{"id":"W4407320154","doi":"10.1039/d4sc06529h","title":"Crash testing machine learning force fields for molecules, materials, and interfaces: model analysis in the TEA Challenge 2023","year":2025,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"Institute for Information and Communications Technology Promotion; Engineering and Physical Sciences Research Council; Klaus Tschira Stiftung; University of Toronto; Bundesministerium für Bildung und Forschung; European Research Council; Fonds De La Recherche Scientifique - FNRS; Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea; Fonds National de la Recherche Luxembourg; Canada First Research Excellence Fund; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation; Université du Luxembourg; Korea University; Horizon 2020 Framework Programme; Canadian Institute for Advanced Research; European Commission; Alexander von Humboldt-Stiftung","keywords":"Crash; Computer science; Force field (fiction); Nanotechnology; Engineering; Artificial intelligence; Materials science","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":[0.003681812,0.0002031765,0.0003287574,0.0002334034,0.0004259182,0.0005152404,0.00141317,0.0000893228,0.00006570483],"category_scores_gemma":[0.003338191,0.0001438029,0.00004081606,0.00173745,0.0007025838,0.0002913308,0.0005415807,0.0002246272,0.000007123457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007369254,"about_ca_system_score_gemma":0.0001103127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002395922,"about_ca_topic_score_gemma":0.0000550449,"domain_scores_codex":[0.9976603,0.0001130903,0.0004105748,0.0007961636,0.0004239511,0.0005958761],"domain_scores_gemma":[0.9986669,0.0006239052,0.0001466586,0.0003788827,0.0001062995,0.00007735648],"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":[0.00001516059,0.00002603272,0.0008434977,0.00005430071,0.00000331971,0.00000119644,0.0004333203,0.01490875,0.9821399,0.001242307,0.00002395717,0.000308226],"study_design_scores_gemma":[0.0001922817,0.00004123554,0.0006013479,0.00005497133,0.0000334861,0.000002785873,0.0001244623,0.6080796,0.3867573,0.003892116,0.00003817834,0.0001822087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9713252,0.0001055356,0.02539001,0.001026449,0.0001504745,0.0002999349,0.00001710024,0.00006792256,0.001617423],"genre_scores_gemma":[0.9840045,0.00001086827,0.01530217,0.0003080788,0.00003108451,0.00007565662,0.000005262955,0.000007183209,0.0002552054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5953826,"threshold_uncertainty_score":0.5864111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02172215766477606,"score_gpt":0.2920433356796108,"score_spread":0.2703211780148347,"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."}}