{"id":"W3216023068","doi":"10.1108/dta-05-2021-0108","title":"Data repair of density-based data cleaning approach using conditional functional dependencies","year":2021,"lang":"en","type":"article","venue":"Data Technologies and Applications","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data mining; Data quality; Functional dependency; Scalability; Set (abstract data type); Data set; Quality (philosophy); Data validation; Database; Artificial intelligence; Engineering; Relational database","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002706742,0.0001125986,0.0002178115,0.0001519268,0.0003681256,0.000192698,0.004621487,0.00009084745,0.00005380671],"category_scores_gemma":[0.002575277,0.00009851577,0.00002141231,0.0008185817,0.0004606417,0.001088105,0.01424721,0.0001549246,0.00001509636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001270234,"about_ca_system_score_gemma":0.0001641698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005194349,"about_ca_topic_score_gemma":0.0001335785,"domain_scores_codex":[0.9972885,0.00007655817,0.000502606,0.001268119,0.0007044554,0.0001597859],"domain_scores_gemma":[0.9892853,0.0006718443,0.0002496898,0.009562922,0.0001996844,0.00003050849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002515845,0.0007798381,0.0065473,0.000175984,0.000226726,0.00001200442,0.00001957134,0.0007458166,0.001599433,0.532269,0.2964022,0.161197],"study_design_scores_gemma":[0.0002720912,0.00001041377,0.002868274,0.00002016402,0.0001194973,0.00003178735,0.01215368,0.2696049,0.0003905749,0.04242838,0.6718565,0.0002437872],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001645066,0.0004426891,0.9508569,0.0009917056,0.00003266639,0.0002332506,0.04517161,0.0002720632,0.0003540615],"genre_scores_gemma":[0.366873,0.0002260715,0.4295741,0.0004009508,0.00008180238,0.00004815603,0.2026613,0.00001534078,0.000119305],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5212829,"threshold_uncertainty_score":0.9937254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5594296950545075,"score_gpt":0.4357612867051186,"score_spread":0.1236684083493889,"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."}}