{"id":"W2117770626","doi":"10.1186/2041-1480-2-s5-s11","title":"Assessment of NER solutions against the first and second CALBC Silver Standard Corpus","year":2011,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of New Brunswick","funders":"Concordia University; National Institute of Informatics; Universitat Jaume I; Magyar Tudományos Akadémia; Universidad Complutense de Madrid; Instituto de Salud Carlos III; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Universiteit Antwerpen; Institute of Information Science, Academia Sinica; Academia Sinica; Fondazione Bruno Kessler; Universitat Pompeu Fabra","keywords":"Annotation; Computer science; Natural language processing; Set (abstract data type); Information retrieval; Artificial intelligence; Named-entity recognition; Identification (biology); Task (project management)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006191987,0.000105419,0.0002382165,0.0000523518,0.00009844219,0.00001106395,0.0002337527,0.0001902138,0.00005325098],"category_scores_gemma":[0.0001921829,0.00006079378,0.0001092976,0.00009487399,0.0008498676,0.000003531841,0.0001441858,0.0002193152,5.337179e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001268841,"about_ca_system_score_gemma":0.0001506264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005464,"about_ca_topic_score_gemma":0.00002514931,"domain_scores_codex":[0.9988856,0.00004922587,0.0004333191,0.0001133181,0.0003169904,0.0002015369],"domain_scores_gemma":[0.999184,0.00005439972,0.0002966724,0.0001701409,0.0001466796,0.0001481373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001029585,0.002703239,0.1079436,0.0008179595,0.002979144,0.0004710331,0.002883841,0.00001231289,0.4313828,0.003077819,0.2191702,0.2275285],"study_design_scores_gemma":[0.002609423,0.004008765,0.1446359,0.0002217923,0.0002298223,0.0004118646,0.0009759972,0.0003537335,0.01674227,0.0006983292,0.828773,0.0003391409],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9821047,0.002093099,0.01205933,0.002259462,0.000576944,0.00007955755,0.00004405346,0.000005208136,0.0007777045],"genre_scores_gemma":[0.9937198,0.0008095661,0.004794676,0.0003743153,0.0002066759,9.566767e-7,0.000005475649,0.000008248478,0.00008026402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6096028,"threshold_uncertainty_score":0.3131373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0245083958644906,"score_gpt":0.2709703653760666,"score_spread":0.246461969511576,"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."}}