{"id":"W2883256923","doi":"10.1145/3239570","title":"Evaluation-as-a-Service for the Computational Sciences","year":2018,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data science; Crowdsourcing; Field (mathematics); Executable; Domain (mathematical analysis); Service (business); Confidentiality; Big data; Work (physics); World Wide Web; Data mining; Computer security","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":[0.010552,0.00004053088,0.00006271511,0.00006530986,0.000399626,0.000363438,0.0009756603,0.00001806932,0.00001545962],"category_scores_gemma":[0.00134008,0.0000246838,0.00001346201,0.0002195429,0.00007974594,0.008163187,0.0001553626,0.00006479221,0.00001707799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001219836,"about_ca_system_score_gemma":0.0003050714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002933175,"about_ca_topic_score_gemma":0.000006664369,"domain_scores_codex":[0.9987254,0.0001248028,0.0004169543,0.00006986487,0.0006014598,0.00006148206],"domain_scores_gemma":[0.9973268,0.0005496059,0.0005627371,0.0002953162,0.001233146,0.00003242395],"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":[0.00002100077,0.00001909103,0.0004669597,0.00002228125,0.00002688163,1.628289e-8,0.001999551,0.0005775252,0.000008514745,0.2633557,0.008554601,0.7249479],"study_design_scores_gemma":[0.0003362994,0.0001018782,0.026372,0.000007697025,0.00001453535,0.00001765218,0.0003301192,0.8309835,0.000006493758,0.009466233,0.1323229,0.0000406437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005839112,0.00007849322,0.9734832,0.01920679,0.0002177447,0.0001150647,0.00004469369,0.000008596578,0.001006279],"genre_scores_gemma":[0.8973797,0.00004238575,0.09706096,0.005113926,0.0002490061,0.000003672358,0.0001436514,0.000001312381,0.000005379151],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8915406,"threshold_uncertainty_score":0.5918114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2061877675601156,"score_gpt":0.4578079204475153,"score_spread":0.2516201528873997,"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."}}