{"id":"W4283589003","doi":"10.2196/37817","title":"A Syntactic Information–Based Classification Model for Medical Literature: Algorithm Development and Validation Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Computer science; Algorithm; Data mining; Information model; Artificial intelligence; Natural language processing; Software 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001082003,0.0001437448,0.0001600865,0.0001030957,0.0002913066,0.00006334706,0.0002781881,0.0002283773,0.00004097663],"category_scores_gemma":[0.0005864041,0.0001228802,0.0000417109,0.0001593037,0.00009309468,0.00002424224,0.0002189183,0.0002813436,0.000003546158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004036989,"about_ca_system_score_gemma":0.0006359979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.447507e-7,"about_ca_topic_score_gemma":0.00000202979,"domain_scores_codex":[0.9979627,0.00006176437,0.000633131,0.0001243656,0.001000101,0.0002179304],"domain_scores_gemma":[0.9991977,0.00007070017,0.000182913,0.0002004708,0.0001035319,0.0002447386],"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":[0.0001764216,0.0007070193,0.0005952573,0.0003119515,0.0001165292,0.000004462614,0.01371426,0.0001539714,0.00004495011,0.0001861358,0.01012735,0.9738617],"study_design_scores_gemma":[0.002230131,0.0005822682,0.0005537458,0.00003913463,0.00001993828,0.00003855729,0.005309312,0.9082049,0.0002383612,0.00004992051,0.08248635,0.0002473535],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4177074,0.0001166581,0.5792584,0.001280773,0.0002319121,0.001092003,0.00006841061,0.00007992068,0.0001644972],"genre_scores_gemma":[0.9294623,0.00002421309,0.06321526,0.003354031,0.0001077161,0.001654571,0.002052792,0.00001528485,0.0001138247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9736143,"threshold_uncertainty_score":0.5010911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02448416749302044,"score_gpt":0.3111505147853861,"score_spread":0.2866663472923657,"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."}}