{"id":"W4392295981","doi":"10.1038/s41467-024-45629-w","title":"Learning stochastic dynamics and predicting emergent behavior using transformers","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"Micro and Nano Robotics","field":"Physics and Astronomy","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Standards Association; University of Ottawa","funders":"Lawrence Berkeley National Laboratory; Office of Science; Natural Sciences and Engineering Research Council of Canada; Vlaamse regering; Universiteit Gent; Basic Energy Sciences; Fonds Wetenschappelijk Onderzoek; National Energy Research Scientific Computing Center; Vlaams Supercomputer Centrum; Belgian American Educational Foundation; U.S. Department of Energy","keywords":"Statistical physics; Computer science; Granularity; Transformer; Dynamical systems theory; Non-equilibrium thermodynamics; Artificial neural network; Phase space; Monte Carlo method; Artificial intelligence; Physics; Mathematics","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":[0.00008793768,0.00009019558,0.00008171066,0.0000626375,0.0003406769,0.00006001241,0.0001789876,0.00007329493,0.00003972605],"category_scores_gemma":[0.000005492753,0.00008939631,0.0000519249,0.0001756848,0.0000531291,0.0000870794,0.00008674763,0.000886951,0.000003373559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003784407,"about_ca_system_score_gemma":0.0000468275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004801378,"about_ca_topic_score_gemma":0.00005124775,"domain_scores_codex":[0.9995197,0.00003301276,0.0001365134,0.0001183918,0.00006411646,0.0001282752],"domain_scores_gemma":[0.9995592,0.00008746978,0.00002673059,0.0002462889,0.00003452589,0.00004580187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001234053,0.0005449468,0.2060793,0.0001587425,0.0006717105,0.000003932718,0.007892554,0.01323405,0.01638449,0.4463847,0.0006015691,0.3080317],"study_design_scores_gemma":[0.0001666721,0.00002323052,0.001852653,0.0001295133,0.0003412112,0.000007114963,0.001797516,0.9919165,0.0001230709,0.000262271,0.003141682,0.0002385737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7478833,0.01492157,0.2282712,0.001270183,0.0007724417,0.0006526494,0.0001849855,0.0002627778,0.005780829],"genre_scores_gemma":[0.996667,0.00006262826,0.002865146,0.00000882794,0.00005838115,0.00001407523,0.0001370785,0.00001864328,0.0001682534],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9786825,"threshold_uncertainty_score":0.385341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.015823852104318,"score_gpt":0.306847140692133,"score_spread":0.291023288587815,"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."}}