{"id":"W4415598576","doi":"10.1115/detc2025-169062","title":"Adaptive Uncertainty-Aware Deep Learning for Materials Discovery With High-Dimensional Design Inputs","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bayesian optimization; Representation (politics); Deep learning; Process (computing); Gaussian process; Reduction (mathematics); Feature (linguistics); Bayesian probability; Uncertainty quantification","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","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005092362,0.001189446,0.001590084,0.000501766,0.001882795,0.002592069,0.001591318,0.0004461281,0.00490526],"category_scores_gemma":[0.001241694,0.0009218496,0.0001699441,0.001021393,0.001161313,0.001740073,0.0009459337,0.0004800658,0.0003136086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004860212,"about_ca_system_score_gemma":0.001337121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001144237,"about_ca_topic_score_gemma":0.0001201641,"domain_scores_codex":[0.9905257,0.002233973,0.001559767,0.002516786,0.001231083,0.00193273],"domain_scores_gemma":[0.9944664,0.002371575,0.001019368,0.001010597,0.0008308855,0.00030122],"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":[0.004146704,0.0001713957,0.00008834515,0.0003342732,0.00009618355,0.00003106478,0.0002435169,0.5438336,0.4410093,0.008965451,0.0005003817,0.0005798366],"study_design_scores_gemma":[0.004282333,0.003691071,0.001227064,0.001685831,0.0004237851,0.00005336734,0.000506818,0.2344188,0.74526,0.005605068,0.0008257242,0.002020161],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2632478,0.0001099303,0.7278322,0.001401796,0.004074566,0.002556106,0.000133176,0.0003149268,0.0003295159],"genre_scores_gemma":[0.8812485,0.00002435354,0.1037363,0.001215263,0.0003603275,0.0004806816,0.0000835721,0.0001038264,0.01274716],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6240959,"threshold_uncertainty_score":0.9994166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0142153497066984,"score_gpt":0.2606286449865119,"score_spread":0.2464132952798135,"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."}}