{"id":"W4402930836","doi":"10.26434/chemrxiv-2024-ctdm3","title":"Crash Testing Machine Learning Force Fields for Molecules, Materials, and Interfaces: Model Analysis in the TEA Challenge 2023","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Crash; Computer science; Nanotechnology; Materials science; Operating system","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":[0.003788648,0.0005331975,0.0008170762,0.00035007,0.0002420123,0.001081697,0.001320911,0.0003814111,0.0002025306],"category_scores_gemma":[0.0013349,0.0004001271,0.0001428541,0.0005153449,0.0001903672,0.0001021175,0.002034008,0.0009599021,0.00004014426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007955606,"about_ca_system_score_gemma":0.0001133875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005907632,"about_ca_topic_score_gemma":0.0002560682,"domain_scores_codex":[0.9965171,0.0003310869,0.0007617206,0.001334224,0.0004292316,0.0006266384],"domain_scores_gemma":[0.9980382,0.0006152607,0.0004030525,0.0007573164,0.0001033746,0.00008275214],"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":[0.00004918822,0.00006715934,0.0005741312,0.002209949,0.00009809515,0.00002663633,0.003281663,0.3974341,0.594804,0.0009240678,0.0002173774,0.0003135575],"study_design_scores_gemma":[0.0002121609,0.00008593708,0.0002135511,0.0003956878,0.0003785656,0.000008937312,0.0001714712,0.9324512,0.04767325,0.01776528,0.00007144024,0.0005724838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9833676,0.001101098,0.01140871,0.001228525,0.0006724551,0.0007776719,0.00008623875,0.000218879,0.001138792],"genre_scores_gemma":[0.9833886,0.00009910417,0.01478386,0.0001448712,0.0002156807,0.0003830324,0.00008690573,0.00006143579,0.0008365241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5471308,"threshold_uncertainty_score":0.9999553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03982651992374889,"score_gpt":0.2947916084681235,"score_spread":0.2549650885443746,"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."}}