{"id":"W4210862833","doi":"10.1186/s40537-021-00468-0","title":"Big data quality framework: a holistic approach to continuous quality management","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Big data; Computer science; Data quality; Profiling (computer programming); Data science; Data mining; Quality (philosophy); Data management; Exploratory data analysis; Engineering; Operations management","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02319967,0.001635723,0.001460026,0.008474006,0.001729945,0.01249012,0.005137668,0.002282169,0.001491374],"category_scores_gemma":[0.01704438,0.0009524018,0.002635168,0.006920575,0.004829486,0.009860926,0.007141108,0.004336807,0.0004441428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004613797,"about_ca_system_score_gemma":0.008362233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008350067,"about_ca_topic_score_gemma":0.004430864,"domain_scores_codex":[0.9801129,0.007178219,0.002191905,0.002336131,0.007177746,0.001003089],"domain_scores_gemma":[0.9840884,0.004016307,0.002351393,0.002461807,0.005660739,0.001421214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001093133,0.0002621348,0.007876138,0.001075091,0.0002837821,0.0005295757,0.001807496,0.08542763,0.002813424,0.7666662,0.008924868,0.1242244],"study_design_scores_gemma":[0.00004817708,0.0002370221,0.003071013,0.001147669,0.000230517,0.0004890858,0.001600674,0.5202304,0.003794894,0.4036711,0.06530437,0.000175027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003223868,0.001045924,0.9877215,0.002229395,0.0001161466,0.0003257338,0.0002040851,0.0007506341,0.004382772],"genre_scores_gemma":[0.1608619,0.001365987,0.834285,0.0005096621,0.0002860672,0.000522727,0.0007481945,0.0001623917,0.001258121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02319967,"threshold_uncertainty_score":0.1226931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7948772270531455,"score_gpt":0.5341265486844159,"score_spread":0.2607506783687296,"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."}}