{"url":"/dataset/commitbart","name":"CommitBART","full_name":null,"description_markdown":"**CommitBART** is a benchmark for researching commit-related task such as denoising, cross-modal generation and contrastive learning. The dataset contains over 7 million commits across 7 programming languages.\r\n\r\nSource: [CommitBART: A Large Pre-trained Model for GitHub Commits](https://paperswithcode.com/paper/commitbart-a-large-pre-trained-model-for)\r\n\r\nImage Source: [https://arxiv.org/pdf/2208.08100v1.pdf](https://arxiv.org/pdf/2208.08100v1.pdf)","description_withheld":null,"homepage":"https://anonymous.4open.science/r/CommitBart-443E/README.md","introduced_date":"2022-08-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/commitbart-a-large-pre-trained-model-for","title":"CommitBART: A Large Pre-trained Model for GitHub Commits","first_author":"Shangqing Liu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Denoising","url":"/task/denoising","datasets_with_task":"/datasets/task/denoising"},{"name":"Contrastive Learning","url":"/task/contrastive-learning","datasets_with_task":"/datasets/task/contrastive-learning"}],"languages":[],"variants":["CommitBART"],"data_loaders":[],"num_papers_in_archive":3,"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."}