{"id":"W3161168558","doi":"10.1145/3447541","title":"TabReformer: Unsupervised Representation Learning for Erroneous Data Detection","year":2021,"lang":"en","type":"article","venue":"ACM/IMS Transactions on Data Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Computer science; Pipeline (software); Range (aeronautics); Representation (politics); Encoder; Probabilistic logic; Artificial intelligence; Tuple; Machine learning; External Data Representation; Mixture model; Task (project management); Data mining; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001351602,0.0001817852,0.0001754613,0.0002968399,0.001180905,0.0006239695,0.008993422,0.00007802892,0.00003853769],"category_scores_gemma":[0.001316186,0.0001854786,0.00003765209,0.002412387,0.0002669088,0.008841366,0.0005728247,0.0003222874,0.00005225712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001456144,"about_ca_system_score_gemma":0.0004934566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007904704,"about_ca_topic_score_gemma":0.0001300507,"domain_scores_codex":[0.9964529,0.00009665756,0.000385446,0.001890242,0.0007226235,0.0004520883],"domain_scores_gemma":[0.9896311,0.0003339193,0.0001586782,0.009361732,0.0003763425,0.0001382491],"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":[0.00002093968,0.0001845431,0.00003088569,0.00002081667,0.00001715106,0.000006217449,0.0001851882,0.0008374485,0.1407135,0.0009871443,0.000536599,0.8564596],"study_design_scores_gemma":[0.0004304949,0.0001297495,0.0007790657,0.00003148503,0.00002658232,0.00009618382,0.0002450694,0.6219256,0.3420904,0.0009421242,0.03294817,0.0003550824],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007982398,0.0000337901,0.9952773,0.001753505,0.0005526813,0.0003741102,0.0004372676,0.0005666218,0.0002064762],"genre_scores_gemma":[0.6590311,0.0002256095,0.3387251,0.0002876148,0.00005390662,0.00009201417,0.001274289,0.00001949815,0.0002908475],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8561046,"threshold_uncertainty_score":0.9963684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1334307593239981,"score_gpt":0.3654867943384096,"score_spread":0.2320560350144115,"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."}}