{"id":"W3173347419","doi":"10.1115/vvs2021-65268","title":"Bayesian Calibrating Educational Building Thermal Models to Hourly Indoor Air Temperature: Methodology and Case Study","year":2021,"lang":"en","type":"article","venue":"","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Building energy simulation; Calibration; Bayesian inference; Computer science; Environmental science; Thermal comfort; Bayesian probability; Uncertainty analysis; HVAC; Building model; Inference; Sensitivity (control systems); Efficient energy use; Process (computing); Air conditioning; Simulation; Energy performance; Meteorology; Engineering; Statistics; Artificial intelligence; Geography; Mechanical engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002738247,0.0007129463,0.0006294502,0.0007707348,0.0004742172,0.0008601435,0.001212121,0.001496161,0.001333151],"category_scores_gemma":[0.004946669,0.0004812564,0.00113908,0.0007422022,0.0006341985,0.0005799214,0.0008233187,0.001125161,0.0001654345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001321555,"about_ca_system_score_gemma":0.0009173435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02301693,"about_ca_topic_score_gemma":0.01114674,"domain_scores_codex":[0.999102,0.0005006044,0.0000375206,0.0001212935,0.0001578504,0.0000807691],"domain_scores_gemma":[0.9971265,0.002031388,0.0001967911,0.0002153865,0.0003702893,0.00005956465],"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":[0.00003656965,0.00007291717,0.002698313,0.00004195663,0.00002223267,0.0001119999,0.00003882341,0.9895169,0.0005059742,0.001450032,0.0001308236,0.005373402],"study_design_scores_gemma":[0.000008604745,0.00003239701,0.000930512,0.000009299158,0.00001225536,0.0000166093,0.00003124222,0.9971392,0.0009219773,0.0006676425,0.0002201927,0.00001009162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6704054,0.0003193996,0.3210939,0.0002768067,0.00002936133,0.0002759791,0.0004827949,0.0003604689,0.006755929],"genre_scores_gemma":[0.975225,0.00007421256,0.02384365,0.00001607839,0.000006305626,0.00008891794,0.0001573098,0.00001876724,0.000569816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02301693,"threshold_uncertainty_score":0.04576594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03414041274470526,"score_gpt":0.2730497250677337,"score_spread":0.2389093123230284,"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."}}