{"id":"W4414602669","doi":"10.1038/s41598-025-11086-8","title":"Evaluating ChatGPT’s ability to simplify scientific abstracts for clinicians and the public","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Bruyère; Kingston Health Sciences Centre; Queen's University; Providence Health Care","funders":"","keywords":"Readability; Jargon; Consistency (knowledge bases); Reading (process); Rigour; Reliability (semiconductor); Test (biology); MEDLINE","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2184267,0.001672571,0.003366977,0.01677601,0.001645184,0.006574139,0.002631646,0.002034886,0.006522391],"category_scores_gemma":[0.6564059,0.001363749,0.005620468,0.007679674,0.001625302,0.007526094,0.009844928,0.002500387,0.002584804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004004356,"about_ca_system_score_gemma":0.006977671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001230444,"about_ca_topic_score_gemma":0.003505392,"domain_scores_codex":[0.7709541,0.1249736,0.06627697,0.005289791,0.03074606,0.001759477],"domain_scores_gemma":[0.1439065,0.6296148,0.0827869,0.03118687,0.1075066,0.004998467],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.006144322,0.0006041476,0.07199626,0.05760005,0.003637907,0.001366539,0.03541009,0.002441826,0.009538359,0.001459292,0.06181829,0.747983],"study_design_scores_gemma":[0.007009384,0.01697123,0.4190819,0.06199597,0.01473041,0.02003139,0.03191582,0.02623038,0.03006706,0.01418693,0.35434,0.003439545],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6276692,0.0609611,0.1730343,0.02878499,0.008581052,0.04147498,0.016123,0.01223572,0.03113578],"genre_scores_gemma":[0.5907863,0.01398043,0.3377707,0.005367174,0.00333999,0.03390685,0.00768997,0.001697858,0.005460676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7815733,"threshold_uncertainty_score":0.963819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2818935628062844,"score_gpt":0.5271029647745198,"score_spread":0.2452094019682354,"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."}}