{"id":"W4391543065","doi":"10.1016/j.buildenv.2024.111268","title":"A comparative analysis of machine learning and statistical methods for evaluating building performance: A systematic review and future benchmarking framework","year":2024,"lang":"en","type":"review","venue":"Building and Environment","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Benchmarking; Computer science; Machine learning; Artificial intelligence; Statistical analysis; Engineering; Management science; Statistics; Mathematics; Economics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001291422,0.0004187812,0.002537807,0.0002857012,0.000145812,0.00005968509,0.00007892644,0.0002072803,0.00001611561],"category_scores_gemma":[0.00005214423,0.0003297339,0.0001683855,0.0003314685,0.00005382558,0.00005276889,0.0001071025,0.0004337625,1.307239e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008083195,"about_ca_system_score_gemma":0.000009796149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001945536,"about_ca_topic_score_gemma":1.551791e-7,"domain_scores_codex":[0.9982457,0.0002248253,0.000741042,0.000423994,0.0001459572,0.0002184367],"domain_scores_gemma":[0.9987671,0.0007405424,0.0002380668,0.0001653905,0.000009716461,0.0000791959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001675588,0.000005968363,0.000004151038,0.7052115,0.002349123,4.50391e-7,0.0001503536,0.03140648,0.000001974019,0.001069538,0.000004368269,0.2597944],"study_design_scores_gemma":[0.0000567129,0.00008018827,0.000001990435,0.1469202,0.04579392,0.00001677101,0.00002384461,0.7890096,0.000001202785,0.00007037206,0.01766472,0.0003603935],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00003367898,0.7304732,0.2687874,0.000003954637,0.00005976809,0.0005695735,0.00002679325,0.00003856178,0.000007091998],"genre_scores_gemma":[0.0001374475,0.7540054,0.2454577,0.000005649886,0.00004252734,0.0002447147,0.00006446627,0.00003355673,0.000008527389],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7576032,"threshold_uncertainty_score":0.9999155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03210962319066626,"score_gpt":0.3772872998526078,"score_spread":0.3451776766619415,"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."}}