{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005893763,0.0001326921,0.0001577994,0.0001212457,0.0004620696,0.0001177836,0.001031977,0.00005491254,0.00001312205],"category_scores_gemma":[0.0005225941,0.0001031118,0.00009429118,0.0008185813,0.00005778573,0.0005630208,0.0002874008,0.0001922685,5.811016e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009847521,"about_ca_system_score_gemma":0.0002935803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001895693,"about_ca_topic_score_gemma":0.00001510689,"domain_scores_codex":[0.9984652,0.0002096351,0.00032236,0.0005128819,0.0002877922,0.0002021246],"domain_scores_gemma":[0.9981571,0.000318254,0.0001792041,0.001038457,0.0001649724,0.0001420148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000210451,0.002875393,0.0004744379,0.002328692,0.0001284418,0.00001774941,0.04446766,0.0004650312,0.03714182,0.797538,0.026107,0.08824534],"study_design_scores_gemma":[0.002021123,0.0002071305,0.0004321043,0.00009573454,0.00003106381,0.00001661267,0.0002731414,0.8489129,0.0004354249,0.002865037,0.1444968,0.0002129569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003593328,0.002214431,0.9734788,0.007575963,0.0005042857,0.001193191,0.01136444,0.00006995558,0.000005597626],"genre_scores_gemma":[0.08294737,0.000137929,0.8932693,0.00823726,0.0003196147,0.001821616,0.01277533,0.00003178602,0.0004597814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8484479,"threshold_uncertainty_score":0.4204777,"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."}}