{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007683021,0.00009307177,0.0001964977,0.00004365823,0.00003966611,0.00003886788,0.000189715,0.00003505269,0.002294855],"category_scores_gemma":[0.002528802,0.00008636135,0.00001380141,0.00007711268,0.00004330035,0.0002073314,0.00007432918,0.00008671488,0.00005335865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003941526,"about_ca_system_score_gemma":0.00002406999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001508037,"about_ca_topic_score_gemma":0.0009996155,"domain_scores_codex":[0.9987333,0.0001587818,0.0004460705,0.000244689,0.000323921,0.00009323104],"domain_scores_gemma":[0.99839,0.001164751,0.000126541,0.0001815966,0.00006518579,0.00007189985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002329095,0.0001298277,0.09904625,0.0002287064,0.00004865548,0.000007342375,0.0001106712,0.000001711689,0.000006211887,0.6970776,0.03462542,0.1686943],"study_design_scores_gemma":[0.0002623552,0.00001655671,0.59827,0.0008238677,0.00002451086,0.000005418186,0.000001803477,0.01257767,7.900234e-7,0.3823296,0.005589293,0.00009816645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1460907,0.00760916,0.8250107,0.007666512,0.001559261,0.001084938,0.005067573,0.0001577196,0.005753397],"genre_scores_gemma":[0.9237005,0.001238304,0.06601498,0.0006173919,0.0005085399,0.000007525033,0.00776328,0.00001835155,0.0001311715],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7776097,"threshold_uncertainty_score":0.9986172,"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."}}