{"id":"W4285822645","doi":"10.26868/25222708.2021.30290","title":"Coupling of neural models for predicting indoor temperatures and heating loads in buildings","year":2021,"lang":"en","type":"article","venue":"Building Simulation Conference proceedings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Thermostat; HVAC; Mean squared error; Building energy simulation; Environmental science; Coupling (piping); Artificial neural network; Energy (signal processing); Work (physics); Computer science; Cooling load; Meteorology; Simulation; Engineering; Energy performance; Statistics; Mechanical engineering; Mathematics; Machine learning; Air conditioning; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002069559,0.0001881912,0.000270768,0.000180727,0.0001051283,0.0001276666,0.00009501917,0.0001347806,0.00000444319],"category_scores_gemma":[0.0001857129,0.0002171214,0.00004208653,0.0003629524,0.00003030955,0.0006072138,0.00004695038,0.0001864511,2.651207e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000433989,"about_ca_system_score_gemma":0.00003700198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001486116,"about_ca_topic_score_gemma":0.000005341333,"domain_scores_codex":[0.9988479,0.000002952162,0.000434576,0.0002967222,0.0001580747,0.0002597547],"domain_scores_gemma":[0.9992449,0.0001634355,0.000102331,0.0000679254,0.0003683986,0.00005301206],"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":[0.00001760245,0.00001076249,0.01707096,0.000244198,0.0000138,4.940812e-7,0.0005645207,0.9466274,0.02238724,0.01189468,0.000004259366,0.001164034],"study_design_scores_gemma":[0.0005355834,0.00002301676,0.0004491126,0.0003425622,0.00001589177,0.000005114981,0.0003591373,0.9744027,0.02062916,0.003022277,0.00001447257,0.0002010063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8768016,0.0002758115,0.1223451,0.00003259001,0.0001054277,0.0001864813,0.000004930139,0.000165732,0.00008237293],"genre_scores_gemma":[0.978934,0.00004377174,0.02083752,0.00002005655,0.00006536615,0.00003883246,0.00001215418,0.00003709531,0.00001122261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1021324,"threshold_uncertainty_score":0.8853953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02008435837511492,"score_gpt":0.2494661241947831,"score_spread":0.2293817658196682,"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."}}