{"url":"/dataset/verified-smart-contracts","name":"Verified Smart Contracts","full_name":null,"description_markdown":"**Verified Smart Contracts** is a dataset of real Ethereum smart contracts, containing both Solidity and Vyper source code. It consists of 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 186,397 unique smart contracts are provided, filtered down from 2,217,692 smart contracts. The dataset contains 53,843,305 lines of code.","description_withheld":null,"homepage":"https://doi.org/10.6084/m9.figshare.20781799","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":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"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":["andstor/smart_contracts inflated_plain_text","Verified Smart Contracts"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/andstor/smart_contracts","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":[],"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."}