{"id":"W4386714071","doi":"10.1038/s41524-023-01104-6","title":"Hyperactive learning for data-driven interatomic potentials","year":2023,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Research Councils UK","keywords":"Interatomic potential; Ab initio; Molecular dynamics; Polyethylene glycol; Cluster (spacecraft); Process (computing); Statistical physics; Materials science; Computer science; Chemical physics; Molecular physics; Chemistry; Physics; Computational chemistry; Quantum mechanics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"category_scores_codex":[0.002290242,0.0002585349,0.0004368556,0.0002137303,0.000496288,0.0007013069,0.001087984,0.00008972509,0.002242608],"category_scores_gemma":[0.00119997,0.0002446559,0.00005299077,0.0002904477,0.0001372526,0.0007050935,0.0007085468,0.00009710839,0.003523689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006129117,"about_ca_system_score_gemma":0.0001433046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006636175,"about_ca_topic_score_gemma":0.000002479901,"domain_scores_codex":[0.996981,0.0004586917,0.000645162,0.000857276,0.000523794,0.0005340758],"domain_scores_gemma":[0.9979047,0.0009028711,0.0003847542,0.0004527756,0.0002535501,0.0001013598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008307179,0.00002066876,0.00007036977,0.00005489695,0.00001140036,0.000006315467,0.0001660542,0.2185462,0.776809,0.001338047,0.002657966,0.0002360364],"study_design_scores_gemma":[0.001506782,0.0002637501,0.007779201,0.000178622,0.00005909294,0.00006884305,0.0002034273,0.6538148,0.3085888,0.01955985,0.007061547,0.0009153199],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9513481,0.000007456773,0.04365946,0.0006091404,0.002429224,0.0005799703,0.0005438669,0.0006857238,0.0001371062],"genre_scores_gemma":[0.9564599,0.000003401785,0.04023772,0.0002015987,0.0005521716,0.0001194777,0.001956617,0.00005466155,0.0004145005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4682202,"threshold_uncertainty_score":0.9986695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04394644643524804,"score_gpt":0.3389252481607739,"score_spread":0.2949788017255259,"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."}}