{"url":"/dataset/histgen-wsi-report-dataset","name":"HistGen WSI-Report Dataset","full_name":null,"description_markdown":"This dataset is composed of 7,753 pairs of whole slide images and their corresponding diagnostic reports, extracted from the TCGA platform and refined with large language models. This dataset aims to boost the field of automated histopathology report generation by providing a new publicly available evaluation benchmark. See HistGen paper (see https://arxiv.org/pdf/2403.05396.pdf for reference) for a more detailed description of this dataset.","description_withheld":null,"homepage":"https://github.com/dddavid4real/HistGen","introduced_date":"2024-03-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/histgen-histopathology-report-generation-via","title":"HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction","first_author":"Zhengrui Guo","url":null},"license":{"name":"Apache License, Version 2.0","url":"https://opensource.org/license/apache-2-0"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Medical Report Generation","url":"/task/medical-report-generation","datasets_with_task":"/datasets/task/medical-report-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HistGen WSI-Report Dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/medical-report-generation-on-histgen-wsi","task":"Medical Report Generation","dataset_variant":"HistGen WSI-Report Dataset","rows":1,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"HistGen","paper":"/paper/histgen-histopathology-report-generation-via","metrics":{"BLEU-4":"0.184"},"code_links":[{"title":"dddavid4real/HistGen","url":"https://github.com/dddavid4real/HistGen"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/histgen-histopathology-report-generation-via","title":"HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction","date":"2024-03-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":6,"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."}