{"doi":"10.1109/escience65000.2025.00090","title":"Improving FAIR Compliance for High-Dimensional Data via Automated Metadata Extraction","abstract":"High-dimensional datasets are becoming an increasingly vital asset in the machine learning and AI domains due to their ability to capture large volumes of structured, self-descriptive information. Research data repositories play a key role in supporting the documentation, discoverability, and reuse of such data. This paper highlights the growing presence of high-dimensional formats—particularly NetCDF and HDF5—underscoring the need for better infrastructure to support them. We use a large language model to assess the quality of metadata associated with these files and find that user-provided metadata often falls short when compared to the richness of embedded metadata within the files themselves. In response, we implement an automated metadata extraction process during file ingestion, offering a practical pathway to FAIR-ify high-dimensional data. Our empirical analysis and technical solution are demonstrated through integration with the Dataverse data repository platform.","journal":null,"year":2025,"id":577086,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9245,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":86490,"name":"Jan Range","orcid":"0000-0001-6478-1051","position":1,"is_corresponding":false},{"id":1486309,"name":"Philip Durbin","orcid":"0000-0002-9528-9470","position":2,"is_corresponding":false},{"id":1486310,"name":"Amber Leahey","orcid":"0000-0001-6476-223X","position":3,"is_corresponding":false},{"id":1486311,"name":"Wei Li","orcid":"0000-0001-7547-2908","position":4,"is_corresponding":false},{"id":106070,"name":"Danielle Braun","orcid":"0000-0002-5177-8598","position":5,"is_corresponding":false},{"id":49307,"name":"Ana Trisovic","orcid":"0000-0003-1991-0533","position":0,"is_corresponding":true}],"reference_count":16,"raw_metadata":null,"created_at":"2026-07-19T02:58:04.622308Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}