{"id":"W4396229344","doi":"10.1080/19401493.2024.2346833","title":"Retraining surrogate models in increasingly restricted design spaces: a novel building energy model calibration method","year":2024,"lang":"en","type":"article","venue":"Journal of Building Performance Simulation","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Surrogate model; Latin hypercube sampling; Calibration; Energy (signal processing); Building energy simulation; Computer science; Mathematical optimization; Algorithm; Polynomial; Mathematics; Statistics; Energy performance; Monte Carlo method","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":[0.0009929176,0.0002228258,0.0002880197,0.0009388303,0.00009218881,0.0001968004,0.000163796,0.0001988553,0.000003941656],"category_scores_gemma":[0.00005934007,0.0002225673,0.00008723782,0.0009913496,0.00001438969,0.002406015,0.00002223657,0.0004008826,8.664951e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003210243,"about_ca_system_score_gemma":0.0001195023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001909551,"about_ca_topic_score_gemma":0.000002636525,"domain_scores_codex":[0.9983656,0.00006524151,0.0007363781,0.0001893614,0.0003597745,0.0002836705],"domain_scores_gemma":[0.9992138,0.0002895702,0.0001770106,0.000129387,0.0001157602,0.00007454651],"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":[0.00007588088,0.00001592528,0.00004144087,0.00007286297,0.00003799368,0.000006211624,0.0004215121,0.9722831,0.01622098,0.002472247,0.00001896987,0.008332912],"study_design_scores_gemma":[0.0004458065,0.00006380009,0.00003341753,0.0007551399,0.00003692607,0.00003815803,0.00001835956,0.991371,0.005162743,0.0017972,0.00004813219,0.0002292553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2700056,0.0003496751,0.7290536,0.00002105223,0.0003081397,0.00005288723,0.000001300122,0.0001445373,0.00006316144],"genre_scores_gemma":[0.7151067,0.0001912295,0.2844839,0.00001493612,0.000137955,0.000003636194,0.000004171227,0.00004713806,0.00001038374],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4451011,"threshold_uncertainty_score":0.9076032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04002775762091131,"score_gpt":0.2757304122420546,"score_spread":0.2357026546211433,"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."}}