{"id":"W4224325974","doi":"10.1093/database/baac069","title":"Multi-label classification for biomedical literature: an overview of the BioCreative VII LitCovid Track for COVID-19 literature topic annotations","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"U.S. National Library of Medicine; Medical Research Council; National Institutes of Health","keywords":"Computer science; Coronavirus disease 2019 (COVID-19); Annotation; Named-entity recognition; Scientific literature; Information retrieval; Data science; Artificial intelligence; Natural language processing; World Wide Web; Task (project management); Medicine; Infectious disease (medical specialty)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0198239,0.002875823,0.003112155,0.04253365,0.004193842,0.01148644,0.005162113,0.00361624,0.02204815],"category_scores_gemma":[0.04768389,0.00160008,0.004641766,0.03224641,0.001190466,0.008785834,0.009696248,0.003386465,0.03994055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004758654,"about_ca_system_score_gemma":0.01145212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01292998,"about_ca_topic_score_gemma":0.0314092,"domain_scores_codex":[0.9812501,0.003814021,0.003263559,0.004289219,0.00638824,0.0009948596],"domain_scores_gemma":[0.955544,0.01540177,0.004680471,0.007638965,0.0125597,0.004175187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005412457,0.00032313,0.005838515,0.01014503,0.0004279924,0.0003907618,0.0007372942,0.000972156,0.01053301,0.00325734,0.7306157,0.2362178],"study_design_scores_gemma":[0.0001429975,0.000171971,0.007483691,0.002160841,0.0001606538,0.0004991769,0.0002566875,0.004575587,0.004261619,0.003211177,0.9769165,0.0001591549],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.012055,0.07380354,0.1060613,0.01162583,0.004568662,0.003988834,0.6112822,0.1420867,0.03452796],"genre_scores_gemma":[0.005542506,0.009867406,0.1512381,0.003005392,0.000797905,0.002230965,0.8128781,0.006275997,0.008163751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9574664,"threshold_uncertainty_score":0.10484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2046024088696558,"score_gpt":0.4089928303778776,"score_spread":0.2043904215082218,"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."}}