{"id":"W7112131225","doi":"","title":"DiscHPO: Generative Models and Sentence Transformers for the Recognition and Normalisation of Continuous and Discontinuous Phenotype Mentions","year":2025,"lang":"en","type":"article","venue":"Research Explorer (The University of Manchester)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Disjoint sets; Sentence; Transformer; Named-entity recognition; Pipeline (software); Phrase; Probabilistic logic; Knowledge base","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002193697,0.001603446,0.0005739179,0.00118934,0.0004020996,0.001422429,0.00216923,0.001662369,0.01247408],"category_scores_gemma":[0.007220557,0.0008494306,0.001884507,0.0005332024,0.0007969125,0.002819337,0.002233063,0.002865768,0.006518165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001122272,"about_ca_system_score_gemma":0.0009899597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005531646,"about_ca_topic_score_gemma":0.009405803,"domain_scores_codex":[0.9991339,0.000280331,0.00006185572,0.00034006,0.0001310755,0.0000528798],"domain_scores_gemma":[0.9972075,0.002013371,0.0001288974,0.0003130405,0.0002563695,0.00008081138],"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":[0.001231865,0.000310345,0.004933489,0.0009183077,0.000380309,0.001316872,0.001156868,0.1445532,0.0349312,0.02695184,0.05040417,0.7329115],"study_design_scores_gemma":[0.00003856343,0.0000908166,0.0007012231,0.00004404065,0.00004692665,0.0002782006,0.00008235389,0.9604807,0.01000571,0.01999589,0.008198567,0.00003707321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01289685,0.0005149113,0.9456928,0.00068544,0.0002344414,0.0002490881,0.0034127,0.03423697,0.002076793],"genre_scores_gemma":[0.3401145,0.0006187181,0.6277556,0.001035023,0.0001934202,0.0005211719,0.01717019,0.002651572,0.009939732],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01247408,"threshold_uncertainty_score":0.04172999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09671815083821429,"score_gpt":0.309607006926984,"score_spread":0.2128888560887697,"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."}}