{"url":"/dataset/agb-de","name":"AGB-DE","full_name":null,"description_markdown":"AGB-DE is a legal NLP corpus for the automated detection of potentially void clauses in German standard form consumer contracts. It consists of 3,764 clauses that have been legally assessed by experts and annotated as potentially void (1) or valid (0). Additionally, each clause is annotated with a topic label.","description_withheld":null,"homepage":"https://github.com/DaBr01/AGB-DE","introduced_date":"2024-06-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/agb-de-a-corpus-for-the-automated-legal","title":"AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts","first_author":"Daniel Braun","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Detection of potentially void clauses","url":"/task/detection-of-potentially-void-clauses","datasets_with_task":"/datasets/task/detection-of-potentially-void-clauses"}],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["AGB-DE"],"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/detection-of-potentially-void-clauses-on-agb","task":"Detection of potentially void clauses","dataset_variant":"AGB-DE","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"AGBert","paper":"/paper/agb-de-a-corpus-for-the-automated-legal","metrics":{"F1":"0.54"},"code_links":[{"title":"DaBr01/AGB-DE","url":"https://github.com/DaBr01/AGB-DE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/agb-de-a-corpus-for-the-automated-legal","title":"AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts","date":"2024-06-10","rows_on_this_dataset":1,"code_links":1,"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."}