{"id":"W2186688881","doi":"","title":"Understanding Survey Data Collection through the Analysis of Paradata at Statistics Canada","year":2008,"lang":"en","type":"article","venue":"","topic":"Census and Population Estimation","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Data collection; Respondent; Data quality; Data science; Agency (philosophy); Computer science; Population; Statistics; Business; Marketing; Sociology; Political science; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003197738,0.00006340508,0.0001684677,0.00003772624,0.000275878,0.000006682676,0.0001681535,0.00002241974,0.0002959229],"category_scores_gemma":[0.0005111822,0.00004453841,0.00001376873,0.0007731365,0.0000369313,0.00008329064,0.00007992805,0.00003660008,5.761776e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002503073,"about_ca_system_score_gemma":0.0001708964,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6699036,"about_ca_topic_score_gemma":0.9860935,"domain_scores_codex":[0.9991124,0.0001022001,0.0002852646,0.00012602,0.000287258,0.00008688132],"domain_scores_gemma":[0.9978958,0.001244927,0.0001764276,0.0005906183,0.00007393991,0.00001829292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00002142649,0.0000287225,0.2311228,0.00001710803,0.000496652,0.000001859604,0.0004545038,0.001779296,0.000002484486,0.04474024,0.7213108,0.00002405909],"study_design_scores_gemma":[0.0002155603,0.00000991764,0.5918507,0.000004613127,0.0006697936,0.000006737622,0.000227975,0.3965809,0.00002445054,0.008564484,0.001701902,0.0001430037],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07135713,0.00001458056,0.9224626,0.0001626747,0.0001260735,0.0001699949,0.004043495,0.00001876778,0.001644703],"genre_scores_gemma":[0.982079,0.00002901533,0.01220152,0.00004055771,0.000007793704,8.664064e-7,0.004562248,0.000006371929,0.00107257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9107219,"threshold_uncertainty_score":0.3322945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5706535237707858,"score_gpt":0.3895662230336076,"score_spread":0.1810873007371783,"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."}}