{"id":"W4409093442","doi":"10.2196/73698","title":"Authors’ Reply: Citation Accuracy Challenges Posed by Large Language Models","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Citation; Computer science; Library science","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","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.009149401,0.0007655388,0.00109993,0.001447569,0.002793566,0.003527539,0.002275091,0.01913348,0.01561701],"category_scores_gemma":[0.1172944,0.0005313542,0.001234979,0.001220619,0.003119267,0.004877743,0.002044916,0.02676021,0.0121949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002306695,"about_ca_system_score_gemma":0.004670808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003747914,"about_ca_topic_score_gemma":0.004968964,"domain_scores_codex":[0.9959936,0.001006108,0.0008189307,0.0006604092,0.001183883,0.0003371155],"domain_scores_gemma":[0.9380783,0.03304939,0.002511878,0.002455495,0.02175295,0.002151898],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004923102,0.00001377976,0.0006225744,0.00010366,0.00002014332,0.000255315,0.0002142176,0.00007588125,0.0001264217,0.001843457,0.9879602,0.008715243],"study_design_scores_gemma":[0.000085277,0.00005680153,0.001444902,0.0003946007,0.0000512511,0.00167403,0.0008566745,0.000698368,0.000911557,0.01197257,0.981716,0.0001380502],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0003707973,0.0008659542,0.000509901,0.9573676,0.03973613,0.00001150099,0.000214625,0.0001179595,0.0008055478],"genre_scores_gemma":[0.008592375,0.002060584,0.001684541,0.9248579,0.05511583,0.00007805362,0.0001831217,0.0001165025,0.007311034],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9985524,"threshold_uncertainty_score":0.05224413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09489012269270007,"score_gpt":0.4803000377405062,"score_spread":0.3854099150478061,"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."}}