{"id":"W4405105245","doi":"10.1016/j.egyai.2024.100450","title":"Digital twin-centered hybrid data-driven multi-stage deep learning framework for enhanced nuclear reactor power prediction","year":2024,"lang":"en","type":"article","venue":"Energy and AI","topic":"Nuclear reactor physics and engineering","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; National Research Council; U.S. Nuclear Regulatory Commission; National Science Foundation","keywords":"Stage (stratigraphy); Nuclear power; Artificial intelligence; Deep learning; Computer science; Power (physics); Machine learning; Physics; Nuclear physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002793615,0.0001461232,0.0001227288,0.00004677935,0.000049822,0.0002196736,0.0001092588,0.00006206459,0.00003434085],"category_scores_gemma":[0.00002032643,0.0001483341,0.00004248898,0.00006487405,0.00001377934,0.0004857542,0.000062055,0.0002016449,0.00001046319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002483481,"about_ca_system_score_gemma":0.000003674608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003106827,"about_ca_topic_score_gemma":0.000001275111,"domain_scores_codex":[0.9993691,0.000003744904,0.0001226811,0.0002361557,0.00006872711,0.0001995206],"domain_scores_gemma":[0.9996725,0.00004461773,0.00001124207,0.0001880587,0.00001122032,0.00007230909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001291968,0.0002485355,0.0001683095,0.001150905,0.001508971,0.00009570539,0.00308126,0.1999226,0.2678382,0.1286647,0.005400521,0.3917911],"study_design_scores_gemma":[0.0001209423,0.00003007877,0.00004663717,0.00009069223,0.00001030725,0.000002235045,0.00003784282,0.5820455,0.000815655,0.0001032813,0.4165564,0.0001403832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1396774,0.0008581252,0.8526428,0.00003909742,0.001732976,0.0001119309,0.0004179262,0.001524262,0.002995459],"genre_scores_gemma":[0.997731,0.0001404138,0.001298122,0.0000200163,0.0002536782,0.000005867848,0.0002411552,0.00009663511,0.0002130972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8580536,"threshold_uncertainty_score":0.604889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01582883564728739,"score_gpt":0.2336183406848663,"score_spread":0.2177895050375789,"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."}}