{"id":"W2148362397","doi":"10.1186/1471-2105-12-s8-s8","title":"Benchmarking of the 2010 BioCreative Challenge III text-mining competition by the BioGRID and MINT interaction databases","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Associazione Italiana per la Ricerca sul Cancro; Canadian Institutes of Health Research; European Commission","keywords":"Computer science; Annotation; Benchmarking; Identification (biology); Test set; Information retrieval; Normalization (sociology); Data curation; Named-entity recognition; Natural language processing; Set (abstract data type); Information extraction; Artificial intelligence; Database; Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03068834,0.005638873,0.004060193,0.011866,0.003764387,0.008400519,0.009078763,0.005750671,0.008413741],"category_scores_gemma":[0.04079245,0.0009449435,0.003767196,0.0132387,0.002589618,0.007244414,0.009059873,0.003399385,0.01274263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006694376,"about_ca_system_score_gemma":0.007366178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03898377,"about_ca_topic_score_gemma":0.04764815,"domain_scores_codex":[0.9712259,0.009572006,0.003154465,0.005296099,0.009194469,0.001556984],"domain_scores_gemma":[0.9607223,0.01410884,0.002281567,0.005103904,0.01221168,0.005571715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.006049634,0.006383222,0.01505969,0.008066518,0.002002165,0.001337589,0.00101245,0.02543046,0.009636577,0.004902478,0.801294,0.1188252],"study_design_scores_gemma":[0.006600252,0.004621934,0.08686746,0.001357139,0.001384302,0.003570529,0.003827465,0.2874751,0.03279287,0.01003278,0.5607495,0.0007206378],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3830306,0.02400383,0.02046777,0.01849199,0.004480437,0.004463146,0.4588635,0.03780372,0.04839507],"genre_scores_gemma":[0.06302171,0.001493931,0.02366696,0.001632796,0.0003682812,0.001147329,0.9016179,0.001429309,0.005621794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03898377,"threshold_uncertainty_score":0.1622974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05083072981329605,"score_gpt":0.2669098268853785,"score_spread":0.2160790970720824,"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."}}