{"url":"/dataset/eth-py150-open","name":"ETH Py150 Open","full_name":null,"description_markdown":"A massive, deduplicated corpus of 7.4M Python files from GitHub.\r\n\r\nSource: [Learning and Evaluating Contextual Embedding of Source Code](/paper/pre-trained-contextual-embedding-of-source-1)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/eth_py150_open","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/pre-trained-contextual-embedding-of-source-1","title":"Learning and Evaluating Contextual Embedding of Source Code","first_author":"Aditya Kanade","url":null},"license":null,"modalities":[],"tasks":[{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Program Repair","url":"/task/program-repair","datasets_with_task":"/datasets/task/program-repair"},{"name":"Contextual Embedding for Source Code","url":"/task/contextual-embedding-for-source-code","datasets_with_task":"/datasets/task/contextual-embedding-for-source-code"}],"languages":[],"variants":["ETH Py150 Open"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/eth_py150_open","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eth_py150_open","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research-datasets/eth_py150_open","url":"https://github.com/google-research-datasets/eth_py150_open","frameworks":[]}],"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."}