{"url":"/dataset/standardized-project-gutenberg-corpus","name":"Standardized Project Gutenberg Corpus","full_name":null,"description_markdown":"The **Standardized Project Gutenberg Corpus** (SPGC) is an open science approach to a curated version of the complete PG data containing more than 50,000 books and more than 3×109 word-tokens.\n\nSource: [https://arxiv.org/abs/1812.08092](https://arxiv.org/abs/1812.08092)","description_withheld":null,"homepage":"https://github.com/pgcorpus/gutenberg-analysis","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-standardized-project-gutenberg-corpus-for","title":"A standardized Project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics","first_author":"Martin Gerlach","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Anomaly Detection","url":"/task/anomaly-detection","datasets_with_task":"/datasets/task/anomaly-detection"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"}],"languages":[],"variants":["Standardized Project Gutenberg Corpus"],"data_loaders":[{"repo":"https://github.com/pgcorpus/gutenberg-analysis","url":"https://github.com/pgcorpus/gutenberg-analysis","frameworks":[]}],"num_papers_in_archive":9,"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":"2026-09-25T09:33:49+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."}