{"id":"W4224288101","doi":"10.1145/3524303","title":"Contextual Data Cleaning with Ontology Functional Dependencies","year":2022,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; University of Waterloo; McMaster University","funders":"","keywords":"Ontology; Axiom; Computer science; Functional dependency; Inference; Dependency (UML); Set (abstract data type); Dependency theory (database theory); Relation (database); Data mining; Artificial intelligence; Relational database; Mathematics","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":[0.01965825,0.00007485142,0.0002399641,0.000215312,0.0003718963,0.0003486891,0.002125288,0.00002035389,0.0007801087],"category_scores_gemma":[0.002353606,0.00005090814,0.00002005252,0.0002561655,0.00009541355,0.01824009,0.00278619,0.0002601177,0.00002295756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000309135,"about_ca_system_score_gemma":0.0001774111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007038731,"about_ca_topic_score_gemma":0.0001273336,"domain_scores_codex":[0.9960566,0.0005074446,0.001294394,0.0001704441,0.001851863,0.0001192398],"domain_scores_gemma":[0.9962589,0.0007830739,0.001380099,0.00118925,0.0003076586,0.00008101842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001447198,0.0001606272,0.008092613,0.00004342758,0.0001939934,0.00001232651,0.003837462,0.0003811502,0.00001173061,0.106944,0.4624178,0.4164577],"study_design_scores_gemma":[0.000935105,0.0002212702,0.02922946,0.000005750696,0.00002535382,0.0002069625,0.04179703,0.002337459,0.000001951253,0.001926091,0.923215,0.00009858714],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1877855,0.000399644,0.7680259,0.01547386,0.00177725,0.0003985738,0.01313973,0.00003932301,0.01296018],"genre_scores_gemma":[0.9888012,0.000051509,0.004055404,0.004526499,0.0001055607,0.000001724062,0.002280913,0.000002927509,0.0001742654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8010157,"threshold_uncertainty_score":0.9954913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4677702605003999,"score_gpt":0.452390842963974,"score_spread":0.01537941753642585,"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."}}