{"id":"W4295736424","doi":"10.1039/d2dd00028h","title":"Bayesian optimization with known experimental and design constraints for chemistry applications","year":2022,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Vector Institute; University of Toronto; Government of Ontario; Government of Canada","keywords":"Computer science; Chemical space; Bayesian optimization; Robustness (evolution); Flexibility (engineering); A priori and a posteriori; Mathematical optimization; Artificial intelligence; Chemistry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001712332,0.0001102653,0.0001073014,0.00001957905,0.0003408018,0.0006039013,0.0001938383,0.00001607032,0.0005232362],"category_scores_gemma":[0.00002994231,0.00009945792,0.00001861051,0.0000861462,0.0002612771,0.0006845942,0.0001430566,0.00004255894,0.000004216821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004800204,"about_ca_system_score_gemma":0.00007311242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002482594,"about_ca_topic_score_gemma":5.545578e-8,"domain_scores_codex":[0.9991204,0.00002589093,0.0001366884,0.0003375024,0.000195402,0.0001841281],"domain_scores_gemma":[0.9995992,0.00007807732,0.00008952748,0.0001597604,0.00001913596,0.00005429437],"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":[0.0001518151,0.0001609902,0.0002397841,0.00004182432,0.000005235909,0.000002938434,0.0002059227,0.311573,0.6858987,0.001015992,0.0001701527,0.0005337317],"study_design_scores_gemma":[0.002658738,0.00109218,0.0002212102,0.00005102597,0.00003980934,0.0003720325,0.00378903,0.2152029,0.7684328,0.001663048,0.005034696,0.001442482],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09408682,0.00003888595,0.902891,0.00005275441,0.00005774312,0.0005358816,0.0002997165,0.00006877038,0.00196841],"genre_scores_gemma":[0.9766124,4.60393e-7,0.02204935,0.00005193102,0.00003603758,0.0006777873,0.00008667017,0.00001674077,0.0004686035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8825256,"threshold_uncertainty_score":0.5823435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008969485086710615,"score_gpt":0.2371597787144913,"score_spread":0.2281902936277807,"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."}}