{"id":"W4415960426","doi":"10.26434/chemrxiv-2025-f1wcr","title":"Honegumi RAG Assistant: An Agentic System for Accelerating Bayesian Optimization Adoption in Experimental Sciences","year":2025,"lang":"","type":"article","venue":"ChemRxiv","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Code (set theory); Domain (mathematical analysis); Documentation; Bayesian optimization; Code generation; Bayesian network; Source code; Bayesian probability","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":[0.001033627,0.0005143518,0.0005436623,0.0007516518,0.001220531,0.001131054,0.001123261,0.0002548577,0.0000359237],"category_scores_gemma":[0.0002033894,0.000593,0.0001532348,0.002957311,0.0003352494,0.002963628,0.0003191466,0.0002405154,0.00000557593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001187696,"about_ca_system_score_gemma":0.0005039542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001958057,"about_ca_topic_score_gemma":0.00001014775,"domain_scores_codex":[0.9957436,0.0002552466,0.001054834,0.001671066,0.0004769448,0.0007983153],"domain_scores_gemma":[0.9980344,0.000181168,0.0005229727,0.0006707769,0.0004064415,0.0001843029],"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":[0.00006003656,0.0006126594,0.0003311583,0.0002738895,0.00002969299,0.00001048548,0.001940262,0.9701758,0.007788468,0.01059051,0.00001288896,0.008174142],"study_design_scores_gemma":[0.001991149,0.0001978144,0.0002339826,0.0005573398,0.00002337792,0.000006815662,0.002854716,0.9103693,0.08318079,0.00006471513,0.00002044766,0.0004995193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008707419,0.0005916758,0.9849169,0.0001652506,0.001966481,0.001711032,0.00000364019,0.0002390593,0.001698578],"genre_scores_gemma":[0.579695,0.00002008014,0.4196708,0.00007895629,0.00009420495,0.0002301843,0.00001787272,0.00002543556,0.0001674726],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5709876,"threshold_uncertainty_score":0.9999059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03592029959743746,"score_gpt":0.3178501660026649,"score_spread":0.2819298664052274,"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."}}