{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002127891,0.000109885,0.0001079569,0.00002570283,0.0001217517,0.00001194705,0.0001719042,0.00008412961,0.00002030967],"category_scores_gemma":[0.0001068781,0.00006053912,0.00005044866,0.00006846113,0.0003853525,0.000009949292,0.0002037945,0.00008833489,0.000001660425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005708,"about_ca_system_score_gemma":0.00002785879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008696426,"about_ca_topic_score_gemma":0.0001158366,"domain_scores_codex":[0.9993517,0.00004409695,0.000266897,0.0001035405,0.0001038003,0.0001299787],"domain_scores_gemma":[0.9993823,0.00006255759,0.000220899,0.000261108,0.00004151132,0.00003167585],"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":[0.001159206,0.00106145,0.06746949,0.001525827,0.0008968841,0.000002309684,0.04348492,0.0000269992,0.05879597,0.005725169,0.09136035,0.7284914],"study_design_scores_gemma":[0.004551442,0.003541067,0.09111501,0.001624683,0.0004695311,0.0002768326,0.1100491,0.04183451,0.4450838,0.000291786,0.2994188,0.001743413],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9364148,0.002499935,0.04886492,0.0003722928,0.0009339366,0.0004982164,0.0002358522,0.00003557886,0.0101445],"genre_scores_gemma":[0.9703475,0.0006438484,0.0284479,0.0001612992,0.00009442329,0.00001492191,0.000151089,0.000008811549,0.0001302172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.726748,"threshold_uncertainty_score":0.2468714,"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."}}