{"id":"W4410761124","doi":"","title":"Structured Knowledge Base Enhances Effective Use of Large Language Models for Metadata Curation.","year":2024,"lang":"en","type":"article","venue":"PubMed","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Infection and Immunity","funders":"","keywords":"Metadata; Computer science; Knowledge base; Base (topology); Information retrieval; Digital curation; Natural language processing; World Wide Web; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008541613,0.0008696686,0.001045153,0.007663111,0.00146111,0.005522515,0.00212567,0.001537927,0.010562],"category_scores_gemma":[0.05237293,0.0008604357,0.00139314,0.00572016,0.0007162293,0.01278192,0.005667065,0.001794319,0.008443096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001171175,"about_ca_system_score_gemma":0.006102867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00707331,"about_ca_topic_score_gemma":0.01688777,"domain_scores_codex":[0.9939843,0.002614816,0.0006848464,0.0007177047,0.001817325,0.0001810616],"domain_scores_gemma":[0.964112,0.02117281,0.001071269,0.006999956,0.00606257,0.0005813315],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001026352,0.001604382,0.006888136,0.002813194,0.000461619,0.001163786,0.002719066,0.01293207,0.03097332,0.07323413,0.1016499,0.7645341],"study_design_scores_gemma":[0.0004484703,0.000581724,0.004444099,0.001865573,0.001012859,0.001252806,0.002646115,0.3423583,0.07827711,0.2367405,0.3299945,0.000377897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02920108,0.001289174,0.8868691,0.003336089,0.0005667866,0.001331126,0.01419547,0.03500352,0.02820762],"genre_scores_gemma":[0.1363826,0.001419726,0.8245092,0.0009091579,0.0001717199,0.0005661612,0.02759276,0.002085425,0.006363273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9914584,"threshold_uncertainty_score":0.04517293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04173598398695012,"score_gpt":0.2876790439563235,"score_spread":0.2459430599693734,"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."}}