{"id":"W3160363205","doi":"10.1007/s00214-021-02766-5","title":"A new active learning approach for global optimization of atomic clusters","year":2021,"lang":"en","type":"article","venue":"Theoretical Chemistry Accounts","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; University of Calgary","funders":"","keywords":"Chemical space; Homonuclear molecule; Computer science; Global optimization; Random search; Cluster (spacecraft); Gaussian process; Gaussian; Artificial neural network; Chemistry; Machine learning; Statistical physics; Artificial intelligence; Algorithm; Molecule; Computational chemistry; Physics; Quantum mechanics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005017796,0.0001653741,0.0002751612,0.000008296168,0.0001030036,0.0001042683,0.0004012753,0.0001314013,0.003486148],"category_scores_gemma":[0.00117304,0.0001572475,0.00007300895,0.0001908916,0.0003602077,0.0001468702,0.0001932225,0.0001183979,0.00001315165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009605713,"about_ca_system_score_gemma":0.0002234358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006976721,"about_ca_topic_score_gemma":9.872093e-8,"domain_scores_codex":[0.998485,0.00009438954,0.0002946214,0.0004597755,0.000335526,0.0003307226],"domain_scores_gemma":[0.9990901,0.0001389823,0.0001832125,0.0002775117,0.0001882867,0.0001218447],"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":[0.0002751674,0.0000511291,0.0001389213,0.0002135201,0.000008698033,0.000001944075,0.0001069931,0.2118835,0.7665982,0.02034596,0.00006663932,0.0003094023],"study_design_scores_gemma":[0.0005999103,0.00002421956,0.0000439429,0.0000338774,0.0000308579,0.00003006397,0.0001169448,0.1960638,0.7947282,0.008079463,0.00005142824,0.0001972237],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4023969,0.00001835929,0.5838601,0.0001057214,0.000116657,0.0001324841,0.00004144802,0.00007404751,0.01325421],"genre_scores_gemma":[0.8508224,0.000002726187,0.1486528,0.00004750133,0.0001263728,0.00001363672,0.00005456073,0.00001511331,0.000264867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4484255,"threshold_uncertainty_score":0.9974248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006650379626511266,"score_gpt":0.2574636985803049,"score_spread":0.2508133189537937,"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."}}