{"id":"W4323519786","doi":"10.1093/database/baad005","title":"Chemical identification and indexing in full-text articles: an overview of the NLM-Chem track at BioCreative VII","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"H2020 Marie Skłodowska-Curie Actions; U.S. National Library of Medicine; Fundação para a Ciência e a Tecnologia; Natural Sciences and Engineering Research Council of Canada; European Commission; University of Oxford; Albaha University; National Institutes of Health; Nvidia","keywords":"Computer science; Search engine indexing; Named-entity recognition; Identification (biology); Information retrieval; Natural language processing; Task (project management); Normalization (sociology); Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04178872,0.003495964,0.003411316,0.02970882,0.003755909,0.01381698,0.005919686,0.003830043,0.03323917],"category_scores_gemma":[0.04993556,0.00226855,0.004281163,0.01986606,0.001176133,0.01503271,0.008765157,0.003388592,0.07025816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003936198,"about_ca_system_score_gemma":0.008512912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006001055,"about_ca_topic_score_gemma":0.009404777,"domain_scores_codex":[0.9711753,0.005458975,0.004570467,0.00537931,0.01197593,0.001440043],"domain_scores_gemma":[0.9249449,0.01971072,0.005340219,0.01218863,0.03075593,0.007059549],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008331373,0.0008148982,0.006158555,0.005201385,0.0005433775,0.0004501589,0.0008034177,0.002531295,0.01917255,0.001974897,0.5349363,0.4265801],"study_design_scores_gemma":[0.0004005018,0.001247764,0.01471431,0.001276153,0.0002693948,0.001516711,0.0005556589,0.02684375,0.038202,0.003655214,0.910898,0.0004205759],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03904616,0.04206648,0.2854689,0.01134251,0.009719356,0.009462548,0.2681726,0.2730609,0.0616606],"genre_scores_gemma":[0.02592668,0.008824418,0.341594,0.002278804,0.001924465,0.003363805,0.5512696,0.01766029,0.04715796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9582113,"threshold_uncertainty_score":0.2210025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06945455733307294,"score_gpt":0.3394277437636137,"score_spread":0.2699731864305407,"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."}}