{"id":"W4410186776","doi":"10.1177/17442591251333433","title":"Enhancing building energy performance prediction: A fusion of deep learning and first-principles simulation methods","year":2025,"lang":"en","type":"article","venue":"Journal of Building Physics","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada","funders":"Office of Energy Research and Development","keywords":"Fusion; Deep learning; Energy (signal processing); Computer science; Architectural engineering; Artificial intelligence; Environmental science; Engineering; 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":[0.0004144506,0.0001310136,0.0002552272,0.0001862766,0.0001550582,0.00003261682,0.0000979252,0.00008663739,0.000003871378],"category_scores_gemma":[0.00007025323,0.0001329199,0.00007443914,0.0003664672,0.00002430087,0.0003807559,0.00005052482,0.0002327718,2.090458e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007494694,"about_ca_system_score_gemma":0.0000192109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003072088,"about_ca_topic_score_gemma":0.000001391356,"domain_scores_codex":[0.9990823,0.00004342896,0.0004823671,0.00009834167,0.000155691,0.0001378516],"domain_scores_gemma":[0.9992427,0.0002373334,0.0002491628,0.00008489458,0.0001475148,0.00003838292],"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":[0.00001829792,0.0000118914,0.001346814,0.0001432768,0.00006232405,4.601349e-7,0.0001260523,0.9159135,0.02381022,0.002431123,0.000002671443,0.05613337],"study_design_scores_gemma":[0.0002361226,0.00005447838,0.0003938069,0.0004619615,0.00005488985,0.00000587683,0.00002965821,0.8918315,0.104569,0.0005893888,0.001685386,0.00008796848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2981198,0.0007617534,0.7005991,0.000008018214,0.0003181339,0.00001853461,2.578634e-7,0.00003935571,0.0001350679],"genre_scores_gemma":[0.8841372,0.0008289925,0.1148195,0.000007635777,0.0001629541,0.000001554725,0.000001002886,0.00001745457,0.00002376557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5860174,"threshold_uncertainty_score":0.5420315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009508701835179881,"score_gpt":0.2634423751237938,"score_spread":0.2539336732886139,"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."}}