{"id":"W4389265746","doi":"10.1016/j.enbuild.2023.113811","title":"Thermal modeling for control applications of 60,000 homes in North America using smart thermostat data","year":2023,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Thermostat; Leverage (statistics); Building energy simulation; Computer science; Flexibility (engineering); Thermal comfort; Building model; Metadata; Energy modeling; Model predictive control; Engineering; Simulation; Efficient energy use; Control (management); Mathematics; Statistics; Mechanical engineering; Geography; Machine learning; Artificial intelligence; Energy performance","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":[0.00009730954,0.00009817076,0.0001499106,0.0001255514,0.00006202961,0.00001336326,0.0001549248,0.00005175008,0.000003441291],"category_scores_gemma":[0.000007453142,0.00009738671,0.00002145432,0.0003784351,0.0000233279,0.0001811304,0.00004484651,0.00004315097,1.022774e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000121469,"about_ca_system_score_gemma":0.000008894817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001529449,"about_ca_topic_score_gemma":0.00005390584,"domain_scores_codex":[0.9994156,0.00000894358,0.0001741535,0.0001486762,0.00006176095,0.0001908655],"domain_scores_gemma":[0.9996603,0.00005768277,0.00003097683,0.0002009101,0.00001838727,0.00003175299],"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":[0.00001166665,0.000009384156,0.0009347241,0.00002378779,0.00002506085,2.671077e-7,0.00009313242,0.9845687,0.0009188193,0.0007113901,0.00004737429,0.01265572],"study_design_scores_gemma":[0.0002677138,0.000007866133,0.000137007,0.0000156527,0.00001534643,5.413411e-7,0.00005399794,0.9955112,0.000225809,0.0001141046,0.003540372,0.0001103341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4649442,0.0003902417,0.5343161,0.00001619746,0.00004854537,0.00006955931,0.00005498319,0.0001019114,0.00005819061],"genre_scores_gemma":[0.9951114,0.0003602601,0.004151001,0.0000397698,0.00005593702,0.00005409684,0.0001822613,0.00002670221,0.00001855663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5301672,"threshold_uncertainty_score":0.3971315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01793536617614158,"score_gpt":0.2268861211904071,"score_spread":0.2089507550142655,"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."}}