{"id":"W4407733222","doi":"10.1039/d5sc00200a","title":"Adaptive representation of molecules and materials in Bayesian optimization","year":2025,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; University of Toronto","keywords":"Bayesian optimization; Representation (politics); Bayesian probability; Computer science; Molecule; Chemistry; Theoretical computer science; Nanotechnology; Artificial intelligence; Materials science; Organic chemistry; Political science","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":[0.000902693,0.00008400483,0.0001777764,0.0001539325,0.00006918635,0.0000958153,0.0004011039,0.00004097371,0.0001438166],"category_scores_gemma":[0.0009121475,0.00007450563,0.000009977084,0.0009369358,0.0009625555,0.0003313139,0.0002445878,0.00004312587,0.000003566841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005129573,"about_ca_system_score_gemma":0.00009102267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001599305,"about_ca_topic_score_gemma":0.000002154443,"domain_scores_codex":[0.998704,0.00006880512,0.0002971773,0.0004244286,0.0002826594,0.0002229224],"domain_scores_gemma":[0.9994631,0.00009075019,0.000115378,0.0002002332,0.00008224705,0.0000482538],"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":[0.00002200813,0.00001586047,0.0005205327,0.00001686588,2.668795e-7,7.117282e-7,0.0001342826,0.006641841,0.9895833,0.002818266,0.0000068482,0.0002392834],"study_design_scores_gemma":[0.0001330489,0.00001338679,0.002694122,0.00005887241,0.000001805294,0.000001580408,0.00006470967,0.04098902,0.9539959,0.001977271,0.000001649476,0.00006865872],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9430062,0.00001840892,0.05484106,0.000173886,0.0001744477,0.0001366517,0.000004062455,0.00002613383,0.001619126],"genre_scores_gemma":[0.9413873,0.000005158639,0.05851212,0.00004918453,0.000009220394,0.00001043124,0.000001251403,0.000002804956,0.00002253725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03558736,"threshold_uncertainty_score":0.3546576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00810305137646516,"score_gpt":0.283279876719724,"score_spread":0.2751768253432588,"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."}}