{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005011081,0.0009368419,0.0006205288,0.0005255532,0.0009663394,0.001100206,0.002669998,0.00191535,0.007387809],"category_scores_gemma":[0.014587,0.0004334232,0.001278254,0.0005614351,0.0006104614,0.001677145,0.002169495,0.002298278,0.001826977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008482262,"about_ca_system_score_gemma":0.001352629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009139946,"about_ca_topic_score_gemma":0.01106764,"domain_scores_codex":[0.9986624,0.0005088654,0.00006964675,0.0001776824,0.0004164947,0.0001650262],"domain_scores_gemma":[0.9958165,0.002154098,0.0001329791,0.0009169822,0.0008241892,0.0001552335],"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":[0.001195677,0.001080177,0.02220492,0.001299786,0.0004367095,0.0003768211,0.000533303,0.673861,0.008851477,0.05359768,0.1248936,0.111669],"study_design_scores_gemma":[0.0001477634,0.0004278188,0.003451211,0.00009802693,0.00003017777,0.00008929405,0.0001436057,0.9517658,0.0104861,0.01046866,0.02284266,0.00004883256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7426038,0.002619923,0.1615411,0.00465359,0.001733979,0.0007643865,0.03061485,0.01239504,0.04307339],"genre_scores_gemma":[0.844598,0.0004990592,0.1169296,0.0007856197,0.0001473234,0.0008599597,0.0272748,0.002083349,0.006822336],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009139946,"threshold_uncertainty_score":0.02650148,"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."}}