{"id":"W2578360098","doi":"10.1007/s10270-016-0571-8","title":"The Train Benchmark: cross-technology performance evaluation of continuous model queries","year":2017,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Scalability; Metamodeling; Implementation; Automotive industry; Graph; Programming language; Software engineering; Theoretical computer science; Database","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":[0.003233734,0.0002753437,0.0004001518,0.000164704,0.00108622,0.0005700169,0.002705307,0.0002399525,7.398769e-7],"category_scores_gemma":[0.0002776789,0.0002255776,0.0001064446,0.0001454282,0.0002239247,0.001051562,0.000541229,0.0002924385,0.000002926085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001566459,"about_ca_system_score_gemma":0.0002830685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001091871,"about_ca_topic_score_gemma":0.00001062556,"domain_scores_codex":[0.9972894,0.00008667284,0.0007079028,0.0005232916,0.0009097123,0.0004830054],"domain_scores_gemma":[0.9957361,0.00007078965,0.0005125231,0.002483927,0.001130766,0.00006595295],"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":[0.000005317044,0.00001212626,0.003018379,0.00006009287,0.00002332143,9.257005e-7,0.0003616379,0.8698493,0.0001163052,0.03906056,0.00002669736,0.08746535],"study_design_scores_gemma":[0.0002616457,0.00004389343,0.0001708825,0.0002434584,0.00001710925,0.00001533116,0.00001593251,0.9943726,0.0003643168,0.004009383,0.0002421421,0.0002432896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2580598,0.000915612,0.7391867,0.00007020575,0.0004700738,0.000477204,0.000006370956,0.0007356263,0.00007840538],"genre_scores_gemma":[0.8416904,0.00006026476,0.1578407,0.000005235461,0.00004672977,0.0002487576,0.000002467001,0.00002764049,0.00007782467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5836306,"threshold_uncertainty_score":0.919879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0399046633489821,"score_gpt":0.3052448455659134,"score_spread":0.2653401822169312,"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."}}