{"id":"W3092530885","doi":"10.1088/2632-2153/abedc8","title":"Olympus: a benchmarking framework for noisy optimization and experiment planning","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of British Columbia; Vector Institute; University of Toronto","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Benchmarking; Suite; Benchmark (surveying); Python (programming language); Probabilistic logic; Software; Task (project management); Automation","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001807351,0.0002006245,0.0002735933,0.000363843,0.001325353,0.0004674572,0.0004024846,0.0001568866,0.0001712574],"category_scores_gemma":[0.003249202,0.0001868768,0.0000181553,0.001088804,0.001133864,0.0003444352,0.0005798411,0.0003030847,0.00000559411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005557209,"about_ca_system_score_gemma":0.0001747936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002233636,"about_ca_topic_score_gemma":0.000002009307,"domain_scores_codex":[0.9977574,0.00008009357,0.0002764105,0.0009132065,0.0003956404,0.0005772821],"domain_scores_gemma":[0.9988904,0.0002348335,0.0001881191,0.0002994325,0.0002785353,0.0001086989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001774543,0.00003477516,0.01800586,0.00005520674,0.000004002068,0.00002195277,0.0009905117,0.02973596,0.9087718,0.03344696,0.0000142725,0.008901],"study_design_scores_gemma":[0.0006401241,0.0005113726,0.00108688,0.0002385652,0.00002379321,0.000339056,0.0009202742,0.6788179,0.3021099,0.01145611,0.003258393,0.0005976188],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.735937,0.001330197,0.2592604,0.002251227,0.0004585062,0.0002024179,0.000003512736,0.0003449432,0.0002117859],"genre_scores_gemma":[0.6521312,0.00003716688,0.3474794,0.0001653635,0.00006303353,0.00004444601,0.00000412295,0.00001502937,0.00006024994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.649082,"threshold_uncertainty_score":0.9999748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01001838752986364,"score_gpt":0.2885465198786015,"score_spread":0.2785281323487379,"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."}}