{"id":"W4380989093","doi":"10.2196/47434","title":"A Deep Learning Model for the Normalization of Institution Names by Multisource Literature Feature Fusion: Algorithm Development Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chinese Academy of Medical Sciences","keywords":"Normalization (sociology); Computer science; Artificial intelligence; Institution; Deep learning; Natural language processing; Scopus; Machine learning; Information retrieval; Political science; Law","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":[],"consensus_categories":[],"category_scores_codex":[0.001296251,0.0008729979,0.0009002181,0.0009620709,0.0004657165,0.000842475,0.001705192,0.001188823,0.002447872],"category_scores_gemma":[0.002270894,0.0004674062,0.0009101952,0.001168427,0.0004072645,0.001387459,0.001253354,0.001723332,0.0008170966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001394141,"about_ca_system_score_gemma":0.002513417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0163242,"about_ca_topic_score_gemma":0.01233073,"domain_scores_codex":[0.9996569,0.00005411114,0.00002624667,0.0001215802,0.000080594,0.00006058976],"domain_scores_gemma":[0.9994142,0.0001881239,0.00004588655,0.00004858257,0.0002692899,0.00003397107],"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":[0.0001490122,0.0001961049,0.003966013,0.0001060176,0.0001413375,0.0001323201,0.00009531476,0.4236793,0.005462734,0.004988764,0.004693192,0.55639],"study_design_scores_gemma":[0.0000047682,0.00001427505,0.0001556051,0.000004748746,0.00001105925,0.00001435056,0.000007870045,0.9979882,0.0008122663,0.0007302617,0.0002531785,0.000003283552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04014363,0.0006274937,0.9540635,0.0004875293,0.0000827557,0.0001395837,0.0002100677,0.002393567,0.00185189],"genre_scores_gemma":[0.6101101,0.0006739929,0.3796937,0.0003890877,0.00007586434,0.0005178689,0.001362671,0.0001280332,0.007048722],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0163242,"threshold_uncertainty_score":0.03245836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03768942248781827,"score_gpt":0.3803296186251347,"score_spread":0.3426401961373164,"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."}}