{"id":"W4377023704","doi":"10.26434/chemrxiv-2023-74w8d","title":"Olympus, enhanced: benchmarking mixed-parameter and multi-objective optimization in chemistry and materials science","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Office of Naval Research; Defense Advanced Research Projects Agency","keywords":"Benchmarking; Benchmark (surveying); Computer science; Python (programming language); Categorical variable; Optimization problem; Algorithm; Machine learning; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003088409,0.0004803219,0.0006436589,0.0002045598,0.0002910073,0.001056825,0.000812725,0.0003513363,0.0002985231],"category_scores_gemma":[0.001550948,0.00047973,0.00003393796,0.0004341161,0.001327422,0.0003985014,0.002672843,0.0003784528,0.00003094821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001991297,"about_ca_system_score_gemma":0.000265901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003105718,"about_ca_topic_score_gemma":0.00001640345,"domain_scores_codex":[0.9961054,0.0001551307,0.0006479691,0.001863812,0.0005237347,0.0007039406],"domain_scores_gemma":[0.9982679,0.0002429324,0.0004990915,0.0006604834,0.0001504894,0.0001791411],"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":[0.00001709063,0.00002811712,0.0007676266,0.000430194,0.000003386263,0.000009478912,0.0006480013,0.02106173,0.9767752,0.00001326672,0.000009301701,0.0002366492],"study_design_scores_gemma":[0.0003487789,0.00001844144,0.01185754,0.0004991097,0.00001601706,0.0000139688,0.0001035761,0.05398087,0.9321581,0.0004603643,0.00000280605,0.0005404764],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843966,0.0001290669,0.01267872,0.00008453336,0.001830617,0.0004795144,0.00002112916,0.0002116122,0.0001682449],"genre_scores_gemma":[0.906569,0.0001421758,0.0926355,0.0000349396,0.0001884476,0.0001466302,0.00002914269,0.00005345693,0.0002006864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07995678,"threshold_uncertainty_score":0.9999802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01747419541794644,"score_gpt":0.2795966063434814,"score_spread":0.262122410925535,"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."}}