{"id":"W4389223874","doi":"10.1088/1742-6596/2600/8/082006","title":"How good is the advice from ChatGPT for building science? Comparison of four scenarios","year":2023,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Brainstorming; Advice (programming); Computer science; Inference; Domain (mathematical analysis); Public domain; Data science; Artificial intelligence; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0264542,0.0008371283,0.0009297813,0.003030173,0.003169825,0.007450006,0.003071486,0.006073384,0.0199672],"category_scores_gemma":[0.1144533,0.0006137014,0.001066603,0.002616119,0.003513154,0.008453482,0.004553545,0.002681033,0.005037726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003108847,"about_ca_system_score_gemma":0.003188622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005599834,"about_ca_topic_score_gemma":0.007376791,"domain_scores_codex":[0.9779979,0.01681484,0.0005676934,0.0009281134,0.002931441,0.0007600027],"domain_scores_gemma":[0.8626313,0.1085182,0.002504904,0.01036417,0.01241822,0.003563152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005486611,0.001576219,0.03938461,0.005586214,0.0003809543,0.004448058,0.03099808,0.09064798,0.006966523,0.3088509,0.1485702,0.3571037],"study_design_scores_gemma":[0.0007109664,0.00147106,0.01856097,0.002400624,0.0002894773,0.002187344,0.03233901,0.3433054,0.01370964,0.3063331,0.278083,0.0006095454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3489833,0.005366262,0.2734027,0.08147954,0.001793556,0.0008467848,0.003402115,0.009311398,0.2754143],"genre_scores_gemma":[0.909002,0.0009598839,0.07455306,0.003190431,0.0002390488,0.0004141326,0.001501378,0.0007772588,0.009362717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0264542,"threshold_uncertainty_score":0.1399049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03313587853056629,"score_gpt":0.2611291914245325,"score_spread":0.2279933128939662,"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."}}