{"id":"W4387333835","doi":"10.26434/chemrxiv-2023-s5qnw","title":"Anubis: Bayesian optimization with unknown feasibility constraints for scientific experimentation","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Bayesian optimization; Computer science; Benchmarking; Benchmark (surveying); A priori and a posteriori; Optimization problem; Mathematical optimization; Flexibility (engineering); Bayesian probability; Gaussian process; Machine learning; Artificial intelligence; Gaussian; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.003654702,0.001399002,0.001428844,0.0008875377,0.000655324,0.001811443,0.001664677,0.001650909,0.006038895],"category_scores_gemma":[0.009863543,0.0008562437,0.001447628,0.0007026031,0.001624665,0.001449746,0.002604619,0.002848289,0.001043802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001346181,"about_ca_system_score_gemma":0.002668229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004744961,"about_ca_topic_score_gemma":0.005020838,"domain_scores_codex":[0.9982246,0.0009076268,0.00006108911,0.0002002277,0.0005029404,0.0001036379],"domain_scores_gemma":[0.9949923,0.003795144,0.0002990651,0.0003404056,0.0004183632,0.0001547944],"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":[0.00008260109,0.00007222888,0.0006857939,0.0002618953,0.0000857439,0.00005635758,0.00005640742,0.8814529,0.001593017,0.07796296,0.002546799,0.03514342],"study_design_scores_gemma":[0.00001659633,0.00002424314,0.00006610229,0.00003033353,0.000007565237,0.00001006461,0.000008256906,0.9698709,0.0005393666,0.02709623,0.00232261,0.000007652428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004476939,0.0006131807,0.9871907,0.0004023903,0.00006193242,0.0000825618,0.0001491178,0.0006093582,0.00641387],"genre_scores_gemma":[0.2458008,0.001132207,0.7440395,0.0006866797,0.0001379171,0.0009739557,0.0007616064,0.0009279407,0.005539413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006038895,"threshold_uncertainty_score":0.02020216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05639905873510422,"score_gpt":0.3321946760553058,"score_spread":0.2757956173202016,"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."}}