{"id":"W2951405260","doi":"10.1007/978-3-030-23381-5_5","title":"Big Data Quality: A Data Quality Profiling Model","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Data quality; Profiling (computer programming); Computer science; Data governance; Big data; Data mining; Data science; Engineering","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","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.03956093,0.0006845152,0.001290482,0.001077829,0.0003523703,0.002135506,0.03140527,0.0003983438,0.00007898422],"category_scores_gemma":[0.006604656,0.0005411217,0.0001273926,0.001021635,0.001219588,0.002468155,0.03470977,0.001121111,0.0005962455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001881327,"about_ca_system_score_gemma":0.001787052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002381147,"about_ca_topic_score_gemma":0.001486263,"domain_scores_codex":[0.9845428,0.000381934,0.002348243,0.00570824,0.006117659,0.0009011055],"domain_scores_gemma":[0.9727358,0.004067136,0.001208331,0.02125386,0.0004847867,0.0002500763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002704418,0.00005735486,0.00008901255,0.00009290673,0.00002513983,0.00001559363,0.0003066962,0.02399706,0.00003737216,0.04619346,0.001405307,0.927753],"study_design_scores_gemma":[0.0002651226,0.00003630296,0.00005749974,0.0001614134,0.00001965329,0.000004581824,0.000003941423,0.6469634,0.00003948657,0.3162508,0.0354677,0.0007301113],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006264286,0.0003095366,0.9803907,0.002683202,0.003306473,0.0008376845,0.002587035,0.0001025524,0.009720135],"genre_scores_gemma":[0.05255124,0.0002448047,0.8968768,0.01968079,0.003195945,0.00001546358,0.004959987,0.0001714143,0.02230353],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9270229,"threshold_uncertainty_score":0.999704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5635995789952036,"score_gpt":0.4702822448180456,"score_spread":0.09331733417715798,"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."}}