{"id":"W4411433890","doi":"10.1039/d5dd00018a","title":"Anubis: Bayesian optimization with unknown feasibility constraints for scientific experimentation","year":2025,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Office of Naval Research; Canada Foundation for Innovation; Canada First Research Excellence Fund; Government of Ontario; Government of Canada; Vector Institute; Canadian Institute for Advanced Research","keywords":"Bayesian optimization; Flexibility (engineering); Bayesian probability; Computer science; Sample (material); Artificial intelligence; Mathematics; Statistics","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":[0.0002141325,0.0001064861,0.0001379814,0.00008974661,0.0001303397,0.0006744976,0.00008687055,0.00003499967,0.00002724363],"category_scores_gemma":[0.001635229,0.00008774426,0.00004356484,0.0001930306,0.0002922147,0.0005459833,0.00002191547,0.00003239479,0.000001787984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007522014,"about_ca_system_score_gemma":0.0002214556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.027149e-7,"about_ca_topic_score_gemma":0.000003233923,"domain_scores_codex":[0.9992343,0.00003169392,0.0002044001,0.0002705885,0.0001156365,0.0001434288],"domain_scores_gemma":[0.9987918,0.0007305641,0.00008428854,0.0002223529,0.0001394341,0.00003159781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003120061,0.0007666576,0.003947143,0.0004004016,0.0001063312,0.000001312893,0.001389732,0.0008585051,0.0004870607,0.9579369,0.02037963,0.01341433],"study_design_scores_gemma":[0.003870749,0.0003356761,0.003005485,0.000425117,0.0001852077,0.000008363527,0.0165995,0.007270757,0.02907271,0.935021,0.003348882,0.0008564894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03155568,0.00001954013,0.9575271,0.0001138384,0.0005938019,0.0005853678,0.0003003676,0.0000664848,0.009237795],"genre_scores_gemma":[0.783873,0.000001236073,0.2070599,0.00006990752,0.00002046631,0.0001066712,0.000372506,0.00001252683,0.008483686],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7523174,"threshold_uncertainty_score":0.6504195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1294477438279952,"score_gpt":0.4203192255170704,"score_spread":0.2908714816890752,"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."}}