{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009205617,0.00009538679,0.0001037298,0.00009477977,0.0004797031,0.00003731065,0.0002112826,0.0001613624,0.000001605278],"category_scores_gemma":[0.0002305974,0.00006074586,0.0000409487,0.0004538788,0.0001544534,0.000009306651,0.0002163429,0.0002689365,0.000003583016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002145229,"about_ca_system_score_gemma":0.00007154512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003225502,"about_ca_topic_score_gemma":0.00001046571,"domain_scores_codex":[0.9989046,0.0001389724,0.0001598913,0.0001781692,0.0003544993,0.0002638696],"domain_scores_gemma":[0.9993466,0.00008750866,0.00005972263,0.0001382183,0.0003266275,0.00004130523],"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":[0.0002704646,0.0003703306,0.001038201,0.0002114642,0.0001765179,0.00000239055,0.06842422,0.004263296,0.01581601,0.00003915005,0.02706934,0.8823186],"study_design_scores_gemma":[0.001429559,0.001189948,0.005573413,0.0001019355,0.000008270687,0.000004367787,0.01614829,0.8690442,0.01361459,0.00004059943,0.09264465,0.000200201],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5478326,0.002340033,0.4476112,0.0005176391,0.0001097665,0.001378229,0.00004923143,0.00005841189,0.0001029196],"genre_scores_gemma":[0.9940202,0.0002805409,0.002940775,0.00001795756,0.00005207822,0.0004079415,0.0004970299,0.00001053295,0.001772912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8821184,"threshold_uncertainty_score":0.3689537,"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."}}