{"id":"W3172720573","doi":"10.3389/fmats.2021.673574","title":"Machine Learning Based Methodology to Predict Point Defect Energies in Multi-Principal Element Alloys","year":2021,"lang":"en","type":"article","venue":"Frontiers in Materials","topic":"High Entropy Alloys Studies","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Basic Energy Sciences; Office of Science; Canadian Centre for Applied Research in Cancer Control; University of Wyoming; U.S. Department of Energy","keywords":"Quinary; Ternary operation; Vacancy defect; Crystallographic defect; Materials science; Binary number; Alloy; Shape-memory alloy; Lattice (music); Principal component analysis; Statistical physics; Crystallography; Computer science; Metallurgy; Artificial intelligence; Chemistry; Physics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001056596,0.0002565025,0.0006436211,0.0002884998,0.00004093791,0.00003903667,0.0001689962,0.0001081394,0.0002356079],"category_scores_gemma":[0.0005743684,0.0002715296,0.00006572887,0.0002403958,0.00002799115,0.00006499351,0.0001561646,0.000166785,0.00001882094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002883112,"about_ca_system_score_gemma":0.00002742644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001313504,"about_ca_topic_score_gemma":0.0003982349,"domain_scores_codex":[0.9977644,0.0006805033,0.0005317321,0.0003405956,0.000154684,0.0005280752],"domain_scores_gemma":[0.9995106,0.0001173163,0.00004230693,0.0002323458,0.00002855689,0.00006885255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001007862,0.00005882441,0.05372363,0.0001948417,0.0001507915,0.0002105901,0.001182382,0.6915637,0.250588,0.0000684588,0.001780791,0.0003772215],"study_design_scores_gemma":[0.004299737,0.0001905554,0.04843555,0.00028109,0.00008335337,0.00001030913,0.001295186,0.07922345,0.8388062,0.0001758346,0.02614726,0.001051467],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.762642,0.002047357,0.230423,0.0001776494,0.003747941,0.000407087,0.00006674779,0.0003160638,0.0001720681],"genre_scores_gemma":[0.6927879,0.0002933146,0.3063176,0.00009796213,0.00007323362,0.0001892674,0.00005799807,0.00005992499,0.0001228427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6123403,"threshold_uncertainty_score":0.9999737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02840793975699973,"score_gpt":0.2638671408885958,"score_spread":0.235459201131596,"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."}}