{"id":"W4405357813","doi":"10.2139/ssrn.5038555","title":"Performance of ChatGPT and Gemini on the Fundamentals of Engineering (FE) Civil Exam: A Preliminary Comparison and Potential Implications for Civil Engineering Education","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics education; Engineering; Civil engineering; Engineering ethics; Psychology","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":[0.01154459,0.0006280285,0.001422708,0.001730603,0.001134724,0.0024497,0.001479261,0.001732438,0.01983408],"category_scores_gemma":[0.0414712,0.0003119216,0.0005917591,0.001616438,0.0005081808,0.002485739,0.00243264,0.001755529,0.006122938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001481667,"about_ca_system_score_gemma":0.002620856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01206122,"about_ca_topic_score_gemma":0.01722123,"domain_scores_codex":[0.9959275,0.002058132,0.0002285299,0.0006626892,0.0007286905,0.000394346],"domain_scores_gemma":[0.958026,0.02704865,0.00199713,0.002343551,0.003335706,0.007248934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.07360903,0.0067019,0.186905,0.001060008,0.0003525481,0.0002455106,0.003727047,0.007526516,0.01018174,0.003867496,0.03455711,0.671266],"study_design_scores_gemma":[0.003434511,0.02363337,0.815621,0.000281603,0.0005753923,0.0005054551,0.005596941,0.06208694,0.02672608,0.004214458,0.05701574,0.0003086092],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9418846,0.001650418,0.005406596,0.002608459,0.0005124251,0.0004984931,0.002447674,0.002339736,0.0426515],"genre_scores_gemma":[0.9625815,0.0004695602,0.009433609,0.0006844383,0.000147897,0.000190012,0.002808705,0.0002959281,0.02338828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01983408,"threshold_uncertainty_score":0.06635159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05640264553532058,"score_gpt":0.3630478927673806,"score_spread":0.30664524723206,"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."}}