{"id":"W3122531144","doi":"10.6084/m9.figshare.14687696","title":"Fast Bayesian Record Linkage With Record-Specific Disagreement Parameters","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Record linkage; Linkage (software); Bayesian probability; Computer science; Statistics; Econometrics; Artificial intelligence; Mathematics; Biology; Sociology; Genetics; Demography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0217569,0.001519517,0.00228586,0.006495842,0.002067929,0.00430018,0.00526603,0.002760404,0.01374436],"category_scores_gemma":[0.08890279,0.001833355,0.002727159,0.01206759,0.0007608323,0.005417958,0.005003199,0.003976149,0.01207048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001864868,"about_ca_system_score_gemma":0.005946335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01215371,"about_ca_topic_score_gemma":0.02227734,"domain_scores_codex":[0.9869235,0.005232548,0.00124438,0.003441439,0.002758793,0.0003992965],"domain_scores_gemma":[0.973118,0.01387936,0.001650104,0.007584647,0.003435276,0.0003327249],"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":[0.001042486,0.000348354,0.02093562,0.001950999,0.001241398,0.0002740282,0.0008194619,0.06011784,0.002534335,0.04131908,0.4173191,0.4520972],"study_design_scores_gemma":[0.0009450049,0.0001268158,0.008483217,0.0004088299,0.0003638182,0.000758927,0.0003391517,0.4961349,0.008089997,0.2213566,0.2627541,0.0002385463],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.01040808,0.001281911,0.8318523,0.001352429,0.0002434925,0.0006839481,0.1162215,0.03379197,0.004164355],"genre_scores_gemma":[0.04647064,0.0006113012,0.753553,0.0004802583,0.00013648,0.001756251,0.1906128,0.002378033,0.004001274],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.0217569,"threshold_uncertainty_score":0.1150629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2024257611765003,"score_gpt":0.3652343665565406,"score_spread":0.1628086053800403,"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."}}