{"id":"W3202820157","doi":"","title":"An Extensible Benchmark Suite for Learning to Simulate Physical Systems","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Benchmark (surveying); Suite; Kernel (algebra); Physical system; Complement (music); Machine learning; Stability (learning theory); Distributed computing; Set (abstract data type); Artificial intelligence; Data mining","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":[0.0001670246,0.0001910333,0.0002786885,0.00008456315,0.0003997057,0.0009332889,0.0001194505,0.00004961071,0.00001423096],"category_scores_gemma":[0.00001556468,0.0001756599,0.00008702742,0.0003196095,0.00001474896,0.001912785,0.00002669332,0.0001905392,0.00003581745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002860654,"about_ca_system_score_gemma":0.00007334806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004070494,"about_ca_topic_score_gemma":2.727738e-7,"domain_scores_codex":[0.9986646,0.00007513139,0.0004604885,0.0002202466,0.0002488621,0.0003306297],"domain_scores_gemma":[0.9987807,0.00004802278,0.0002463492,0.0001864683,0.00055423,0.0001842698],"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":[0.0000270982,0.00003793171,0.0003149017,0.0002218549,0.00001275459,4.668827e-7,0.001276106,0.9592682,0.001771603,0.002266538,0.0008560389,0.03394657],"study_design_scores_gemma":[0.0003277739,0.00007733265,0.00004545347,0.0001053938,0.00001570259,0.000008741468,0.002345058,0.9702532,0.0007490354,0.00005221696,0.02580051,0.0002196122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8418247,0.0001376377,0.1511453,0.0002122309,0.001810302,0.001024917,0.00003800041,0.0002731368,0.003533858],"genre_scores_gemma":[0.9971415,6.022205e-7,0.0001256046,0.0001227746,0.001059363,0.0001434242,0.0002987684,0.00001917792,0.001088781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1553169,"threshold_uncertainty_score":0.8999727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01692231316719438,"score_gpt":0.2951060489753647,"score_spread":0.2781837358081703,"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."}}