{"id":"W4410016010","doi":"10.1016/j.buildenv.2025.113101","title":"Identifying and classifying thermal anomalies in Arctic houses using two infrared cameras and different metrics","year":2025,"lang":"en","type":"article","venue":"Building and Environment","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Sentinelle Nord, Université Laval; Fonds de recherche du Québec; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Thermal infrared; Infrared; Arctic; Remote sensing; The arctic; Thermal; Environmental science; Computer science; Artificial intelligence; Computer vision; Geography; Geology; Meteorology; Optics; Oceanography; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000375498,0.0005238306,0.0003203529,0.001766671,0.0005288163,0.0007391178,0.0002926376,0.0002833634,0.0005070623],"category_scores_gemma":[0.0004143335,0.0001685136,0.0003017655,0.001301145,0.0003906566,0.0002356437,0.0003821181,0.000193748,0.000170291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001231578,"about_ca_system_score_gemma":0.0007820014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2349442,"about_ca_topic_score_gemma":0.5261814,"domain_scores_codex":[0.9996455,0.00003545942,0.00001998292,0.00009449029,0.0001275672,0.00007709212],"domain_scores_gemma":[0.9995851,0.00003585704,0.0000559507,0.00002054628,0.0002607234,0.00004179657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003671849,0.00009745367,0.8555853,0.0001749113,0.0001002293,0.0005274102,0.002166985,0.004592307,0.07460871,0.0001847379,0.0004857896,0.0611089],"study_design_scores_gemma":[0.000004528088,0.00006921278,0.9736183,0.00002611648,0.00005573801,0.0001976489,0.002705059,0.01378439,0.008803212,0.00003578071,0.0006759158,0.00002399515],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968109,0.00009687826,0.001986476,0.000008116725,0.000004969416,0.00003119308,0.0002979593,0.00003510338,0.0007284454],"genre_scores_gemma":[0.9936387,0.00007367943,0.005274594,0.000006734778,0.000001949381,0.00001542556,0.0003927672,0.000007709938,0.0005884455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2349442,"threshold_uncertainty_score":0.4671534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01515652641411536,"score_gpt":0.2242660116933796,"score_spread":0.2091094852792643,"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."}}