{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00611038,0.002630425,0.0009439884,0.00225923,0.0005202353,0.002080171,0.003615263,0.00192359,0.003640026],"category_scores_gemma":[0.01868859,0.0005248387,0.001145079,0.003143262,0.0008956587,0.003163198,0.002414535,0.001408306,0.001476714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00176308,"about_ca_system_score_gemma":0.001533925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01046444,"about_ca_topic_score_gemma":0.007404339,"domain_scores_codex":[0.9921204,0.002551879,0.0007819535,0.00128907,0.002680118,0.0005765244],"domain_scores_gemma":[0.98704,0.006216977,0.0006797522,0.003102593,0.002433838,0.0005268338],"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":[0.006503452,0.004065144,0.03161249,0.00466084,0.001316289,0.0009807074,0.0009772708,0.488875,0.04750623,0.02053248,0.1531153,0.2398549],"study_design_scores_gemma":[0.0006835866,0.002401533,0.01188796,0.0001805891,0.0002223319,0.0004919429,0.0005092009,0.8957135,0.04601941,0.008708037,0.03303925,0.0001426639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7397299,0.006299548,0.1030298,0.001447171,0.0009512709,0.0007023503,0.03110547,0.0883353,0.02839913],"genre_scores_gemma":[0.813895,0.001211896,0.0972472,0.0004858897,0.00007745012,0.0003710889,0.07605705,0.006434268,0.004220016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01046444,"threshold_uncertainty_score":0.03231519,"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."}}