{"id":"W2892160487","doi":"10.23889/ijpds.v3i4.979","title":"Bias, accuracy and sample size in the systematic linking of historical records","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Census and Population Estimation","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University; University of Guelph","funders":"","keywords":"Representativeness heuristic; Computer science; Sampling bias; Sample size determination; Data quality; Invariant (physics); Data mining; Sample (material); Selection bias; Statistics; Econometrics; Artificial intelligence; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004079155,0.00007081105,0.0001483713,0.0002056886,0.0002259906,0.0001641421,0.000989965,0.00002872473,0.0000179383],"category_scores_gemma":[0.0322664,0.00004873481,0.00002809884,0.0002820211,0.00007997182,0.001108759,0.0001198906,0.00009047067,7.795061e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001931098,"about_ca_system_score_gemma":0.00006233787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003062476,"about_ca_topic_score_gemma":0.0002641118,"domain_scores_codex":[0.9982099,0.00007809365,0.000680437,0.0001728753,0.0007413375,0.0001173874],"domain_scores_gemma":[0.9946106,0.003856024,0.0006526386,0.0003123991,0.0005319839,0.0000363256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002757341,0.0004830319,0.6077721,0.002268773,0.0000928708,0.000007341638,0.007877603,0.0002085666,0.0009506219,0.3396304,0.006843749,0.03358925],"study_design_scores_gemma":[0.001126286,0.0001796528,0.2596345,0.002528334,0.0000783717,0.0003350247,0.0003787034,0.2099244,0.0000692217,0.522617,0.002834814,0.0002937121],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9162197,0.0000661666,0.07674188,0.002518309,0.003404945,0.0007366951,0.0001564314,0.00002029336,0.0001355956],"genre_scores_gemma":[0.9465586,0.00001381717,0.05294168,0.00007522947,0.0003513415,0.000005061645,0.00002607833,0.000005119634,0.000023058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3481376,"threshold_uncertainty_score":0.9758852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2533297546395775,"score_gpt":0.4503384809297971,"score_spread":0.1970087262902196,"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."}}