{"id":"W3129829742","doi":"10.1109/icdmw51313.2020.00082","title":"SynC: A Copula based Framework for Generating Synthetic Data from Aggregated Sources","year":2020,"lang":"en","type":"article","venue":"","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; sync; Copula (linguistics); Data mining; Scalability; Synthetic data; Machine learning; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001194776,0.0001666476,0.0002061305,0.00002655361,0.0001691399,0.0006057596,0.002362662,0.00008794067,0.0001960703],"category_scores_gemma":[0.0006115804,0.0001364357,0.00003709454,0.000334553,0.00003256144,0.0004555029,0.0004802414,0.0001341169,0.00006685307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008063706,"about_ca_system_score_gemma":0.0001311559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005011272,"about_ca_topic_score_gemma":0.000009058293,"domain_scores_codex":[0.998433,0.0000364339,0.0002540528,0.0007911633,0.0002043259,0.0002810365],"domain_scores_gemma":[0.9982324,0.0003874415,0.0001236715,0.001010375,0.00006944473,0.0001766565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002137987,0.0006634041,0.008893566,0.001201057,0.0004455702,0.0002119115,0.005656293,0.00422801,0.02280932,0.5861873,0.06660952,0.3028802],"study_design_scores_gemma":[0.0001841909,0.00007246054,0.00004748052,0.00009351102,0.00001267797,0.000001143814,0.00003319416,0.9832492,0.00449813,0.01011521,0.001478623,0.0002141212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003378972,0.0002060399,0.9888557,0.006705514,0.0001330406,0.0001827712,0.00005853779,0.0003114603,0.0001680312],"genre_scores_gemma":[0.4593233,0.000002420334,0.5371763,0.003311423,0.0001147819,0.00001172826,0.00003706047,0.00000897607,0.00001411035],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9790213,"threshold_uncertainty_score":0.5841354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07637689567952773,"score_gpt":0.2882800888457438,"score_spread":0.2119031931662161,"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."}}