{"id":"W4413943769","doi":"10.26434/chemrxiv-2025-10gfq","title":"RAMBOAU: Risk-averse Multiobjective Bayesian Optimization with Aleatoric Uncertainty for Nanomaterial Synthesis","year":2025,"lang":"en","type":"article","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Research Foundation","keywords":"Bayesian probability; Bayesian optimization; Multi-objective optimization; Computer science; Mathematical optimization; Mathematics; Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008968839,0.0002744551,0.0003566387,0.0001380039,0.0004842574,0.0002593255,0.0004670348,0.0001254362,0.0009819096],"category_scores_gemma":[0.001224899,0.0002218137,0.00006985706,0.0003940613,0.0002319524,0.0002790239,0.00009577444,0.00008583739,0.00005234485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001846815,"about_ca_system_score_gemma":0.0001785516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002519998,"about_ca_topic_score_gemma":0.00002208202,"domain_scores_codex":[0.9980713,0.0002022165,0.0003306477,0.0006948498,0.0002459131,0.0004550805],"domain_scores_gemma":[0.9985186,0.0004224808,0.0002934397,0.0004692897,0.0002077852,0.00008841847],"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":[0.000963922,0.0001295202,0.003327808,0.0002119884,0.00003760566,0.000005157588,0.000425074,0.4284976,0.5642493,0.0007643768,0.0007445615,0.0006430156],"study_design_scores_gemma":[0.0012376,0.0001234616,0.001550481,0.0001493509,0.0001317646,0.000005680925,0.0001950965,0.1942401,0.8005598,0.0003685438,0.000970779,0.0004673093],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6984677,0.00001530551,0.2974616,0.0001714321,0.001368517,0.0007718293,0.00003287679,0.0003182155,0.001392529],"genre_scores_gemma":[0.9058651,0.000008137735,0.09301625,0.00008914999,0.0001595387,0.0003640943,0.00001320913,0.00003103588,0.0004534521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2363105,"threshold_uncertainty_score":0.9999313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005077054943429509,"score_gpt":0.2378949330525785,"score_spread":0.232817878109149,"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."}}