{"id":"W4307622887","doi":"10.3233/sji-220082","title":"Predicting the quality and evaluating the use of administrative data for the 2021 Canadian Census of Population","year":2022,"lang":"en","type":"article","venue":"Statistical Journal of the IAOS","topic":"Census and Population Estimation","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Census; Imputation (statistics); Data quality; Population; Pandemic; Geography; Missing data; Coronavirus disease 2019 (COVID-19); Computer science; Statistics; Environmental health; Medicine; Operations management; Economics; 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":[0.003475724,0.0000659398,0.0001611127,0.00002086029,0.0005763512,0.00002940144,0.0003608956,0.00001802773,0.00005525129],"category_scores_gemma":[0.01098031,0.00002908024,0.00004757681,0.0001058465,0.0001093758,0.00007576316,0.0001247546,0.000231495,3.476321e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000550235,"about_ca_system_score_gemma":0.0002091696,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007426022,"about_ca_topic_score_gemma":0.007796993,"domain_scores_codex":[0.9979616,0.0006788979,0.0006844255,0.00007552509,0.000493823,0.0001057746],"domain_scores_gemma":[0.9894401,0.008943969,0.000959742,0.0003828084,0.0002339416,0.00003944202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009287111,0.0001973549,0.06863651,0.000340853,0.0006366546,0.000003608092,0.008545369,0.02125189,0.0003056646,0.8070316,0.01440088,0.07772085],"study_design_scores_gemma":[0.0006050116,0.0003187211,0.3887798,0.00008366157,0.0005868774,0.00007277475,0.003043548,0.4622658,0.00001976975,0.1428705,0.001256521,0.00009708276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9155316,0.0002159615,0.04826589,0.02080179,0.0008060882,0.001780944,0.01253307,0.00000419727,0.00006039588],"genre_scores_gemma":[0.9874335,0.000003503193,0.0123379,0.00007272172,0.00007484011,0.000005610682,0.00004556139,0.000007298978,0.00001909768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6641611,"threshold_uncertainty_score":0.9991836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5978813152470713,"score_gpt":0.523511196845447,"score_spread":0.07437011840162433,"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."}}