{"id":"W3208707586","doi":"10.1021/acs.jctc.1c00647","title":"Linear Atomic Cluster Expansion Force Fields for Organic Molecules: Beyond RMSE","year":2021,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"UK Research and Innovation; Engineering and Physical Sciences Research Council; AstraZeneca","keywords":"Extrapolation; Force field (fiction); Benchmark (surveying); Potential energy surface; Statistical physics; Cluster (spacecraft); Smoothness; Computer science; Cluster expansion; Potential energy; Physics; Algorithm; Mathematics; Molecule; Artificial intelligence; Classical mechanics; Thermodynamics; Quantum mechanics; Mathematical analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.001203508,0.00008275132,0.0001809625,0.00003027821,0.00006343873,0.00007479012,0.0001227452,0.00006865933,0.0001319908],"category_scores_gemma":[0.0006096589,0.00006660924,0.00005580901,0.0000703954,0.00006183825,0.0001754061,0.0000622633,0.0001077197,0.000005967336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001914382,"about_ca_system_score_gemma":0.00006259404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.36041e-7,"about_ca_topic_score_gemma":8.711373e-8,"domain_scores_codex":[0.9990324,0.0001946481,0.000330375,0.0001468295,0.0001722418,0.0001235451],"domain_scores_gemma":[0.998939,0.000473841,0.0002397989,0.00007195634,0.0002083027,0.00006709658],"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":[0.0002375049,0.00002474461,0.000009293921,0.00004191608,0.000003978747,0.000005523011,0.0003168964,0.001875103,0.9946752,0.001707059,0.000114563,0.0009882721],"study_design_scores_gemma":[0.0005826763,0.00009552796,0.00002267011,0.00005101883,0.00002120565,0.0001833003,0.00008981331,0.01969625,0.8541831,0.1249275,0.00005966755,0.00008728858],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6547459,0.00007315804,0.3445784,0.0002483967,0.0002707858,0.00003926603,0.000001414277,0.000008004426,0.0000346436],"genre_scores_gemma":[0.97004,0.000007660982,0.02911217,0.0005445851,0.0002092479,0.000001429759,0.000003828098,0.000008680322,0.00007242399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3154662,"threshold_uncertainty_score":0.2716246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007661685857072209,"score_gpt":0.2739616576948919,"score_spread":0.2662999718378197,"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."}}