{"id":"W3176317624","doi":"10.1137/21m1441122","title":"QM/MM Methods for Crystalline Defects. Part 3: Machine-Learned MM Models","year":2022,"lang":"en","type":"article","venue":"Multiscale Modeling and Simulation","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; National Natural Science Foundation of China; Leverhulme Trust","keywords":"A priori and a posteriori; Matching (statistics); Computer science; Statistical physics; Interatomic potential; Construct (python library); QM/MM; Algorithm; Quantum; Molecular dynamics; Physics; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.00334909,0.0002194072,0.0003135526,0.0001112012,0.001059386,0.0001880131,0.0002812093,0.0000694948,0.0002885247],"category_scores_gemma":[0.0003577694,0.0002128583,0.00008142005,0.0001465523,0.00005600396,0.0003262834,0.000273625,0.0001893048,0.000006060557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006730669,"about_ca_system_score_gemma":0.00003410337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001929064,"about_ca_topic_score_gemma":0.000008831474,"domain_scores_codex":[0.9974443,0.0006255414,0.0005073499,0.0006707094,0.0003463569,0.000405747],"domain_scores_gemma":[0.9987624,0.0005088224,0.0001830288,0.0003259394,0.0001080608,0.0001117404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001168969,0.00003923905,0.00007263412,0.00003549667,0.000002895898,6.033659e-7,0.000448266,0.9109442,0.08296323,0.0002886077,0.000009272746,0.005078667],"study_design_scores_gemma":[0.0007290483,0.0001130361,0.00001430937,0.00001215525,0.00002411879,0.000004668958,0.00006937926,0.9885242,0.001136533,0.007899583,0.001204919,0.0002680426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3712184,0.0001776701,0.6275339,0.000120217,0.0003445133,0.0003312581,0.00004815364,0.0001426105,0.00008338798],"genre_scores_gemma":[0.8105702,0.000006783214,0.1887114,0.0001234476,0.0001033751,0.0001235559,0.00006265006,0.00003448489,0.0002640689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4393519,"threshold_uncertainty_score":0.868011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0661070101412467,"score_gpt":0.3675241679315931,"score_spread":0.3014171577903464,"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."}}