{"url":"/dataset/product-page","name":"Product Page","full_name":null,"description_markdown":"**Product Page** is a large-scale and realistic dataset of webpages. The dataset contains 51,701 manually labeled product pages from 8,175 real e-commerce websites. The pages can be rendered entirely in a web browser and are suitable for computer vision applications. This makes it substantially richer and more diverse than other datasets proposed for element representation learning, classification and prediction on the web.","description_withheld":null,"homepage":"https://github.com/klarna/product-page-dataset","introduced_date":"2021-11-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-klarna-product-page-dataset-a","title":"The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models","first_author":"Alexandra Hotti","url":null},"license":{"name":"Creative Commons BY-NC-SA","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["Product Page"],"data_loaders":[],"num_papers_in_archive":1,"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."}