{"id":"W7099779528","doi":"","title":"Achieving Data Quality in a Statistical Agency: A Methodological Perspective DATA DETECTIVES: UNCOVERING SYSTEMATIC ERRORS IN ADMINISTRATIVE DATABASES","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Consistency (knowledge bases); Data quality; General partnership; Data integrity; Public health; Information system; Health data; Systematic review","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":[0.002011915,0.0002577176,0.00063517,0.0001463055,0.0001481469,0.0000553207,0.003552353,0.00005325055,0.00002174734],"category_scores_gemma":[0.006973624,0.0002137536,0.00002309383,0.001160908,0.000203738,0.00233603,0.003739478,0.0004416528,0.00002516177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002268864,"about_ca_system_score_gemma":0.0002208836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001059655,"about_ca_topic_score_gemma":0.002348386,"domain_scores_codex":[0.9948782,0.001801075,0.0008373953,0.00164709,0.0003910917,0.0004451258],"domain_scores_gemma":[0.9889508,0.006796413,0.0002382217,0.003812109,0.00006755213,0.0001348756],"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":[0.0001475138,0.00144707,0.01464228,0.002047945,0.0001322787,0.001018722,0.0111658,0.004275756,0.00215227,0.9592131,0.000408426,0.003348857],"study_design_scores_gemma":[0.001400156,0.0002913882,0.2523721,0.001453778,0.00004129879,0.0004090986,0.009671369,0.6908509,0.0003024136,0.04157752,0.00005487041,0.001575199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03588288,0.0002091984,0.9615559,0.0003511466,0.00004195921,0.001104273,0.0002330158,0.0001386666,0.0004829389],"genre_scores_gemma":[0.5282235,0.00003481376,0.4714597,0.0000787777,0.00001418775,0.0001014264,0.00006579355,0.000007258903,0.00001457732],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9176356,"threshold_uncertainty_score":0.8716617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5597639220459774,"score_gpt":0.5002279048689732,"score_spread":0.05953601717700419,"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."}}