{"id":"W2124714582","doi":"10.1093/bioinformatics/btr452","title":"OrganismTagger: detection, normalization and grounding of organism entities in biomedical documents","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of New Brunswick","funders":"","keywords":"Computer science; Organism; Information retrieval; Taxonomy (biology); Natural language processing; Precision and recall; Named-entity recognition; Artificial intelligence; Task (project management); Biology","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":[0.002935746,0.001305431,0.0008677316,0.01254553,0.0008396967,0.00288127,0.001662138,0.001745309,0.004300389],"category_scores_gemma":[0.01083716,0.0007301982,0.0008530173,0.005605407,0.0007813099,0.003720705,0.001918041,0.0008375224,0.006540365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001115092,"about_ca_system_score_gemma":0.002258395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004079635,"about_ca_topic_score_gemma":0.006514501,"domain_scores_codex":[0.9971911,0.0003885985,0.0005045267,0.001062257,0.0007568059,0.00009676625],"domain_scores_gemma":[0.993681,0.002842868,0.001143096,0.0008884022,0.001254171,0.0001904499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004861687,0.0002927883,0.02910841,0.004623541,0.0003606018,0.001456699,0.0014504,0.004162255,0.09488849,0.004779577,0.08869346,0.7696975],"study_design_scores_gemma":[0.0002519022,0.0006438121,0.08641172,0.00219453,0.0007810085,0.007306713,0.001755331,0.1114991,0.3355861,0.0157008,0.4373908,0.0004781778],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1155553,0.007690686,0.5046654,0.001810454,0.0008434966,0.001176171,0.08185356,0.2745901,0.01181471],"genre_scores_gemma":[0.1012169,0.001502083,0.8089986,0.0004985353,0.0001465927,0.0004568379,0.07945493,0.002569956,0.005155517],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01254553,"threshold_uncertainty_score":0.01552594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01456975050186216,"score_gpt":0.2312963566121826,"score_spread":0.2167266061103204,"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."}}