{"id":"W4305072061","doi":"10.1016/j.buildenv.2022.109685","title":"Cohort comfort models — Using occupant’s similarity to predict personal thermal preference with less data","year":2022,"lang":"en","type":"article","venue":"Building and Environment","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Thermal comfort; Cohort; Preference; Population; Computer science; Leverage (statistics); Personalization; Statistics; Artificial intelligence; Geography; Medicine; Mathematics; Environmental health","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":[0.0001885688,0.0001470547,0.0001319282,0.00004253266,0.0002829375,0.00002942861,0.0002342842,0.00003301412,0.00004910886],"category_scores_gemma":[9.740963e-7,0.0001430347,0.00001296778,0.00006261492,0.00002892598,0.0001647874,0.0003825194,0.0001698951,1.620039e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109721,"about_ca_system_score_gemma":0.00001244112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006695098,"about_ca_topic_score_gemma":0.000002775431,"domain_scores_codex":[0.999055,0.00002168605,0.0001198076,0.0003178415,0.0002694611,0.0002162454],"domain_scores_gemma":[0.9995583,0.00001212978,0.00002188506,0.0003203013,0.000002288834,0.0000850928],"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":[0.00002509268,0.00002491812,0.01110574,0.00001163947,0.0000454105,0.000003352093,0.0001374334,0.9861564,0.0004912335,0.0001104424,0.0000986884,0.001789628],"study_design_scores_gemma":[0.000177271,0.00004741794,0.003092739,0.00001522555,0.00004136195,0.0000190622,0.00007705647,0.9950356,0.0001210877,0.00002873325,0.001144531,0.0001998548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.752732,0.0001261709,0.2466339,0.0000247518,0.00005628266,0.0001276266,0.00007889651,0.00008230347,0.0001381036],"genre_scores_gemma":[0.9867404,0.00007347222,0.01290778,0.00006311078,0.000031933,0.00004077511,0.00007871987,0.00002874496,0.00003511711],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2340084,"threshold_uncertainty_score":0.5832787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06260798492569304,"score_gpt":0.2094873092135976,"score_spread":0.1468793242879046,"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."}}