{"id":"W4402927202","doi":"10.26434/chemrxiv-2024-jhm5l","title":"Crash Testing Machine Learning Force Fields for Molecules, Materials, and Interfaces: Molecular Dynamics in the TEA Challenge 2023","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Crash; Molecular dynamics; Nanotechnology; Computer science; Materials science; Engineering; Chemistry; Computational chemistry","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003198812,0.0005701692,0.0006378614,0.0001779828,0.000213179,0.001081701,0.001375318,0.0004316738,0.0001528067],"category_scores_gemma":[0.001711402,0.0004465915,0.00008747949,0.0002320931,0.0002300414,0.00008837185,0.00229055,0.001151569,0.00005755523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002182577,"about_ca_system_score_gemma":0.0001594994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005703886,"about_ca_topic_score_gemma":0.0002145697,"domain_scores_codex":[0.9965379,0.0003906205,0.0007162314,0.001254824,0.0004235996,0.0006768081],"domain_scores_gemma":[0.9981354,0.0005907064,0.000373906,0.0007164488,0.00009977783,0.00008379573],"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":[0.0000585221,0.0000827078,0.0003216219,0.004414174,0.000028464,0.0001309356,0.002340295,0.01514657,0.9705801,0.005679642,0.0001699453,0.001047021],"study_design_scores_gemma":[0.0008732752,0.000504004,0.0003156445,0.002959415,0.0002083228,0.0001286268,0.001008099,0.6065949,0.3039027,0.08076153,0.0007489707,0.001994635],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9870448,0.001630663,0.00426911,0.002044376,0.001555615,0.001087388,0.00008123898,0.0002504163,0.00203644],"genre_scores_gemma":[0.9884689,0.00008089672,0.009838507,0.0001976011,0.0002349681,0.0004132966,0.0001082817,0.00009478001,0.0005627826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6666775,"threshold_uncertainty_score":0.9999553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02281019706814085,"score_gpt":0.2761234237653367,"score_spread":0.2533132266971959,"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."}}