{"url":"/dataset/verified-smart-contract-code-comments","name":"Verified Smart Contract Code Comments","full_name":null,"description_markdown":"**Verified Smart Contracts Code Comments** is a dataset of real Ethereum smart contract functions, containing \"code, comment\" pairs of both Solidity and Vyper source code. The dataset is based on every deployed Ethereum smart contract as of 1st of April 2022, whose been verified on [Etherscan](https://etherscan.io/) and has a least one transaction. A total of 1,541,370 smart contract functions are provided, parsed from 186,397 unique smart contracts, filtered down from 2,217,692 smart contracts.","description_withheld":null,"homepage":"https://doi.org/10.6084/m9.figshare.20780878","introduced_date":"2023-08-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/efficient-avoidance-of-vulnerabilities-in","title":"Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding","first_author":"André Storhaug","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"},{"name":"Code Completion","url":"/task/code-completion","datasets_with_task":"/datasets/task/code-completion"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Verified Smart Contract Code Comments"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/andstor/smart_contract_code_comments","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/code-generation-on-verified-smart-contract","task":"Code Generation","dataset_variant":"Verified Smart Contract Code Comments","rows":2,"metrics":["BLEU score"],"first_row_in_archive_order":{"model":"GPT-J 6B Smart Contract","paper":"/paper/efficient-avoidance-of-vulnerabilities-in","metrics":{"BLEU score":"55.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/efficient-avoidance-of-vulnerabilities-in","title":"Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding","date":"2023-09-18","rows_on_this_dataset":2,"code_links":0,"syntology":null}],"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."}