{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001863207,0.0001525884,0.0002381956,0.00004361057,0.00007893661,0.00003270609,0.0001089612,0.0002248,0.000003418806],"category_scores_gemma":[0.00009142914,0.0001453148,0.00002338983,0.00001995197,0.0001551984,0.00001083936,0.001142418,0.000124691,1.20502e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009124186,"about_ca_system_score_gemma":0.00008616962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004065079,"about_ca_topic_score_gemma":0.0006693873,"domain_scores_codex":[0.9990095,0.0000728953,0.0002140048,0.000514926,0.00006530296,0.0001233174],"domain_scores_gemma":[0.9993313,0.00003116425,0.000137286,0.0003992991,0.00004676574,0.00005419007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004049982,0.0002882854,0.004522383,0.002323968,0.00203692,0.00001253386,0.004794866,0.00004574391,0.8560136,0.00144913,0.005526765,0.1225808],"study_design_scores_gemma":[0.006497337,0.0006743378,0.1169447,0.002016754,0.005422632,0.00005145516,0.01195324,0.01070749,0.3425678,0.002906745,0.4970098,0.003247673],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6937303,0.2681674,0.02137502,0.0005721851,0.0004039556,0.000240132,0.01545174,0.00001765114,0.00004161083],"genre_scores_gemma":[0.6332026,0.3275019,0.01824368,0.0001214307,0.0004801583,0.0001020435,0.0198863,0.00002425118,0.0004376544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5134457,"threshold_uncertainty_score":0.5925767,"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."}}