{"id":"W3125002781","doi":"10.5539/gjhs.v13n3p23","title":"Data Cleaning Needs and Issues: A Case Study of the National Reproductive Health Assessment (RHA) Data from Solomon Islands","year":2021,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Data collection; Reproductive health; Standardization; Data entry; Reliability (semiconductor); Process (computing); Research data; Medicine; Computer science; Environmental health; Database; Data science; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01734236,0.0004103211,0.0004796994,0.001691249,0.009033784,0.002678031,0.002739056,0.002465006,0.002354543],"category_scores_gemma":[0.03647725,0.0004742389,0.0005055944,0.002948562,0.002791012,0.001605076,0.003498471,0.00209526,0.0002336082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008578945,"about_ca_system_score_gemma":0.01143831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1150817,"about_ca_topic_score_gemma":0.1751859,"domain_scores_codex":[0.9810635,0.01291347,0.001395989,0.0007599706,0.002357775,0.00150938],"domain_scores_gemma":[0.9615303,0.02610854,0.003469629,0.00209268,0.004674688,0.002124164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002147301,0.000718692,0.1139344,0.001782749,0.0001311311,0.08648758,0.7097188,0.0009547254,0.002414972,0.005101157,0.007187934,0.07135312],"study_design_scores_gemma":[0.00002446927,0.0003933016,0.06810889,0.001242643,0.00006572215,0.01078973,0.8646383,0.001279592,0.001608297,0.001345414,0.05043202,0.00007154232],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9785825,0.0005796294,0.00308536,0.01030801,0.0000467846,0.000839947,0.0002432241,0.00002526439,0.006289316],"genre_scores_gemma":[0.980701,0.001270463,0.01133584,0.001992893,0.0000378872,0.0006379233,0.0002040261,0.00004058622,0.003779556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1150817,"threshold_uncertainty_score":0.2288237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4862324880655968,"score_gpt":0.5819926248280866,"score_spread":0.09576013676248973,"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."}}