{"id":"W2237788583","doi":"","title":"Stepwise Variable Selection for Loglinear Mixture in Record Linkage","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick; McMaster University","funders":"","keywords":"Log-linear model; Overfitting; Mathematics; Model selection; Covariate; Selection (genetic algorithm); Mixture model; Statistical model; Linkage (software); Probabilistic logic; Statistics; Linear model; Artificial intelligence; Computer science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004440696,0.00007550793,0.0001464905,0.0001813661,0.0000731553,0.0002118902,0.0004483783,0.0001019483,0.001968642],"category_scores_gemma":[0.002346462,0.00005478654,0.00004224157,0.0005973083,0.00002272718,0.0003755252,0.0001031754,0.0001832064,0.000296692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001147392,"about_ca_system_score_gemma":0.00003491462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003149621,"about_ca_topic_score_gemma":0.006209631,"domain_scores_codex":[0.9986314,0.0000712994,0.0003910885,0.0003606569,0.0003512893,0.0001942811],"domain_scores_gemma":[0.9986856,0.0006439182,0.00008344345,0.0003924523,0.0001394387,0.00005515981],"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":[0.0001096046,0.0002730846,0.004798804,0.00002336208,0.00001347262,0.000001631861,0.0002400176,0.0000978917,0.005108053,0.3188041,0.4623762,0.2081538],"study_design_scores_gemma":[0.0003477666,0.00005194103,0.0006847879,0.000002733682,0.000003716491,6.763119e-7,0.0001743519,0.01047988,0.0005335969,0.09796932,0.8896634,0.0000878365],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06804915,0.000009133245,0.8612075,0.00393399,0.002595759,0.0009417933,0.0000687779,0.0001190607,0.06307477],"genre_scores_gemma":[0.1924798,0.00001093261,0.6184823,0.004837406,0.0007118476,0.0001414342,0.00007828575,0.00002473777,0.1832333],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4272872,"threshold_uncertainty_score":0.9989437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09442882874722106,"score_gpt":0.404395673341274,"score_spread":0.309966844594053,"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."}}