{"id":"W4220908063","doi":"10.1016/j.enbuild.2022.112068","title":"Addressing data inadequacy challenges in personal comfort models by combining pretrained comfort models","year":2022,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Thermal comfort; Computer science; Preference; A priori and a posteriori; Simulation; Statistics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003929408,0.0002550222,0.0002893611,0.0001835695,0.0003439927,0.00006243,0.0004621811,0.0001177325,0.00004267617],"category_scores_gemma":[0.000005476466,0.0002962685,0.00003505602,0.0002556902,0.00005265227,0.0008791914,0.0003321608,0.0003495793,5.525977e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009320676,"about_ca_system_score_gemma":0.00002838319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001808383,"about_ca_topic_score_gemma":0.0000648879,"domain_scores_codex":[0.9984801,0.00005068301,0.0003069102,0.0004611884,0.0003010031,0.0004001333],"domain_scores_gemma":[0.9994355,0.00006099588,0.00006126943,0.0003352271,0.00001314145,0.0000937968],"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":[0.00002752322,0.00005174151,0.0000426833,0.00003709907,0.00003929751,0.000008418849,0.0008524072,0.9449318,0.0002967227,0.03774237,0.001757255,0.01421267],"study_design_scores_gemma":[0.0006158746,0.00004466376,0.000006855556,0.00005895175,0.00001476744,0.00003018447,0.0004178891,0.9840474,0.0001814859,0.005624008,0.008600846,0.0003571133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.602672,0.0551648,0.3124025,0.00111193,0.001236277,0.0004057226,0.0004020626,0.001663109,0.02494161],"genre_scores_gemma":[0.9947531,0.00233992,0.001952269,0.0001630987,0.00004680924,0.00006427002,0.0004509605,0.00006265357,0.0001669512],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3920811,"threshold_uncertainty_score":0.9999489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09905113293928315,"score_gpt":0.2482649734842279,"score_spread":0.1492138405449447,"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."}}