{"id":"W3033881011","doi":"10.1016/j.scriptamat.2020.05.038","title":"Identifying flow defects in amorphous alloys using machine learning outlier detection methods","year":2020,"lang":"en","type":"article","venue":"Scripta Materialia","topic":"Metallic Glasses and Amorphous Alloys","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"U.S. Department of Energy","keywords":"Materials science; Amorphous metal; Outlier; Anomaly detection; Amorphous solid; Shear matrix; Plasticity; Transient (computer programming); Shear (geology); Artificial intelligence; Machine learning; Computer science; Metallurgy; Composite material; Alloy; Crystallography","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"],"consensus_categories":[],"category_scores_codex":[0.000455982,0.0002853362,0.0003981512,0.0001262909,0.0000936705,0.000244604,0.0001890683,0.0001281097,0.0004977337],"category_scores_gemma":[0.00009281603,0.0003012717,0.0001007326,0.0003290089,0.00002077658,0.000267855,0.0000964027,0.0003012718,0.0001003544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001037318,"about_ca_system_score_gemma":0.00001150012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005166879,"about_ca_topic_score_gemma":0.0001441501,"domain_scores_codex":[0.9983732,0.0002181065,0.0004332458,0.0003443691,0.0001814945,0.0004495915],"domain_scores_gemma":[0.9995708,0.000004667295,0.00006769416,0.0001824647,0.00002226651,0.0001520639],"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":[0.00002244703,0.00000808627,0.000554506,0.0001797917,0.00003388104,0.00004942569,0.0004000835,0.003878751,0.9918636,0.00001848892,0.000246844,0.002744092],"study_design_scores_gemma":[0.0006527714,0.00005405795,0.001033959,0.00006265741,0.00005657316,0.00002772911,0.0001492996,0.7102653,0.2454392,0.00009631021,0.04168032,0.0004818064],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8471764,0.0004989205,0.130037,0.00002638182,0.02105624,0.0002726942,0.00001228246,0.0006926965,0.0002274754],"genre_scores_gemma":[0.9403828,0.00005964691,0.05846395,0.0001239217,0.000387405,0.00001776295,0.00001860002,0.0001359675,0.0004098769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7464244,"threshold_uncertainty_score":0.9999439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05110213234928151,"score_gpt":0.2796289402559626,"score_spread":0.2285268079066811,"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."}}