{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001609125,0.00007850654,0.0001034931,0.00008681727,0.00003449911,0.000009690911,0.00008560836,0.0001431619,0.00002638835],"category_scores_gemma":[0.0001094456,0.00006837503,0.00001708167,0.0001183877,0.0001748463,0.00000971218,0.00008455734,0.00004454298,0.00000381918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008536392,"about_ca_system_score_gemma":0.00002702143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003788023,"about_ca_topic_score_gemma":0.00002304403,"domain_scores_codex":[0.999385,0.00001527671,0.0002873504,0.00007756645,0.0001042727,0.000130541],"domain_scores_gemma":[0.9997153,0.000005639922,0.00009461016,0.0001056818,0.00003257681,0.00004622298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003069374,0.0007171365,0.1593166,0.001509361,0.0003059625,0.00001605468,0.03276987,0.000001859114,0.4589592,0.002839166,0.002062242,0.3411956],"study_design_scores_gemma":[0.003689584,0.002256239,0.1154715,0.0002281338,0.00007855274,0.0001663423,0.01397163,0.001527106,0.8269023,0.001799383,0.03300794,0.0009013292],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.966049,0.0001582285,0.03247619,0.000013069,0.0001853925,0.00008216745,0.000006020935,0.00001671095,0.001013276],"genre_scores_gemma":[0.9890587,0.0002088506,0.01055366,0.00004807671,0.0000259128,0.000003041229,0.00002652505,0.000006269115,0.00006892676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3679431,"threshold_uncertainty_score":0.2788253,"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."}}