{"url":"/dataset/tracking-the-trackers","name":"Tracking the Trackers","full_name":null,"description_markdown":"**Tracking the Trackers** is a large-scale analysis of third-party trackers on the World Wide Web. We extract third-party embeddings from more than 3.5 billion web pages of the CommonCrawl 2012 corpus, and aggregate those to a dataset containing more than 140 million third-party embeddings in over 41 million domains.","description_withheld":null,"homepage":"https://ssc.io/trackingthetrackers/","introduced_date":"2016-07-29","introduced_date_note":null,"introduced_by":{"paper":null,"title":"On the Ubiquity of Web Tracking: Insights from a Billion-Page Web Crawl","first_author":null,"url":null},"license":{"name":"Custom","url":"https://commoncrawl.org/terms-of-use/"},"modalities":[],"tasks":[],"languages":[],"variants":["Tracking the Trackers"],"data_loaders":[],"num_papers_in_archive":2,"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."}