{"id":"W3035096436","doi":"","title":"A comparison of machine learning classifiers for use on historical record linkage","year":2020,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Linkage (software); Artificial intelligence; Record linkage; Machine learning; Computer science; Biology; Sociology; Genetics; Demography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001398627,0.0001654694,0.0006694861,0.0002859717,0.0002895245,0.00004150641,0.001461509,0.0001702033,0.0001746794],"category_scores_gemma":[0.0014804,0.0001433123,0.0003849295,0.0005003895,0.00007812631,0.0002070366,0.0001831339,0.0004278888,0.00006335184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001418936,"about_ca_system_score_gemma":0.00006624003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001390005,"about_ca_topic_score_gemma":0.001433327,"domain_scores_codex":[0.9977079,0.000344122,0.0004462418,0.0004224589,0.0009217185,0.0001575352],"domain_scores_gemma":[0.9960592,0.001867681,0.001171337,0.0005588938,0.0002636279,0.00007926067],"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":[0.01124726,0.0007803099,0.0038796,0.0009229413,0.0006968022,0.00002517365,0.04160463,0.0007292465,0.006676805,0.01949417,0.6955244,0.2184187],"study_design_scores_gemma":[0.0006867667,0.0007335067,0.01326388,0.00006846795,0.0003054379,1.378378e-7,0.03359781,0.01013069,0.00007185143,0.001159536,0.9397537,0.0002282804],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7853149,0.001389406,0.13255,0.02744333,0.00836871,0.0047259,0.001683105,0.0003495473,0.0381751],"genre_scores_gemma":[0.9266254,0.0001171623,0.002441131,0.00008002025,0.00006067954,5.693104e-7,0.0007512813,0.00001707329,0.0699067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2442293,"threshold_uncertainty_score":0.5844107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.199900603689484,"score_gpt":0.3669767055172541,"score_spread":0.1670761018277701,"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."}}