{"id":"W4410904053","doi":"10.21203/rs.3.rs-6657064/v1","title":"Benchmarking constrained, multi-objective and surrogate-assisted derivative-free optimization methods","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Polytechnique Montréal","funders":"","keywords":"Benchmarking; Derivative (finance); Computer science; Mathematical optimization; Mathematics; Economics","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.003602936,0.0006182643,0.0007725545,0.001549523,0.0008180175,0.0007951579,0.002196671,0.0006042371,0.00005123512],"category_scores_gemma":[0.005298504,0.000651527,0.0001809856,0.002365921,0.0006971519,0.0007231171,0.009071965,0.002233515,0.000004481692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008273278,"about_ca_system_score_gemma":0.001296893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002082462,"about_ca_topic_score_gemma":0.00006593296,"domain_scores_codex":[0.9917037,0.003324151,0.0006969203,0.00214981,0.001133904,0.0009914702],"domain_scores_gemma":[0.990806,0.002969593,0.0003771727,0.002026879,0.003474904,0.0003454788],"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":[0.00007034732,0.0004490693,0.000647335,0.0009727377,0.0003505444,0.00009794731,0.003858858,0.7183901,0.0001993102,0.01093974,0.0002045536,0.2638195],"study_design_scores_gemma":[0.001675243,0.0001197197,0.00260066,0.0008339427,0.00001689602,0.00001707841,0.0005099432,0.9894187,0.0008285413,0.003167155,0.0002229493,0.000589143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005658704,0.0009312156,0.9919967,0.0005876551,0.0006858284,0.002304961,0.0001934344,0.0004289194,0.002814703],"genre_scores_gemma":[0.003467348,0.0007143981,0.9943061,0.00006460191,0.0001003417,0.0005063935,0.0001421763,0.00004612002,0.0006525218],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2710286,"threshold_uncertainty_score":0.9995936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08449971043528098,"score_gpt":0.4434999385404259,"score_spread":0.3590002281051449,"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."}}