{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008950124,0.0002264867,0.0003627625,0.0006263352,0.0001789558,0.0006746852,0.001016264,0.0001433125,0.00001161204],"category_scores_gemma":[0.001695751,0.000179589,0.00004332426,0.0005233794,0.0004194511,0.0005282181,0.001141738,0.0003614406,0.00001944505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000896132,"about_ca_system_score_gemma":0.0001364642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009753757,"about_ca_topic_score_gemma":0.00045661,"domain_scores_codex":[0.9958366,0.00003381702,0.0007011829,0.002653419,0.0004954301,0.000279545],"domain_scores_gemma":[0.9964404,0.001381688,0.0001762374,0.00172356,0.0001957246,0.00008242594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001254158,0.00001423467,0.0009805091,0.0001191906,0.000003908538,0.000002219085,0.0005217338,0.0005880794,0.00002831561,0.05052799,0.0001226926,0.9470786],"study_design_scores_gemma":[0.0001800677,0.0001702638,0.01358282,0.0002388705,0.00001048373,0.000009852944,0.000001441134,0.1581948,0.0001244954,0.7849451,0.04218801,0.0003538075],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009416672,0.001420475,0.9684228,0.01368876,0.001397624,0.001559654,0.000122475,0.00005804447,0.003913456],"genre_scores_gemma":[0.9411094,0.0006433551,0.04853477,0.002559327,0.0004879239,0.00009185167,0.00002644361,0.00003251186,0.006514464],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9467248,"threshold_uncertainty_score":0.7323427,"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."}}