{"id":"W4413329590","doi":"10.1063/5.0272663","title":"Ranking over regression for Bayesian optimization and molecule selection","year":2025,"lang":"en","type":"article","venue":"APL Machine Learning","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Vector Institute; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Ranking (information retrieval); Bayesian probability; Regression; Selection (genetic algorithm); Bayesian optimization; Computer science; Statistics; Bayesian linear regression; Artificial intelligence; Machine learning; Econometrics; Bayesian inference; Mathematics","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":[0.0004295517,0.0001000922,0.0001085999,0.0001731455,0.0002943324,0.0001554918,0.0001479008,0.00004188711,0.000006596092],"category_scores_gemma":[0.0002436743,0.00009593439,0.0000370307,0.0004107356,0.00001218125,0.0003310098,0.0001438724,0.0001527122,4.939643e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003784095,"about_ca_system_score_gemma":0.0000377568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003066087,"about_ca_topic_score_gemma":0.000003340816,"domain_scores_codex":[0.9991111,0.0001821604,0.0001428061,0.0003036051,0.000120908,0.0001394234],"domain_scores_gemma":[0.9993609,0.000379768,0.00007707446,0.00009788288,0.00005714425,0.00002725086],"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":[0.00001877213,0.00001418075,0.003924824,0.00003878157,0.00001495356,6.885936e-7,0.0002075631,0.8991841,0.0006426767,0.04381554,0.00005530001,0.05208259],"study_design_scores_gemma":[0.0004105851,0.00003474086,0.002076126,0.0000638116,0.000007627867,0.000003749306,0.000004625291,0.98873,0.0005629596,0.007285971,0.0007265962,0.00009322011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01502164,0.0001960076,0.9829159,0.0006718469,0.0001423492,0.0001620809,3.731253e-7,0.0001354537,0.0007543958],"genre_scores_gemma":[0.5691408,0.00001013269,0.4301201,0.0002450806,0.00003166261,0.00001711652,0.00001364773,0.000008889851,0.0004126399],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5541191,"threshold_uncertainty_score":0.3912091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00755139608795133,"score_gpt":0.3021889080860756,"score_spread":0.2946375119981243,"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."}}