{"id":"W4381938374","doi":"10.2196/44310","title":"Normal Workflow and Key Strategies for Data Cleaning Toward Real-World Data: Viewpoint","year":2023,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Workflow; Data quality; Computer science; Data science; Data governance; Data mining; Process (computing); Data virtualization; Data set; Data management; Key (lock); Quality (philosophy); Data cleansing; Database; Engineering; Computer security; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09282124,0.0001155335,0.000444045,0.001070877,0.0002085231,0.001238802,0.006616521,0.00006037477,0.0005750209],"category_scores_gemma":[0.06404767,0.00007587965,0.00006176149,0.001431157,0.0005088947,0.003546612,0.007510413,0.001282738,0.0001546966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006639009,"about_ca_system_score_gemma":0.0007022623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004553104,"about_ca_topic_score_gemma":0.002148638,"domain_scores_codex":[0.9888952,0.001284951,0.001156893,0.0005725516,0.007564767,0.0005256847],"domain_scores_gemma":[0.9709289,0.0250356,0.0005214918,0.001609752,0.001287718,0.0006165486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005208767,0.00006880919,0.0001323325,0.00003130881,0.00009211714,0.0002284001,0.0009476885,0.000005362842,0.00001609588,0.007600079,0.4883393,0.5020177],"study_design_scores_gemma":[0.0008603092,0.0004625425,0.004517656,0.0005177218,0.00002124556,0.00003673193,0.03626725,0.03176307,0.00002654567,0.05847815,0.866923,0.0001258063],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1453177,0.001170813,0.2725326,0.5429013,0.005949566,0.001821868,0.001866968,0.0001087845,0.02833042],"genre_scores_gemma":[0.9751849,0.008130921,0.008486907,0.001670389,0.002723486,0.00001916931,0.0003285149,0.00004567604,0.003410055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8298672,"threshold_uncertainty_score":0.999798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7111703779494515,"score_gpt":0.6382519355459901,"score_spread":0.07291844240346135,"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."}}