{"id":"W4407081389","doi":"10.1039/d4sc06530a","title":"Crash testing machine learning force fields for molecules, materials, and interfaces: molecular dynamics 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":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"H2020 European Research Council; Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea; Korea University; Klaus Tschira Stiftung; University of Toronto; Bundesministerium für Bildung und Forschung; Fonds National de la Recherche Luxembourg; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Université du Luxembourg; Alexander von Humboldt-Stiftung","keywords":"Molecular dynamics; Molecule; Nanotechnology; Crash; Force field (fiction); Computer science; Materials science; Chemical physics; Chemistry; Computational chemistry; Artificial intelligence; Organic chemistry","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":[0.003156071,0.0002180989,0.0002628796,0.0001243284,0.0003766343,0.0005182899,0.001464605,0.0001010597,0.0000524693],"category_scores_gemma":[0.004178971,0.0001607056,0.00002591409,0.0008045979,0.0008235706,0.0002546163,0.0006084506,0.0002683929,0.00001028393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001961146,"about_ca_system_score_gemma":0.0001529925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002422253,"about_ca_topic_score_gemma":0.00004808267,"domain_scores_codex":[0.9976649,0.0001343123,0.000390705,0.0007540334,0.0004174029,0.0006386059],"domain_scores_gemma":[0.9987153,0.0006022059,0.0001383546,0.0003626097,0.0001036633,0.00007789356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001497285,0.00002629018,0.0004059525,0.00008856114,8.699303e-7,0.000004477869,0.0002632343,0.0004739763,0.9921704,0.005706918,0.0000160476,0.0008282815],"study_design_scores_gemma":[0.0003687682,0.0001092712,0.0004245426,0.000188653,0.000009586985,0.0000174271,0.0003474371,0.1443681,0.8453972,0.008291609,0.000178709,0.0002987206],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9844286,0.000157438,0.009936994,0.001704627,0.0003373277,0.0004146138,0.00001629984,0.00007826704,0.002925777],"genre_scores_gemma":[0.9892206,0.00000896818,0.0100599,0.0003986718,0.00003397181,0.00008173069,0.000006481423,0.00001081358,0.0001789095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1467732,"threshold_uncertainty_score":0.6553383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244487347374675,"score_gpt":0.2734310360041148,"score_spread":0.2609861625303681,"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."}}