{"id":"W2573117738","doi":"10.1093/database/baw147","title":"The BioC-BioGRID corpus: full text articles annotated for curation of protein–protein and genetic interactions","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Biotechnology and Biological Sciences Research Council; National Institutes of Health","keywords":"Data curation; Annotation; Crowdsourcing; Computer science; Task (project management); Information retrieval; Gene Annotation; Pipeline (software); World Wide Web; Data science; Natural language processing; Computational biology; Artificial intelligence; Biology; Gene; Genome; Genetics; Engineering","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":[0.0001139364,0.00007467884,0.0000680319,0.00002094924,0.00009412682,0.00001387902,0.00009384326,0.00004471678,0.000005949176],"category_scores_gemma":[0.0004474924,0.00004102988,0.0000289561,0.00004939031,0.0002462814,0.000006072506,0.00006763715,0.00002765428,0.000003525751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003578088,"about_ca_system_score_gemma":0.00002513097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001683093,"about_ca_topic_score_gemma":0.00009774917,"domain_scores_codex":[0.9994283,0.0000382377,0.0001615728,0.0001819991,0.00005650126,0.0001333815],"domain_scores_gemma":[0.9995033,0.00005305138,0.0000813247,0.0002496795,0.00006849495,0.00004410961],"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":[0.0001551587,0.00002554457,0.0001181388,0.00001472069,0.00001778966,5.767039e-7,0.000009160304,7.52332e-8,0.8859626,0.00008546959,0.001364648,0.1122461],"study_design_scores_gemma":[0.0005712846,0.0004102761,0.0006724526,0.00006853007,0.00001290946,0.00001054982,0.00007688805,0.00009093356,0.8648543,0.0001731602,0.1329641,0.00009456659],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9710662,0.001057423,0.02551145,0.001393689,0.00006059918,0.0003446392,0.0005442362,0.00001250979,0.000009284087],"genre_scores_gemma":[0.9932922,0.0001504727,0.005890212,0.0000332696,0.00009373903,0.0001245593,0.0001525769,0.00000824701,0.000254751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1315995,"threshold_uncertainty_score":0.167315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0194035114125649,"score_gpt":0.2759297630851905,"score_spread":0.2565262516726256,"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."}}