{"id":"W6983458742","doi":"","title":"Messing Up with BART: Error Generation for Evaluating Data-CleaningAlgorithms","year":2016,"lang":"en","type":"article","venue":"CINECA IRIS Institutional Research Information System (University of Basilicata)","topic":"German Literature and Culture Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmarking; Scalability; Scale (ratio); Greedy algorithm; Benchmark (surveying); Control (management)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02653647,0.001998548,0.001928657,0.004059977,0.001242343,0.002743679,0.003588371,0.003398894,0.001510047],"category_scores_gemma":[0.1199661,0.0007962115,0.001254031,0.003542913,0.00234322,0.003798899,0.003616479,0.00238661,0.0006457016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001435251,"about_ca_system_score_gemma":0.001940056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00255104,"about_ca_topic_score_gemma":0.002705938,"domain_scores_codex":[0.9700215,0.01547541,0.002791664,0.003715198,0.006995993,0.00100024],"domain_scores_gemma":[0.8364558,0.1225715,0.007762689,0.0237387,0.007973011,0.001498309],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003548611,0.001537155,0.04247596,0.001688736,0.001103954,0.0002424355,0.0007807179,0.6821755,0.008994608,0.01120183,0.01717912,0.2290714],"study_design_scores_gemma":[0.0002322765,0.0008374548,0.004207836,0.00006914246,0.00010324,0.000180772,0.0002159863,0.9672281,0.01322645,0.01147964,0.002167941,0.00005115945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4566902,0.002467737,0.516779,0.001067962,0.0005255328,0.000941593,0.004823741,0.01260514,0.004099106],"genre_scores_gemma":[0.6353793,0.0002778448,0.357181,0.0002823844,0.0001285421,0.0004866038,0.004788272,0.0008091294,0.0006670147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02653647,"threshold_uncertainty_score":0.14034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3148774060364035,"score_gpt":0.3549844233923339,"score_spread":0.04010701735593042,"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."}}