{"id":"W2041132750","doi":"10.5555/1400549.1400617","title":"Experiences with the DEVStone benchmark","year":2008,"lang":"en","type":"article","venue":"Spring Simulation Multiconference","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Benchmark (surveying); DEVS; Computer science; Modular design; Metric (unit); Variety (cybernetics); Set (abstract data type); Process (computing); Modeling and simulation; Discrete event simulation; Distributed computing; Simulation; Programming language; Artificial intelligence; Engineering","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":[0.0005819965,0.0001448053,0.0001640308,0.0001184646,0.0007703987,0.0001612445,0.0007103345,0.00005362986,0.0005467233],"category_scores_gemma":[0.0005616893,0.00008071102,0.00005610644,0.0006912119,0.0003498,0.0003413721,0.00008578072,0.0001364986,0.0001645254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002370828,"about_ca_system_score_gemma":0.0000798121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008265804,"about_ca_topic_score_gemma":0.0000280993,"domain_scores_codex":[0.99792,0.00008851161,0.0004073459,0.0004096482,0.0009660836,0.0002083543],"domain_scores_gemma":[0.9966937,0.001730572,0.0002208542,0.0007761545,0.0004968166,0.00008184553],"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":[0.0001046389,0.0001978242,0.1867332,0.000004794972,0.00003111251,0.00001193983,0.04995452,0.6635633,0.00139324,0.02593354,0.0007290688,0.0713429],"study_design_scores_gemma":[0.0004465257,0.00006215881,0.2187792,0.00001523633,0.000009045521,0.00000824178,0.00826249,0.7489484,0.002721905,0.001303951,0.0191043,0.0003385037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7637208,0.00002009858,0.2335495,0.0005166614,0.00003911733,0.0002610703,0.000001258934,0.0001081133,0.001783387],"genre_scores_gemma":[0.9932904,0.000003173265,0.005606995,0.0001927432,0.00005251983,0.00009768164,0.000001457856,0.000009477717,0.0007456006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2295696,"threshold_uncertainty_score":0.5986237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1688163703236138,"score_gpt":0.4044594372441228,"score_spread":0.235643066920509,"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."}}