{"id":"W4404398506","doi":"10.26434/chemrxiv-2024-fhn98","title":"Adaptive Representation of Molecules and Materials in Bayesian Optimization","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Representation (politics); Bayesian optimization; Bayesian probability; Molecule; Computer science; Artificial intelligence; Physics; Political science; Quantum mechanics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00218419,0.001059768,0.001296695,0.001001381,0.0005020813,0.001593135,0.00160976,0.001763653,0.003031398],"category_scores_gemma":[0.005829315,0.0006756764,0.001244787,0.001000781,0.001232941,0.001596549,0.001693532,0.00193558,0.0008329493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201822,"about_ca_system_score_gemma":0.001957158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005612239,"about_ca_topic_score_gemma":0.005868996,"domain_scores_codex":[0.9990402,0.0004099835,0.0000354395,0.0001506843,0.0002765333,0.00008706048],"domain_scores_gemma":[0.9986872,0.0008130581,0.0001192046,0.0001342706,0.0001886098,0.00005776204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009049008,0.00005691641,0.0007643147,0.0001316387,0.00005091363,0.00005326221,0.00005013347,0.9049372,0.002707525,0.03942141,0.00226965,0.04946653],"study_design_scores_gemma":[0.00001085697,0.00001677201,0.00009040525,0.00001070936,0.000006770262,0.00001090927,0.000005573689,0.9833054,0.0004515903,0.01517792,0.0009050011,0.000008213766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009599955,0.0002745801,0.9865983,0.0004213362,0.00002510036,0.00005542056,0.0002056408,0.0005188766,0.00230085],"genre_scores_gemma":[0.395945,0.0008217045,0.595397,0.0008348212,0.0001050512,0.0007115934,0.001306292,0.0004774174,0.004401211],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005612239,"threshold_uncertainty_score":0.0115512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03139454581396733,"score_gpt":0.3171172859641188,"score_spread":0.2857227401501515,"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."}}