{"id":"W2591700809","doi":"10.14778/3137628.3137631","title":"HoloClean","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":454,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Leverage (statistics); Computer science; Probabilistic logic; Inference; Tuple; Data mining; Statistical model; Machine learning; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002889255,0.00009153604,0.0001748362,0.00006363964,0.0004877773,0.000574952,0.003819774,0.00002560655,0.0001365203],"category_scores_gemma":[0.002600801,0.00005030314,0.0001240365,0.0001049913,0.0002273848,0.0005424615,0.001896428,0.00007774967,0.0001689178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002283535,"about_ca_system_score_gemma":0.00001058732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008488551,"about_ca_topic_score_gemma":0.000009997489,"domain_scores_codex":[0.9979413,0.000008699308,0.000385802,0.0002964365,0.001182719,0.0001850265],"domain_scores_gemma":[0.9982606,0.00006705589,0.0006783588,0.0007305088,0.0002083848,0.00005513363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000058013,0.000232636,0.03047157,0.0000459695,0.00006966102,9.36723e-7,0.001220038,0.000004676824,0.008127528,0.494772,0.3383624,0.1266346],"study_design_scores_gemma":[0.0007907638,0.00009693258,0.1417979,0.00007219232,0.0000428309,0.000004126095,0.002640583,0.0001000451,0.08212352,0.2827421,0.4893618,0.0002272432],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.581025,0.00004108088,0.00008783965,0.02444974,0.001043692,0.000571433,0.00002828331,0.0000391925,0.3927137],"genre_scores_gemma":[0.9901442,0.00001429161,0.0004617177,0.0003847261,0.0000597516,0.00001297408,2.207737e-7,0.000005049163,0.008917073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4091192,"threshold_uncertainty_score":0.7098153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2284211371904144,"score_gpt":0.4286142488382545,"score_spread":0.2001931116478401,"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."}}