{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001473688,0.0001137218,0.0001867812,0.0002528003,0.001892434,0.0001366952,0.0004085916,0.00005076869,0.0001339438],"category_scores_gemma":[0.0002045152,0.00007951388,0.0000471998,0.0001291992,0.0005723336,0.003471415,0.000154191,0.0001085423,0.0001034444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001584676,"about_ca_system_score_gemma":0.0002797383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006549461,"about_ca_topic_score_gemma":0.0001340145,"domain_scores_codex":[0.9984379,0.00008977062,0.0002489196,0.000216461,0.0007676621,0.0002393276],"domain_scores_gemma":[0.9970852,0.000123692,0.0001915316,0.0003789445,0.002146061,0.00007454547],"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":[0.0005074116,0.00004676558,0.000111975,0.0008734909,0.0002424041,0.00000354385,0.05461947,0.00008866021,0.001886146,0.7617435,0.1399521,0.03992452],"study_design_scores_gemma":[0.002366713,0.000289359,0.0004677566,0.0006738977,0.00005535341,0.00001737231,0.05717479,0.01551392,0.0001557794,0.00006068263,0.9229789,0.0002454822],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2001994,0.0007658186,0.4522527,0.01570029,0.002453534,0.006110585,0.01067425,0.0006655643,0.3111779],"genre_scores_gemma":[0.9936303,0.000005817911,0.002531681,0.00003179056,0.000340227,0.000008630166,0.0007344791,0.00000546101,0.00271154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.793431,"threshold_uncertainty_score":0.999407,"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."}}