{"id":"W4416865968","doi":"10.1093/database/baag027","title":"Large-scale Manual Curation and Harmonization of Metadata from Metagenomic and Cancer Genomic Repositories: Challenges and Solutions","year":2025,"lang":"en","type":"preprint","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Population and Public Health","funders":"National Cancer Institute; National Institutes of Health","keywords":"Metadata; Data curation; Harmonization; Geospatial metadata; Ontology; Standardization; Metadata repository; Digital curation","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":[0.1868279,0.001746375,0.002622961,0.01764117,0.007815648,0.01387444,0.007950565,0.002304157,0.002345282],"category_scores_gemma":[0.2648692,0.002207272,0.002973162,0.02242257,0.005045575,0.01223957,0.02141182,0.004389629,0.001672331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004564419,"about_ca_system_score_gemma":0.0315631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01206358,"about_ca_topic_score_gemma":0.02450621,"domain_scores_codex":[0.8538506,0.07167219,0.02960415,0.01541306,0.0269039,0.002556139],"domain_scores_gemma":[0.5340558,0.1737895,0.04840328,0.1767565,0.0625301,0.004464844],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004481784,0.0006560298,0.1044623,0.009345648,0.002079892,0.001561588,0.03125447,0.005748662,0.03167559,0.03616237,0.08165633,0.694949],"study_design_scores_gemma":[0.0002910809,0.0004137144,0.09541553,0.01029784,0.002302598,0.003201721,0.02748603,0.02290877,0.06552801,0.1568955,0.6141769,0.001082387],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1302845,0.01211422,0.7609984,0.04613193,0.001359914,0.004834405,0.0192738,0.01267251,0.01233038],"genre_scores_gemma":[0.09406397,0.002365181,0.8677826,0.006300515,0.000356826,0.002826503,0.02059427,0.003656266,0.00205385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8131721,"threshold_uncertainty_score":0.9880522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04141825308473716,"score_gpt":0.3070385805524538,"score_spread":0.2656203274677166,"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."}}