{"id":"W4237462218","doi":"10.33774/chemrxiv-2021-7qlf5-v4","title":"Linear Atomic Cluster Expansion Force Fields for Organic Molecules: beyond RMSE","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":13,"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); Smoothness; Cluster (spacecraft); Statistical physics; Transferability; Potential energy surface; Potential energy; Computer science; Physics; Mathematics; Molecule; Artificial intelligence; Classical mechanics; Machine learning; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001493204,0.0005540722,0.0007472175,0.0001350332,0.0002729737,0.0007183962,0.001445048,0.0006591964,0.006964785],"category_scores_gemma":[0.000803039,0.0004843941,0.0002646393,0.0001590657,0.0001519926,0.0002390306,0.002567979,0.0005380741,0.0003503362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000131527,"about_ca_system_score_gemma":0.0005092912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001991257,"about_ca_topic_score_gemma":0.0001303943,"domain_scores_codex":[0.9960053,0.0003022232,0.0008066188,0.001551296,0.0006004694,0.000734071],"domain_scores_gemma":[0.997289,0.0002797951,0.000432635,0.001467523,0.0003349232,0.0001961157],"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":[0.0000754937,0.00006801225,0.00005508721,0.0006649571,0.00001344867,0.00001434093,0.000909698,0.0159259,0.9783546,0.0003350133,0.003391566,0.000191884],"study_design_scores_gemma":[0.0009403727,0.0001888867,0.0001206592,0.0003829075,0.00009596952,0.00004483423,0.0003357956,0.2002317,0.7890255,0.00620679,0.001157039,0.00126947],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6493156,0.0001005438,0.3437686,0.000875048,0.003941448,0.0008210287,0.00004556951,0.0002874807,0.0008446995],"genre_scores_gemma":[0.7472388,0.00005277319,0.2386257,0.003040025,0.0008361847,0.0002996021,0.0002577492,0.0001413369,0.009507874],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1893291,"threshold_uncertainty_score":0.9997607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0124614004164755,"score_gpt":0.2779788838603303,"score_spread":0.2655174834438548,"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."}}