{"id":"W4400048270","doi":"10.1039/d4sc00690a","title":"Machine-learned molecular mechanics force fields from large-scale quantum chemical data","year":2024,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; York University; Office of Advanced Cyberinfrastructure; Memorial Sloan-Kettering Cancer Center; New York University; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Preprint; Force field (fiction); License; Field (mathematics); Computer science; Scale (ratio); Statistical physics; Physics; Artificial intelligence; Quantum mechanics; Mathematics; World Wide Web","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007445989,0.0006771596,0.0007261934,0.0007000043,0.0004847042,0.0006060971,0.002191202,0.001270419,0.002847454],"category_scores_gemma":[0.002573595,0.0004690232,0.0006271896,0.0007901324,0.0005983194,0.001081279,0.0008090575,0.001865002,0.0006446375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008292383,"about_ca_system_score_gemma":0.001517342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006402641,"about_ca_topic_score_gemma":0.01096287,"domain_scores_codex":[0.9997596,0.00006650471,0.00001143573,0.00004464213,0.00009576049,0.00002212082],"domain_scores_gemma":[0.9993611,0.0002875741,0.00005735323,0.0001206153,0.0001243942,0.00004905251],"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":[0.00003187181,0.00005394145,0.0005476403,0.00008541809,0.0000356884,0.00007817465,0.00002392143,0.939137,0.003854921,0.01646623,0.002819819,0.0368654],"study_design_scores_gemma":[0.000008428695,0.000006019318,0.00005802963,0.000003949278,0.000001557181,0.000005866236,0.000002735082,0.9940022,0.000515985,0.004495529,0.0008959201,0.000003812809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06273411,0.0005455334,0.9266258,0.0006155284,0.0001598033,0.0001499357,0.001160486,0.002615476,0.005393282],"genre_scores_gemma":[0.4287253,0.0006430019,0.5620156,0.0003561636,0.00009876236,0.000496519,0.00319881,0.0007320878,0.003733644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006402641,"threshold_uncertainty_score":0.01273078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01931325086047909,"score_gpt":0.2985415328073301,"score_spread":0.279228281946851,"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."}}