{"id":"W3040360098","doi":"10.1017/ssh.2020.15","title":"Selection Bias Encountered in the Systematic Linking of Historical Census Records","year":2020,"lang":"en","type":"article","venue":"Social Science History","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University; University of Guelph","funders":"","keywords":"Census; Selection bias; Matching (statistics); Sample (material); Population; Selection (genetic algorithm); Sampling bias; Econometrics; Statistics; Information bias; Genealogy; Geography; Sample size determination; Computer science; Sociology; Economics; History; Demography; Mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01234008,0.00007609107,0.0002761341,0.0002120436,0.0002705998,0.00007026278,0.001541149,0.00004306254,0.00005143511],"category_scores_gemma":[0.004742987,0.00005155679,0.00008524855,0.00201228,0.0003825502,0.0004050183,0.0001355333,0.0001558267,0.00003879177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001903466,"about_ca_system_score_gemma":0.0002422432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003482047,"about_ca_topic_score_gemma":0.0001860302,"domain_scores_codex":[0.9959419,0.0006226016,0.0006688659,0.0003658381,0.002192034,0.0002087599],"domain_scores_gemma":[0.9986672,0.0004683777,0.0004164072,0.0002178299,0.0001750965,0.00005509532],"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":[0.0001204256,0.0004527204,0.004054192,0.002488404,0.00001998976,0.0000261571,0.337369,0.0000343899,0.003620583,0.1328313,0.4889678,0.03001503],"study_design_scores_gemma":[0.0006617587,0.0003904923,0.01529772,0.0004163282,0.0000649799,0.000004760444,0.04767341,0.003698819,0.00006300448,0.01252149,0.9186612,0.0005460357],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4078337,0.00392419,0.02569723,0.05729228,0.02666994,0.005961255,0.00008311721,0.0004752378,0.472063],"genre_scores_gemma":[0.9980163,0.000003819393,0.0001303285,0.001236714,0.0001514153,0.00001264475,8.783916e-7,0.000002882833,0.0004450018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5901826,"threshold_uncertainty_score":0.5678141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4476471592264005,"score_gpt":0.3994208451867887,"score_spread":0.04822631403961175,"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."}}