{"id":"W4309390910","doi":"10.21203/rs.3.rs-2248548/v1","title":"Hyperactive learning for data-driven interatomic potentials","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council","keywords":"Interatomic potential; Computer science; Psychology; Physics; Molecular dynamics; 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":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0131482,0.0004378396,0.0007414894,0.0005918437,0.001677068,0.001626221,0.00568303,0.0002727307,0.01243995],"category_scores_gemma":[0.007248403,0.0004264024,0.0001798751,0.0004049785,0.0004311044,0.0005047068,0.02003303,0.003076359,0.0006896741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006123257,"about_ca_system_score_gemma":0.001113456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001022005,"about_ca_topic_score_gemma":0.00003997796,"domain_scores_codex":[0.9891613,0.004044462,0.0007186042,0.002392191,0.002309936,0.001373523],"domain_scores_gemma":[0.9938145,0.00204248,0.0004746219,0.002638421,0.0007711576,0.0002587884],"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":[0.0006033449,0.0002998292,0.001599394,0.002421358,0.00007163681,0.00009960383,0.002262932,0.2496362,0.7254258,0.001057638,0.01428886,0.002233403],"study_design_scores_gemma":[0.001562421,0.001490356,0.002767402,0.00176163,0.0001011132,0.00005519991,0.003980887,0.7732876,0.04078645,0.00788438,0.1640825,0.002240013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9699553,0.0004378631,0.01464981,0.001482149,0.003951993,0.004405967,0.002229142,0.0006144742,0.002273266],"genre_scores_gemma":[0.9714161,0.0001011541,0.02031023,0.00006213651,0.001023936,0.001522837,0.002530551,0.0001590569,0.002874045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6846393,"threshold_uncertainty_score":0.9998188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1318714538792475,"score_gpt":0.4643498512062033,"score_spread":0.3324783973269558,"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."}}