{"id":"W4415475237","doi":"10.1115/1.4070206","title":"Materials Discovery Using Uncertainty-Aware Constrained Bayesian Optimization With Representation Learning of High-Dimensional Inputs","year":2025,"lang":"en","type":"article","venue":"Journal of Mechanical Design","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Army Research Office; Division of Materials Research","keywords":"Bayesian optimization; Representation (politics); Reduction (mathematics); Uncertainty quantification; Bayesian probability; Feature (linguistics); Gaussian process; Bayesian network; Uncertainty reduction theory","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":[0.002768028,0.0001807959,0.0005513836,0.0002300024,0.0001577412,0.0001927891,0.0003478462,0.0001066251,0.0005122042],"category_scores_gemma":[0.001047052,0.0001333457,0.00006080382,0.0003811725,0.000152651,0.0006256995,0.00009545907,0.0001923107,0.00000214393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009982451,"about_ca_system_score_gemma":0.0004465067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009053345,"about_ca_topic_score_gemma":0.000001040534,"domain_scores_codex":[0.9967148,0.001132764,0.000956861,0.0002809225,0.0006701881,0.0002444774],"domain_scores_gemma":[0.9975381,0.0004786503,0.001254725,0.0001918153,0.0004573572,0.00007930268],"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":[0.0004609253,0.00003035283,0.00001672085,0.00002490943,0.0000115369,0.00001385533,0.0000212158,0.5093766,0.4890303,0.0009584945,0.00001401219,0.00004107716],"study_design_scores_gemma":[0.0009349236,0.0004993739,0.00008314077,0.0005113924,0.00007952155,0.000109423,0.00006231207,0.2974828,0.6985476,0.001547048,0.000002076202,0.0001404421],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3342038,0.000008495382,0.6649525,0.0001545536,0.0005090745,0.0001389999,0.000005437211,0.00001617864,0.00001090359],"genre_scores_gemma":[0.7773112,0.000004048639,0.2224897,0.00007028475,0.00006801949,0.000002048592,0.000003793959,0.00001230471,0.00003859102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4431074,"threshold_uncertainty_score":0.5608277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01801196363068734,"score_gpt":0.2830931623488795,"score_spread":0.2650811987181922,"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."}}