{"id":"W4388089782","doi":"10.1109/isc257844.2023.10293563","title":"A New Semantic Similarity Scheme for More Accurate Identification in Medical Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Jaccard index; Computer science; Similarity (geometry); Semantic similarity; Context (archaeology); Identification (biology); Information retrieval; Cosine similarity; Data mining; Set (abstract data type); Data set; Dice; Key (lock); Similarity measure; Scheme (mathematics); Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005974228,0.00007985691,0.0001053237,0.00004499873,0.00003396946,0.00001916701,0.0005082008,0.0002283522,0.00004255364],"category_scores_gemma":[0.001542201,0.00006696509,0.00002962267,0.0001893794,0.00006797914,0.000003439049,0.0003362952,0.00007521883,0.00002649506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004329946,"about_ca_system_score_gemma":0.0001557786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005970404,"about_ca_topic_score_gemma":0.000283466,"domain_scores_codex":[0.9990178,0.00002158903,0.0002084583,0.0003760576,0.0001653496,0.0002107451],"domain_scores_gemma":[0.9992849,0.00004453659,0.00003541417,0.0005119947,0.00002509465,0.00009803265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001191183,0.00009694653,0.006974497,0.0001233661,0.00007533626,0.00002387219,0.0001008583,0.000007426714,0.09091396,0.0003029711,0.6938528,0.2074088],"study_design_scores_gemma":[0.004533648,0.0003307708,0.09614643,0.0001313378,0.00004870888,0.00003529415,0.0009849936,0.1289937,0.05406265,0.002490236,0.7113485,0.000893736],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7499292,0.00091759,0.2084181,0.03832333,0.0007583088,0.0006907746,0.0001742186,0.0002858942,0.0005026009],"genre_scores_gemma":[0.9685115,0.0005697725,0.01681033,0.001413005,0.0005713191,0.00005721578,0.004617146,0.00003080239,0.007418907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2185823,"threshold_uncertainty_score":0.2730757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08753904631601674,"score_gpt":0.3982877170484738,"score_spread":0.3107486707324571,"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."}}