{"url":"/dataset/ca4p-483","name":"CA4P-483","full_name":null,"description_markdown":"**CA4P-483** is a dataset designed to facilitate the sequence labeling tasks and regulation compliance identification between privacy policies and software. It contains 483 Chinese Android application privacy policies, over 11K sentences, and 52K fine-grained annotations.\r\n\r\nSource: [A Fine-grained Chinese Software Privacy Policy Dataset for Sequence Labeling and Regulation Compliant Identification](https://arxiv.org/pdf/2212.04357v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2212.04357v1.pdf](https://arxiv.org/pdf/2212.04357v1.pdf)","description_withheld":null,"homepage":"https://github.com/zacharykzhao/CA4P-483","introduced_date":"2022-12-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-fine-grained-chinese-software-privacy","title":"A Fine-grained Chinese Software Privacy Policy Dataset for Sequence Labeling and Regulation Compliant Identification","first_author":"Kaifa Zhao","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CA4P-483"],"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":"2026-09-25T09:33:49+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."}