{"id":"W7163681196","doi":"10.13182/t130-39757","title":"A Review of the Status of the Evaluated Reactor Physics Benchmark Experiments Project","year":2022,"lang":"","type":"article","venue":"Transactions of the American Nuclear Society","topic":"Nuclear reactor physics and engineering","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alchemy (Canada)","funders":"","keywords":"Benchmark (surveying); Nuclear reactor","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":[],"consensus_categories":[],"category_scores_codex":[0.0002656054,0.0003287267,0.000673686,0.00002030861,0.0003960524,0.00001167918,0.00119286,0.00003936168,0.0002989482],"category_scores_gemma":[0.00002448461,0.0002232788,0.001655686,0.002265388,0.0006278456,0.0001032131,0.0002062962,0.0008937421,0.000001255752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004542826,"about_ca_system_score_gemma":0.0002952726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001577749,"about_ca_topic_score_gemma":0.000002219801,"domain_scores_codex":[0.9974645,0.000272257,0.0006648752,0.0002613452,0.0008283121,0.0005086568],"domain_scores_gemma":[0.9974982,0.00007829144,0.0007748703,0.001454128,0.0001284155,0.0000661438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001708244,0.002397051,0.0004385078,0.01487642,0.00593093,2.878015e-7,0.04458662,0.1509101,0.7137317,0.0007070408,0.02166814,0.0445824],"study_design_scores_gemma":[0.00465529,0.002008614,0.02702011,0.02101231,0.008207618,0.00003846654,0.05351191,0.3137116,0.07475052,0.0002422616,0.4912708,0.00357054],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9721954,0.0140008,0.0007040843,0.0008447094,0.003109976,0.004118592,0.001905122,0.0001675124,0.002953838],"genre_scores_gemma":[0.9873871,0.01185294,0.0003081512,0.0001986505,0.00003719393,0.00003417462,0.000002399701,0.0001331721,0.00004625784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6389812,"threshold_uncertainty_score":0.9105043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01980067363291164,"score_gpt":0.2610546370576911,"score_spread":0.2412539634247794,"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."}}