349,0.1838145,0.04119122,0.001957752,0.000007421646,0.00003826033,0.00001352199,0.000366592],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9607363,"threshold_uncertainty_score":0.7868396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7736697826487204,"score_gpt":0.5786307282052613,"score_spread":0.1950390544434591,"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."}}