{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009226382,0.0006377094,0.0009192441,0.0004341929,0.0002597449,0.001982113,0.00339815,0.0003449548,0.6139413],"category_scores_gemma":[0.0031134,0.0004755426,0.0003114448,0.001178685,0.00004031416,0.0004954409,0.001743677,0.0007511579,0.0437755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001480488,"about_ca_system_score_gemma":0.0001525296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001205623,"about_ca_topic_score_gemma":0.002573647,"domain_scores_codex":[0.9928164,0.0005547635,0.001235377,0.001917457,0.002809034,0.0006669803],"domain_scores_gemma":[0.9928204,0.001347649,0.0009627881,0.004160976,0.00035778,0.0003504043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002858476,0.0001126154,0.000002905831,0.0001740291,0.00007780771,0.0003682056,0.00002702521,0.000008356661,7.175971e-8,0.00000250678,0.9172109,0.08198694],"study_design_scores_gemma":[0.0002923078,0.0001686216,0.00006579034,0.002346433,0.00003855867,0.000007048041,0.0005320637,0.00001147647,0.00000393631,0.0001126549,0.9957361,0.0006850053],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00000127943,0.0002125755,0.0001652226,0.0004772246,0.0007232606,0.0006888126,0.9963301,0.00005286911,0.001348695],"genre_scores_gemma":[0.000001241475,0.0001543404,0.001748902,0.001454153,0.0003216149,0.0003843913,0.9914995,0.0000338281,0.004402066],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.5701658,"threshold_uncertainty_score":0.9997696,"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."}}