{"url":"/dataset/etd500","name":"ETD500","full_name":null,"description_markdown":"The paper used 500 scanned Electronic Theses and Dissertation cover pages (i.e., front pages). The dataset contains several intermediate datasets, briefly discussed in the paper.","description_withheld":null,"homepage":"","introduced_date":"2021-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/automatic-metadata-extraction-incorporating","title":"Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations","first_author":"Muntabir Hasan Choudhury","url":null},"license":null,"modalities":[],"tasks":[{"name":"Key Information Extraction","url":"/task/key-information-extraction","datasets_with_task":"/datasets/task/key-information-extraction"}],"languages":[],"variants":["ETD500"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/key-information-extraction-on-etd500","task":"Key Information Extraction","dataset_variant":"ETD500","rows":1,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"CRF-visual","paper":"/paper/automatic-metadata-extraction-incorporating","metrics":{"F1 (%)":"81.3% to 96% (depending on the metadata fields)"},"code_links":[{"title":"lamps-lab/ETDMiner","url":"https://github.com/lamps-lab/ETDMiner"},{"title":"lamps-lab/AutoMeta","url":"https://github.com/lamps-lab/AutoMeta"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/automatic-metadata-extraction-incorporating","title":"Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations","date":"2021-07-01","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}