{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.04279782,0.0001240605,0.0002019057,0.0002815093,0.0004670824,0.002666193,0.008188024,0.00003369242,0.0001405685],"category_scores_gemma":[0.0253353,0.0001004495,0.00002832698,0.0007241049,0.0002418645,0.0271492,0.009238501,0.0002703435,0.00002314271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006888637,"about_ca_system_score_gemma":0.0002979884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002974666,"about_ca_topic_score_gemma":0.0001689581,"domain_scores_codex":[0.9932743,0.0002786158,0.001322336,0.001326756,0.003549005,0.0002489692],"domain_scores_gemma":[0.9926621,0.002100429,0.0007492633,0.003532158,0.000808418,0.0001476575],"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":[0.0001876069,0.0003826917,0.0103704,0.0001014918,0.0001812683,0.00003477975,0.0005894537,0.0002122252,0.002072671,0.572507,0.08859328,0.3247672],"study_design_scores_gemma":[0.000754924,0.00005223366,0.02958228,0.0004835178,0.00011345,0.0002233075,0.002185848,0.6348132,0.0003244031,0.04551482,0.2855817,0.0003702943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06595144,0.0002044747,0.8357032,0.02669536,0.004601181,0.0003438903,0.06636573,0.00004577883,0.00008893418],"genre_scores_gemma":[0.9157238,0.0001290655,0.04684753,0.0003276302,0.0005073873,0.000002539694,0.03639632,0.000009690515,0.00005601757],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8497724,"threshold_uncertainty_score":0.9987746,"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."}}