{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002801276,0.001008297,0.0009668847,0.0004537031,0.0008708768,0.0006499754,0.002374132,0.001553106,0.009121007],"category_scores_gemma":[0.007579637,0.000314993,0.001067012,0.0004556948,0.0005763379,0.001041295,0.001982745,0.002041778,0.001398544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007278278,"about_ca_system_score_gemma":0.0009421132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006030243,"about_ca_topic_score_gemma":0.006154631,"domain_scores_codex":[0.9991118,0.0003316193,0.00002960858,0.00009132323,0.000291157,0.0001444053],"domain_scores_gemma":[0.9972965,0.001709114,0.00006735359,0.0003568841,0.0004163097,0.0001537057],"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":[0.001492715,0.001309695,0.01002433,0.001148053,0.0004103957,0.0004337718,0.000252273,0.7747438,0.007035024,0.04909991,0.08572716,0.06832291],"study_design_scores_gemma":[0.0002655136,0.0006753078,0.001961864,0.00008166823,0.00002641758,0.00008768443,0.00007971129,0.9638209,0.006413412,0.007486245,0.01906273,0.00003846031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8135481,0.006347627,0.08664969,0.005595957,0.002022499,0.0005954718,0.0246789,0.005418362,0.05514349],"genre_scores_gemma":[0.8791584,0.001213982,0.08279981,0.001057553,0.0003426448,0.0008732643,0.02243618,0.001769993,0.01034823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009121007,"threshold_uncertainty_score":0.03051281,"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."}}