{"id":"W4380992713","doi":"10.1051/e3sconf/202339602034","title":"A training dataset for machine learning-based prediction of window opening position in a naturally ventilated building","year":2023,"lang":"en","type":"article","venue":"E3S Web of Conferences","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Window (computing); Computer science; Artificial intelligence; Ground truth; Machine learning; Operating system","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":[0.0002475407,0.00008158396,0.0001595107,0.0002451139,0.00003411206,0.00001435345,0.00009861236,0.00006814603,0.00001742778],"category_scores_gemma":[0.00004094197,0.00008508687,0.00003137786,0.0003305951,0.0000196053,0.000128885,0.00001176695,0.0001053968,1.544395e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001236781,"about_ca_system_score_gemma":0.00007354423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003851109,"about_ca_topic_score_gemma":0.00005712772,"domain_scores_codex":[0.9994065,0.00002157118,0.0002423165,0.0001039433,0.0001023489,0.0001233685],"domain_scores_gemma":[0.9997267,0.00008388329,0.00007436167,0.00006468353,0.00003339066,0.00001705107],"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":[0.00004257894,0.000008638524,0.002117891,0.00006990699,0.00002204117,7.972497e-7,0.0001007267,0.9700522,0.02441646,0.0006171347,0.00004984398,0.002501827],"study_design_scores_gemma":[0.0004738079,0.00009026172,0.002310392,0.0002484076,0.00001330655,6.266187e-7,0.0000577979,0.9832164,0.01265041,0.0001097224,0.000757163,0.00007170267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9733143,0.0001366782,0.02505763,0.00004162803,0.0002364432,0.0002203045,0.0005767024,0.0002095819,0.0002067337],"genre_scores_gemma":[0.9946954,0.00002357414,0.001711628,0.000004495022,0.00001534772,0.0000245209,0.003507401,0.00001157757,0.000006055858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02334601,"threshold_uncertainty_score":0.3469742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0300754755646365,"score_gpt":0.253061572551651,"score_spread":0.2229860969870145,"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."}}