{"id":"W4417221948","doi":"10.1007/s44163-025-00646-6","title":"Performance of AI Chatbots on the fundamentals of engineering civil exam","year":2025,"lang":"en","type":"article","venue":"Discover Artificial Intelligence","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Chatbot; Engineering education; Domain (mathematical analysis); Curriculum; Applications of artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005333945,0.00112597,0.0008025445,0.0012916,0.0004207719,0.001508514,0.0008846304,0.001210745,0.002756484],"category_scores_gemma":[0.03282577,0.0002400489,0.0003761671,0.0005875517,0.0003535301,0.001576569,0.001724466,0.0009323988,0.002992427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005979565,"about_ca_system_score_gemma":0.0006315645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001816366,"about_ca_topic_score_gemma":0.002807559,"domain_scores_codex":[0.9954971,0.002039825,0.0003941938,0.0009414965,0.000732401,0.0003948796],"domain_scores_gemma":[0.9724954,0.01842423,0.00193968,0.001603133,0.002931903,0.002605754],"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":[0.008507545,0.00488522,0.2160137,0.00193287,0.0004054235,0.0008851632,0.01144677,0.02060705,0.05168432,0.001302047,0.02558748,0.6567423],"study_design_scores_gemma":[0.0006284742,0.01527952,0.6408274,0.0005928806,0.000360358,0.0008781024,0.01044657,0.224323,0.05803508,0.002310657,0.04592345,0.000394528],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911944,0.0001911767,0.002423165,0.0001421942,0.00008801078,0.0001054419,0.0006504171,0.001548372,0.003656797],"genre_scores_gemma":[0.986,0.0001269853,0.005681138,0.000117241,0.00003761648,0.0001350657,0.00249748,0.0001139131,0.005290613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005333945,"threshold_uncertainty_score":0.02820891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1148162170890376,"score_gpt":0.3925283864032781,"score_spread":0.2777121693142405,"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."}}