{"id":"W3135357647","doi":"10.1039/d1sc01545a","title":"Golem: an algorithm for robust experiment and process optimization","year":2021,"lang":"en","type":"preprint","venue":"Chemical Science","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; National Research Council Canada; Vector Institute; University of Toronto","funders":"National Research Council Canada; Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Robustness (evolution); Computer science; Benchmark (surveying); Robust optimization; Process (computing); Maximization; Noise (video); Design of experiments; Mathematical optimization; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001469413,0.0001813947,0.0002114009,0.00004954011,0.00007079748,0.0002046379,0.0002884358,0.0001439809,0.000006354539],"category_scores_gemma":[0.00006744573,0.0001907625,0.00002615897,0.0001973586,0.0001286576,0.0003664185,0.0001432989,0.0001407961,2.065021e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002011346,"about_ca_system_score_gemma":0.00008024603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002731714,"about_ca_topic_score_gemma":3.664274e-7,"domain_scores_codex":[0.9987549,0.000005598269,0.0002134144,0.000533229,0.0002309408,0.0002619504],"domain_scores_gemma":[0.9993038,0.00001825549,0.00005478631,0.0002575199,0.0002111616,0.000154491],"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":[0.000001038422,0.00001115594,0.000001566311,0.00009287383,0.000003784681,3.970967e-7,0.0002222039,0.9656875,0.02421656,0.000006707194,0.0000034205,0.009752761],"study_design_scores_gemma":[0.0001607713,0.000007075882,0.000001312598,0.00007225138,0.000008037298,0.000002999384,0.0001202078,0.9016209,0.09773701,0.00005594463,0.000007654908,0.0002058831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01244144,0.0005202081,0.9858218,0.00001588387,0.0003221795,0.0004912844,0.00001052449,0.0002025971,0.0001740864],"genre_scores_gemma":[0.3137593,0.00003988798,0.6854931,0.0000144494,0.0001645907,0.0003878707,0.00009744714,0.00003374497,0.000009640421],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3013179,"threshold_uncertainty_score":0.7779069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396232400978441,"score_gpt":0.2643541096531786,"score_spread":0.2503917856433942,"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."}}