{"id":"W2190899134","doi":"10.14778/2850578.2850579","title":"Messing up with BART","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalability; Tuple; Computer science; Benchmarking; Completeness (order theory); Greedy algorithm; Process (computing); Benchmark (surveying); Property (philosophy); Scale (ratio); Control (management); Mathematical optimization; Algorithm; Database; Mathematics; Artificial intelligence; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.003346509,0.000110662,0.0001971539,0.00009599598,0.00009975187,0.0002522856,0.001211513,0.0000230524,0.00005341462],"category_scores_gemma":[0.0008722148,0.00005417162,0.00006151065,0.0005217349,0.0001322892,0.0005001387,0.0006481254,0.00007885478,0.0000786362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005142292,"about_ca_system_score_gemma":0.00004377445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000500094,"about_ca_topic_score_gemma":0.000008549571,"domain_scores_codex":[0.997272,0.00001683841,0.0003880643,0.0003015252,0.001818141,0.0002034088],"domain_scores_gemma":[0.998772,0.00007504292,0.0003329346,0.0002754912,0.0004345559,0.0001099547],"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":[0.0003150601,0.0002990874,0.01675562,0.00006978135,0.0001266563,0.00000160258,0.008404786,0.00009016968,0.004001799,0.2104359,0.7078582,0.05164132],"study_design_scores_gemma":[0.002260909,0.0003465919,0.005026209,0.0001844909,0.00009402323,0.00001936978,0.02731994,0.0003347774,0.07325927,0.1365034,0.7542753,0.0003756959],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5979908,0.0002299551,0.001364051,0.02234807,0.001578442,0.001216744,0.00002691926,0.0001204531,0.3751246],"genre_scores_gemma":[0.9887018,0.000004379363,0.001905079,0.0005365335,0.00005012651,0.00001995333,5.894613e-7,0.000007730512,0.008773807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.390711,"threshold_uncertainty_score":0.2432796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2772987549438379,"score_gpt":0.3926154589624858,"score_spread":0.1153167040186479,"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."}}