{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02649027,0.001963604,0.00250312,0.007485933,0.001473232,0.002751933,0.002219542,0.002491962,0.002294154],"category_scores_gemma":[0.06103544,0.0004753887,0.001785401,0.00591323,0.0005002531,0.004331979,0.001290307,0.002189488,0.001415323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002321938,"about_ca_system_score_gemma":0.002179178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01223323,"about_ca_topic_score_gemma":0.006800066,"domain_scores_codex":[0.9865736,0.005920703,0.00142865,0.001440979,0.003994668,0.0006414566],"domain_scores_gemma":[0.9392996,0.04617658,0.001387121,0.002857196,0.009712821,0.0005666324],"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":[0.003334824,0.0007333351,0.02714823,0.0007494845,0.001204858,0.000155932,0.0002182312,0.08972984,0.001080009,0.003470096,0.0134763,0.858699],"study_design_scores_gemma":[0.0002309145,0.001625839,0.01854677,0.0004122498,0.0005085746,0.0002143262,0.000578338,0.9585096,0.004349293,0.005902534,0.008997856,0.0001236053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5908546,0.04266553,0.313981,0.004172657,0.004242271,0.001624088,0.007167793,0.008870741,0.02642152],"genre_scores_gemma":[0.7495992,0.008841529,0.2263985,0.0004851251,0.0006678874,0.0007356745,0.007902236,0.0003856003,0.004984224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02649027,"threshold_uncertainty_score":0.1400956,"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."}}