{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004264579,0.0001486205,0.0002775487,0.0001853135,0.00008825037,0.00001730931,0.0001895122,0.00007995276,0.0002687708],"category_scores_gemma":[0.0003730402,0.0001092881,0.0001126073,0.0005847745,0.0001862808,0.0001092568,0.00004294821,0.0002534613,0.00005438647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007343113,"about_ca_system_score_gemma":0.0002547124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002971285,"about_ca_topic_score_gemma":0.00004826379,"domain_scores_codex":[0.998483,0.00003358841,0.0007276822,0.0002276439,0.0002853803,0.0002427286],"domain_scores_gemma":[0.9987911,0.000390889,0.0001322977,0.000430465,0.0002018533,0.00005338173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001890011,0.002052662,0.1006412,0.002035881,0.0003024939,0.000006238497,0.009246346,0.0148299,0.1286106,0.3967342,0.001608658,0.3420418],"study_design_scores_gemma":[0.000008292468,0.0003730885,0.004414879,0.0007167538,0.00004021577,0.000001602291,0.001671773,0.01582112,0.973667,0.002821851,0.0003661267,0.00009734707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893335,0.0001348709,0.00378866,0.002973625,0.0006995653,0.0004573514,0.000008035828,0.00002137462,0.002583089],"genre_scores_gemma":[0.9986846,0.0001101977,0.00006126301,0.0007146144,0.0001040818,0.00003512066,0.000006483637,0.00001160905,0.0002720385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8450564,"threshold_uncertainty_score":0.4456639,"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."}}