{"url":"/dataset/newspaper-navigator","name":"Newspaper Navigator","full_name":null,"description_markdown":"The largest dataset of extracted visual content from historic newspapers ever produced. The Newspaper Navigator dataset, finetuned visual content recognition model.\r\n\r\nSource: [The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America](/paper/the-newspaper-navigator-dataset-extracting)","description_withheld":null,"homepage":"https://github.com/LibraryOfCongress/newspaper-navigator","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-newspaper-navigator-dataset-extracting","title":"The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America","first_author":"Benjamin Charles Germain Lee","url":null},"license":null,"modalities":[],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"}],"languages":[],"variants":["Newspaper Navigator"],"data_loaders":[{"repo":"https://github.com/LibraryOfCongress/newspaper-navigator","url":"https://github.com/LibraryOfCongress/newspaper-navigator","frameworks":["pytorch"]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}