{"url":"/dataset/wdc-pave","name":"WDC-PAVE","full_name":"Web Data Commones - Product Attribute Value Extraction","description_markdown":"The datasets contains 1,420 human annotated product offers, systematically selected from the Web Data Commons Product Matching Corpus, featuring 24,582 annotated attribute-value pairs, making it a valuable resource for both product attribute-value extraction and product matching tasks. \r\nThe normalized gold standard contains the standardized attribute value pairs as described below.","description_withheld":null,"homepage":"http://webdatacommons.org/structureddata/wdc-pave/","introduced_date":"2024-03-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/using-llms-for-the-extraction-and","title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","first_author":"Alexander Brinkmann","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Attribute Value Extraction","url":"/task/attribute-value-extraction","datasets_with_task":"/datasets/task/attribute-value-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WDC-PAVE"],"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/attribute-value-extraction-on-wdc-pave","task":"Attribute Value Extraction","dataset_variant":"WDC-PAVE","rows":5,"metrics":["F1-Score"],"first_row_in_archive_order":{"model":"GPT-4_10_example_values_&_10_demonstrations","paper":"/paper/using-llms-for-the-extraction-and","metrics":{"F1-Score":"90.54"},"code_links":[{"title":"wbsg-uni-mannheim/wdc-pave","url":"https://github.com/wbsg-uni-mannheim/wdc-pave"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/using-llms-for-the-extraction-and","title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","date":"2024-03-04","rows_on_this_dataset":5,"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."}