{"id":"W1972625648","doi":"10.1063/1.4846297","title":"Automated fit of high-dimensional potential energy surfaces using cluster analysis and interpolation over descriptors of chemical environment","year":2013,"lang":"en","type":"article","venue":"The Journal of Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Interpolation (computer graphics); Function (biology); Energy (signal processing); Cluster (spacecraft); Computer science; Potential energy; Algorithm; Biological system; Mathematical optimization; Mathematics; Artificial intelligence; Statistics; Physics; Atomic physics","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":[0.0005060268,0.0001285294,0.0003890787,0.00005274433,0.00002975714,0.00003073936,0.0002925841,0.00005883132,0.0004083609],"category_scores_gemma":[0.00005399687,0.00008406336,0.00009940652,0.000168668,0.0003730646,0.0002759024,0.000198389,0.0001071721,0.00000224369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003907789,"about_ca_system_score_gemma":0.00002517978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004131343,"about_ca_topic_score_gemma":1.802228e-7,"domain_scores_codex":[0.9984344,0.0001635065,0.0005822762,0.0001254658,0.0005384789,0.0001559254],"domain_scores_gemma":[0.9986693,0.0001432702,0.0008351016,0.0001692987,0.000115557,0.00006742236],"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":[0.00007766989,0.00005910777,0.0004056986,0.00001370804,0.00005561028,2.718272e-7,0.0001115179,0.04992275,0.949198,0.00002152087,0.00008236769,0.00005175297],"study_design_scores_gemma":[0.0001771965,0.00002773468,0.001090505,0.00002257218,0.0001857199,0.000008406129,0.000007231631,0.3213732,0.6761658,0.0008803749,7.405192e-7,0.00006053403],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900301,0.0000299948,0.009694091,0.00007322012,0.0001118337,0.0000411985,0.000006682681,0.000009132915,0.00000379594],"genre_scores_gemma":[0.9901442,0.00000307505,0.009717555,0.00003891504,0.00008128158,3.936408e-7,0.000002210508,0.000008742378,0.000003639708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2730323,"threshold_uncertainty_score":0.4471265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008528814534774557,"score_gpt":0.2284940830845847,"score_spread":0.2199652685498101,"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."}}