{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002554114,0.00007008798,0.00008981664,0.00002844865,0.00003656626,0.000007656301,0.0001368967,0.00008027554,0.00001205705],"category_scores_gemma":[0.0002395786,0.00005120518,0.00002562948,0.0002067674,0.0001988392,0.000005062895,0.0002281523,0.00005995901,0.000007207609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008362565,"about_ca_system_score_gemma":0.00001877503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003076149,"about_ca_topic_score_gemma":0.0000855906,"domain_scores_codex":[0.9993312,0.00005653215,0.0001646634,0.0002289396,0.00009246448,0.0001262294],"domain_scores_gemma":[0.9995424,0.00002707849,0.0000579425,0.0003102036,0.00001890991,0.00004347498],"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":[0.00004022244,0.00003954118,0.003869157,0.00003903819,0.000008182266,0.000001745621,0.0002089529,9.648403e-7,0.9849169,0.00004956272,0.0008658094,0.009959907],"study_design_scores_gemma":[0.0003879784,0.00004455737,0.03432652,0.00006229308,0.0000113822,0.000008244596,0.0005814569,0.0003405612,0.9607348,0.00006597093,0.003338001,0.00009826126],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985347,0.0008894466,0.00004986376,0.0002345359,0.0000346412,0.00007374916,0.0001468579,0.00001158443,0.0000245948],"genre_scores_gemma":[0.9987619,0.000396931,0.0001897862,0.00006769646,0.00002922211,0.0000109892,0.0004419832,0.000006235649,0.00009527653],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03045736,"threshold_uncertainty_score":0.2088087,"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."}}