{"id":"W4415702568","doi":"10.1016/j.cma.2025.118502","title":"Generalizable machine learning potentials for quantum-accurate predictions of non-equilibrium behavior in 2D materials","year":2025,"lang":"en","type":"article","venue":"Computer Methods in Applied Mechanics and Engineering","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"Argonne National Laboratory; Basic Energy Sciences; Office of Naval Research; Northwestern University; Sandia National Laboratories; Laboratory Directed Research and Development; U.S. Department of Energy; National Nuclear Security Administration; Office of Science; National Science Foundation","keywords":"Benchmark (surveying); Artificial neural network; Multiscale modeling; Transformative learning; Domain (mathematical analysis); Work (physics); Ab initio; Deep learning; Potential field","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":[0.003073179,0.0002318206,0.0005602679,0.0003925061,0.00006635425,0.0001182006,0.0003279371,0.0001251749,0.00003752531],"category_scores_gemma":[0.000112546,0.0002387122,0.00003965788,0.0003778788,0.00002034743,0.00009789717,0.0003456647,0.0001575714,0.00000101784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004708755,"about_ca_system_score_gemma":0.00003547841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008381218,"about_ca_topic_score_gemma":0.000003076386,"domain_scores_codex":[0.9981596,0.0001344995,0.0006995968,0.0004783119,0.0001214131,0.0004065409],"domain_scores_gemma":[0.9992455,0.0002505229,0.0001640625,0.000249434,0.00003659864,0.00005383201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002117917,0.00002325023,0.00002080789,0.0002073547,0.000003095812,0.000001127071,0.00007271217,0.3072106,0.67893,0.01289243,0.000003910124,0.0006135837],"study_design_scores_gemma":[0.0004204977,0.00004854463,0.0003246808,0.00009378699,0.00001583527,0.000002639666,0.00001029602,0.7381377,0.2592678,0.001385255,0.0001368232,0.0001561511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.198713,0.00008387932,0.7992096,0.0000175176,0.001378743,0.0004858994,0.00002040352,0.00007069502,0.00002029592],"genre_scores_gemma":[0.3307513,0.00002588274,0.6689038,0.00001883256,0.00005171942,0.000200065,0.00001002546,0.00002252467,0.00001582073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4309271,"threshold_uncertainty_score":0.9734402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01699517140551311,"score_gpt":0.3112421537914737,"score_spread":0.2942469823859606,"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."}}