{"id":"W4401108396","doi":"10.1007/978-3-031-66431-1_33","title":"DataAssist: A Machine Learning Approach to Data Cleaning and Preparation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004855413,0.0003256864,0.0006293709,0.0003146099,0.000156038,0.001600477,0.0008145367,0.0003108016,0.00002139012],"category_scores_gemma":[0.0005619535,0.0002387723,0.00003523552,0.0001806121,0.00006187198,0.0002670818,0.001811038,0.0006951325,0.00002778803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003271808,"about_ca_system_score_gemma":0.00001697183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002157087,"about_ca_topic_score_gemma":0.0008140188,"domain_scores_codex":[0.9966635,0.0001613024,0.0008070609,0.001412182,0.0007063927,0.0002496309],"domain_scores_gemma":[0.9973891,0.0009278383,0.000254589,0.001269905,0.00004370719,0.0001148577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001775537,0.00003581564,0.0003043432,0.0007984965,0.0002812731,0.00007219247,0.002268762,0.4530181,0.000002218037,0.1916698,0.04027536,0.3110961],"study_design_scores_gemma":[0.00006813752,0.00003750734,0.00001081986,0.0003110411,0.00003556499,0.00001612792,0.00003080857,0.5458704,3.200011e-8,0.005532523,0.4478944,0.00019265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003099672,0.03540276,0.7853817,0.0003928331,0.001270201,0.001165113,0.0003942387,0.00008892138,0.1758733],"genre_scores_gemma":[0.816712,0.002576904,0.002493234,0.0009268858,0.002565784,0.00006763495,0.005668566,0.0001597405,0.1688293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.816681,"threshold_uncertainty_score":0.999436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1569908050652264,"score_gpt":0.3670280918147778,"score_spread":0.2100372867495514,"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."}}