{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.04004332,0.0002755397,0.001019818,0.0004144787,0.000206228,0.001400647,0.01257665,0.0001231949,0.0001549446],"category_scores_gemma":[0.02683098,0.0002125618,0.000150117,0.00165884,0.0001337335,0.001328854,0.01508839,0.0005726027,0.0002915296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007502545,"about_ca_system_score_gemma":0.0002600313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001562218,"about_ca_topic_score_gemma":0.0002152151,"domain_scores_codex":[0.988939,0.001935669,0.003011074,0.001415833,0.004177032,0.0005213502],"domain_scores_gemma":[0.9817297,0.002159789,0.00171538,0.01307151,0.0007946881,0.0005289462],"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":[0.0001520835,0.0009380399,0.0004511293,0.0001076099,0.0002987403,0.0002294442,0.0003107419,0.00003254838,0.00002377781,0.02683655,0.3750104,0.5956089],"study_design_scores_gemma":[0.0007654497,0.00005569167,0.01954164,0.0001260307,0.0001702351,0.00006254426,0.007386626,0.0001672225,0.00001589714,0.02900648,0.9423463,0.0003558746],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00518036,0.0006649357,0.9570451,0.008075943,0.004759148,0.0003519765,0.006621786,0.00002873136,0.01727202],"genre_scores_gemma":[0.6252039,0.001131488,0.3299585,0.01897147,0.006124792,0.00001454051,0.005156794,0.00008357462,0.01335492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6270866,"threshold_uncertainty_score":0.999636,"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."}}