{"id":"W3172457552","doi":"10.1063/5.0048164","title":"G<scp>ryffin</scp>: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge","year":2021,"lang":"en","type":"article","venue":"Applied Physics Reviews","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":156,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research","keywords":"Categorical variable; Bayesian optimization; Domain (mathematical analysis); Process (computing); Kernel (algebra); Domain knowledge; Bayesian probability; Identification (biology)","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":[0.001032688,0.0002938531,0.0007305635,0.00003213956,0.0001883898,0.0001603555,0.0005689325,0.0001118635,0.0002016872],"category_scores_gemma":[0.0003406891,0.0002576134,0.0001082053,0.0004912522,0.0001251598,0.0003473607,0.0001655445,0.0001037573,0.0000878228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006095154,"about_ca_system_score_gemma":0.0002467171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002559808,"about_ca_topic_score_gemma":0.000002777869,"domain_scores_codex":[0.997705,0.0002104651,0.0007719684,0.0005935448,0.0002806844,0.000438359],"domain_scores_gemma":[0.9981093,0.0003881861,0.0005023725,0.0006419728,0.0002047779,0.0001534358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005492616,0.0004900605,0.00001029639,0.0004456566,0.00001147234,7.722809e-7,0.001635662,0.01399781,0.8581019,0.01745414,0.02249978,0.08534694],"study_design_scores_gemma":[0.0006726461,0.0001095021,0.000004856503,0.00009361069,0.000051696,0.000005761947,0.0001629974,0.2254671,0.4641235,0.003425836,0.3055639,0.0003185548],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00112796,0.001692425,0.9900542,0.00002015993,0.0004449705,0.0008614886,0.00005973009,0.00008673681,0.00565236],"genre_scores_gemma":[0.01101774,0.001983396,0.9833434,0.0004610831,0.0007089406,0.0009565403,0.0007701433,0.00009369539,0.0006650461],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3939784,"threshold_uncertainty_score":0.9999876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02413911206244987,"score_gpt":0.3084115666260863,"score_spread":0.2842724545636364,"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."}}