{"id":"W4395098146","doi":"10.1007/978-981-97-2242-6_16","title":"Class Ratio and Its Implications for Reproducibility and Performance in Record Linkage","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Record linkage; Pairwise comparison; Matching (statistics); Linkage (software); Classifier (UML); Data mining; Class (philosophy); Test data; Artificial intelligence; Information retrieval; Statistics; Mathematics","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":[0.1057586,0.0007963167,0.002278552,0.005792446,0.00218289,0.009570444,0.005920631,0.003936104,0.005758942],"category_scores_gemma":[0.5551079,0.001018989,0.001407669,0.01049658,0.005787628,0.01621862,0.003937359,0.00409094,0.002014524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00300211,"about_ca_system_score_gemma":0.002776775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001872938,"about_ca_topic_score_gemma":0.001041824,"domain_scores_codex":[0.896337,0.05645689,0.005861716,0.01074441,0.02899798,0.001602144],"domain_scores_gemma":[0.2237161,0.6977351,0.0124394,0.04680446,0.01790531,0.001399576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00178681,0.0004585118,0.09013221,0.0006082833,0.0005132023,0.0003526149,0.00258312,0.03852952,0.004229775,0.2969555,0.01927185,0.5445786],"study_design_scores_gemma":[0.000238277,0.0006110992,0.0278029,0.0002477101,0.0004671466,0.002568934,0.001135831,0.3090359,0.01805877,0.6271628,0.0123347,0.0003359448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1013541,0.008004916,0.8515677,0.009026157,0.001318809,0.0002633791,0.001242924,0.003410108,0.02381186],"genre_scores_gemma":[0.6854679,0.002259885,0.298678,0.0007949189,0.001677161,0.0004270228,0.0008701516,0.001632264,0.008192775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1057586,"threshold_uncertainty_score":0.5593117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1309395802531087,"score_gpt":0.3785712184593527,"score_spread":0.247631638206244,"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."}}