{"id":"W2990106565","doi":"10.1145/3363459.3363529","title":"Evaluating the Feasibility of Reusing Pre-trained Thermal Models in the Residential Sector","year":2019,"lang":"en","type":"article","venue":"","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Thermostat; Reuse; Computer science; Thermal mass; Energy consumption; Building automation; Home automation; Artificial neural network; Building model; Thermal comfort; Simulation; Engineering; Thermal; Machine learning; Telecommunications; Mechanical engineering; Meteorology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000686231,0.00006163133,0.00007342808,0.00002288815,0.00003093787,0.00001878614,0.0001858919,0.00004028667,0.00008626858],"category_scores_gemma":[0.00001755196,0.00003490143,0.00003254264,0.0001399582,0.0000138714,0.0001261531,0.00002120496,0.00009962513,5.562487e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000208887,"about_ca_system_score_gemma":0.00001464682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009978185,"about_ca_topic_score_gemma":0.00006907748,"domain_scores_codex":[0.9994079,0.0000789214,0.0001641147,0.00008404735,0.0001627491,0.0001022625],"domain_scores_gemma":[0.9995737,0.00009212426,0.00002473743,0.0002834719,0.00001948947,0.00000647101],"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":[0.00001631213,0.000007724015,0.0008758768,0.00001470531,0.000006156464,7.873732e-8,0.000760757,0.985236,0.01130464,0.001435374,0.00001264673,0.0003297554],"study_design_scores_gemma":[0.000181849,0.0000261193,0.006829086,0.00001558072,0.000005596945,7.343981e-7,0.00009214013,0.9901663,0.001497019,0.001136445,0.000001150375,0.00004799148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.98479,0.00003798859,0.009548662,0.00004770837,0.0001051308,0.0002050139,5.879057e-7,0.00004898081,0.005215961],"genre_scores_gemma":[0.998481,0.000002277374,0.001344948,0.00003146575,0.00003046996,0.000007778126,0.00000201384,0.000009436202,0.00009055866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01369109,"threshold_uncertainty_score":0.1423239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06353775754428301,"score_gpt":0.3098394194728813,"score_spread":0.2463016619285983,"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."}}