{"id":"W4406774024","doi":"10.2196/63906","title":"Toward a Domain-Overarching Metadata Schema for Making Health Research Studies FAIR (Findable, Accessible, Interoperable, and Reusable): Development of the NFDI4Health Metadata Schema","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Research Data Management Practices","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Metadata; Preprint; Computer science; Schema (genetic algorithms); Information retrieval; World Wide Web; Data science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.02321541,0.0002838489,0.0007062458,0.0007024798,0.001148841,0.002652819,0.006792886,0.0001178046,0.000006509534],"category_scores_gemma":[0.007635738,0.0001830817,0.000072872,0.002146955,0.0005365433,0.02600018,0.01519236,0.001202846,0.000003254652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003217512,"about_ca_system_score_gemma":0.003341406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005417845,"about_ca_topic_score_gemma":0.0001400899,"domain_scores_codex":[0.9928378,0.0007431591,0.001866634,0.0005157547,0.00293173,0.001104965],"domain_scores_gemma":[0.9938028,0.002519269,0.0006850114,0.002119054,0.0005511921,0.0003227166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000134042,0.0003342228,0.0004466388,0.01769527,0.001154483,0.000008566523,0.02304301,0.000009861017,0.00002359956,0.7030729,0.04324922,0.2108282],"study_design_scores_gemma":[0.003465095,0.00041829,0.001197794,0.008638017,0.00004876614,0.00003087301,0.03308252,0.03505788,0.001544278,0.01426791,0.9015871,0.0006614584],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01112285,0.00194956,0.9513688,0.0301316,0.00034327,0.002654395,0.00003682292,0.0000855235,0.002307191],"genre_scores_gemma":[0.0424141,0.003793023,0.9453795,0.005375051,0.0000565995,0.0007047473,0.00004576655,0.00002516144,0.002206058],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8583379,"threshold_uncertainty_score":0.9985808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.383225358820893,"score_gpt":0.5313485974582216,"score_spread":0.1481232386373286,"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."}}