{"id":"W2891697899","doi":"10.1111/insr.12292","title":"Combining Data from New and Traditional Sources in Population Surveys","year":2018,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Census and Population Estimation","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Data set; Data collection; Survey data collection; Data mining; Computer science; Census; Data science; Linkage (software); Scale (ratio); Population; Set (abstract data type); Geography; Statistics; Cartography; Mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0563448,0.0009347177,0.002175172,0.01226852,0.0007212881,0.005620636,0.002185612,0.0009981,0.001755794],"category_scores_gemma":[0.07360046,0.00115049,0.002385175,0.02197443,0.002224833,0.006239905,0.005867772,0.003197386,0.0009808962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581065,"about_ca_system_score_gemma":0.001957295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001635482,"about_ca_topic_score_gemma":0.002769022,"domain_scores_codex":[0.9284335,0.0466313,0.004848393,0.004034827,0.01550973,0.0005423057],"domain_scores_gemma":[0.9465213,0.03711187,0.002592699,0.006899169,0.006503791,0.0003710981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001559461,0.0001134614,0.02814694,0.005601048,0.00180755,0.000295039,0.001822027,0.009903334,0.00148164,0.112655,0.009446872,0.8285713],"study_design_scores_gemma":[0.0001537573,0.0005422092,0.05470502,0.0105248,0.002010399,0.001763302,0.003336533,0.04963464,0.0101814,0.4598624,0.4067793,0.0005061455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01883343,0.08319367,0.8779201,0.005798824,0.001550688,0.0007210823,0.001987903,0.000456088,0.009538256],"genre_scores_gemma":[0.106699,0.06666288,0.8168385,0.001417742,0.001553189,0.001099174,0.002915267,0.0001865204,0.002627663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0563448,"threshold_uncertainty_score":0.2979833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3018531286839378,"score_gpt":0.4401493471684914,"score_spread":0.1382962184845536,"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."}}