{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00490504,0.002054731,0.001743209,0.004225355,0.001424052,0.0049399,0.005091551,0.001689097,0.02386197],"category_scores_gemma":[0.01016898,0.001900572,0.002288957,0.004625213,0.001128601,0.003879656,0.004841836,0.004126305,0.02075648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006136702,"about_ca_system_score_gemma":0.002257696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002277245,"about_ca_topic_score_gemma":0.003984164,"domain_scores_codex":[0.9969679,0.0006470388,0.0002809574,0.0006015694,0.001372545,0.0001299868],"domain_scores_gemma":[0.9950184,0.002490016,0.000175916,0.001308752,0.0008517411,0.0001551443],"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":[0.0001382015,0.000137107,0.0006782493,0.0005614226,0.0001571015,0.0001670719,0.0003078593,0.007922652,0.006863553,0.02282161,0.1215915,0.8386536],"study_design_scores_gemma":[0.0000920832,0.0001252273,0.001667518,0.0003180771,0.0001683381,0.001003197,0.0002415982,0.2708102,0.0565712,0.1582568,0.5105139,0.0002318396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003072309,0.0002010096,0.9792738,0.0002299276,0.0001174725,0.0001167563,0.001048413,0.01724654,0.001458911],"genre_scores_gemma":[0.003529255,0.000372494,0.9841622,0.0002478533,0.0000904956,0.0002188228,0.002852758,0.002881525,0.005644514],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02386197,"threshold_uncertainty_score":0.07982624,"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."}}