{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004119561,0.002435507,0.001327572,0.001187754,0.0005976559,0.001183794,0.002554319,0.001922556,0.006678554],"category_scores_gemma":[0.006302865,0.0007136749,0.001637124,0.001523669,0.001066618,0.001268247,0.00132204,0.002140137,0.001592343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001449883,"about_ca_system_score_gemma":0.002382527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009659884,"about_ca_topic_score_gemma":0.01382878,"domain_scores_codex":[0.9985982,0.0004985828,0.0001097149,0.0002496058,0.0003907149,0.0001532477],"domain_scores_gemma":[0.9971015,0.001989793,0.0001117623,0.0003439604,0.0003327321,0.0001202559],"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":[0.0004553094,0.0005616728,0.003959953,0.001974068,0.0003735818,0.0001436244,0.000113308,0.871525,0.004467479,0.01128376,0.04064303,0.06449917],"study_design_scores_gemma":[0.0001400132,0.0002373832,0.001172032,0.00006275289,0.00003041473,0.00003359538,0.00003400894,0.9814364,0.003877985,0.003946632,0.008996555,0.00003222847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3417261,0.01000511,0.466305,0.002652613,0.001319295,0.00131197,0.02589463,0.08367259,0.06711279],"genre_scores_gemma":[0.4858491,0.001720006,0.4663807,0.00117296,0.0001065485,0.001648423,0.02915031,0.006815476,0.007156498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009659884,"threshold_uncertainty_score":0.02234197,"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."}}