{"id":"W4415749046","doi":"10.2196/75932","title":"A Multiagent Summarization and Auto-Evaluation Framework for Medical Text: Development and Evaluation Study","year":2025,"lang":"en","type":"article","venue":"JMIR AI","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Cleveland Clinic","keywords":"Automatic summarization; Adaptability; Key (lock); Dependency (UML); Scalability; Salient","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":[0.00196934,0.00007736631,0.00009040081,0.00009291022,0.0001437229,0.0001168975,0.0001480534,0.00007946385,0.00001131692],"category_scores_gemma":[0.0004826613,0.00007231923,0.000009970134,0.0001562705,0.00001197831,0.000165116,0.0001545016,0.00007947731,0.000001258231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008539859,"about_ca_system_score_gemma":0.000341074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006450134,"about_ca_topic_score_gemma":0.00003135089,"domain_scores_codex":[0.9986065,0.0001170211,0.0002217914,0.0003377543,0.0006074221,0.0001095141],"domain_scores_gemma":[0.9993677,0.0001465729,0.00004647825,0.0001979233,0.0001926357,0.00004868164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005333925,0.0001073598,0.006638094,0.00002668413,0.00001972992,3.437611e-7,0.004596118,0.0002626354,0.00001194004,0.01519134,0.0001128818,0.9730275],"study_design_scores_gemma":[0.0008210186,0.0000327467,0.06990685,0.00005752256,0.00001745499,4.789361e-7,0.00009500146,0.9178432,0.00005262003,0.01030693,0.0007959698,0.00007017238],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.20993,0.0001114127,0.7864499,0.0016975,0.0002047385,0.001520321,1.944235e-7,0.0000385931,0.0000473302],"genre_scores_gemma":[0.9105574,0.000002297979,0.08825644,0.0004161683,0.00003133382,0.0006898943,0.000005220597,0.00000324533,0.00003796409],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9729574,"threshold_uncertainty_score":0.2949093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04394454882875393,"score_gpt":0.3929848069328207,"score_spread":0.3490402581040667,"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."}}