{"id":"W4402406136","doi":"10.23889/ijpds.v9i5.2657","title":"Navigating Data Acquisition and Data Quality Validation of Large Databases: Practical Lessons","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saskatchewan Health Quality Council","funders":"","keywords":"Database; Computer science; Data quality; Quality (philosophy); Data mining; Data science; Engineering; Operations management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2234102,0.002998229,0.00209173,0.006018222,0.008685321,0.02344819,0.01103378,0.01054222,0.01087884],"category_scores_gemma":[0.3890887,0.002122457,0.003056365,0.005553029,0.01718698,0.03994498,0.01735848,0.02615604,0.00627428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01187376,"about_ca_system_score_gemma":0.04756484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03295751,"about_ca_topic_score_gemma":0.03246171,"domain_scores_codex":[0.8143449,0.1248558,0.01207737,0.009682599,0.03279702,0.006242298],"domain_scores_gemma":[0.4912102,0.303138,0.0178742,0.05231761,0.107861,0.02759898],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001896935,0.0006622713,0.01336523,0.003222971,0.0002506265,0.001250361,0.02512227,0.005055044,0.0009301595,0.04305983,0.4729127,0.4339789],"study_design_scores_gemma":[0.0002121401,0.0003272682,0.007268265,0.01110276,0.000133972,0.002004086,0.04319217,0.006392805,0.001524167,0.3774868,0.5497773,0.0005783115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.006778736,0.02171862,0.127803,0.8192539,0.006402792,0.0007922314,0.000781035,0.002620332,0.01384942],"genre_scores_gemma":[0.0956626,0.02767973,0.7456494,0.108394,0.008048229,0.001902493,0.002359546,0.002028717,0.008275204],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7765898,"threshold_uncertainty_score":0.9576735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6281295486631037,"score_gpt":0.6648589747416125,"score_spread":0.03672942607850882,"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."}}