{"id":"W4408251534","doi":"10.2196/67244","title":"Large Language Models in Biochemistry Education: Comparative Evaluation of Performance","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Course (navigation); Computational biology; Data science; Biology; World Wide Web; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0220667,0.00145566,0.001361531,0.003601205,0.0006264321,0.003051657,0.001388656,0.001767232,0.002425694],"category_scores_gemma":[0.07131179,0.0003690262,0.001388088,0.002162922,0.0008104742,0.003760612,0.003048238,0.001779562,0.001506665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001544169,"about_ca_system_score_gemma":0.001266793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003877663,"about_ca_topic_score_gemma":0.003533421,"domain_scores_codex":[0.9805222,0.0136949,0.001534116,0.001839853,0.001991094,0.0004179018],"domain_scores_gemma":[0.8774068,0.1093308,0.002989199,0.003062031,0.003955132,0.003255941],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02514016,0.009190421,0.1793543,0.003320047,0.002429358,0.0003796271,0.005007686,0.05994641,0.004380569,0.001536316,0.01107299,0.6982422],"study_design_scores_gemma":[0.002399823,0.02773608,0.2478438,0.001042462,0.003054122,0.0009476994,0.008407818,0.6801251,0.01127618,0.006661377,0.009940087,0.0005654508],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9730154,0.004910246,0.01109774,0.0009067483,0.0003081341,0.0003768525,0.001199629,0.00155591,0.006629186],"genre_scores_gemma":[0.9848552,0.001050376,0.01042795,0.0001299396,0.000124713,0.0002118319,0.002057103,0.0001314452,0.00101145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9779333,"threshold_uncertainty_score":0.1167012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1161257107869459,"score_gpt":0.5239413793665126,"score_spread":0.4078156685795667,"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."}}