{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/datagene-a-framework-for-dataset-similarity","title":"DataGene: A Framework for Dataset Similarity","arxiv_id":null,"date":"2020-06-05","proceeding":"The Alan Turing Institute 2020 6","authors":["Derek Snow"],"abstract":"DataGene is developed to identify data set similarity between real and synthetic datasets as well as train, test, and validation datasets. For many modelling and software development tasks there is a need for datasets to have share similar characteristics. This has traditionally been achieved with visualizations, DataGene seeks to replace these visual methods with a range of novel quantitative methods. Please see the GitHub repository to inspect and install the Python code.","url_abs":"https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3619626","url_pdf":"https://poseidon01.ssrn.com/delivery.php?ID=934115017026001116105082102071096087004000029032026050076123026006092105102106118100121056010047106017007064016071073078024065061005033048047069001071121124111126072086015001004104118082027021001008089012072103027127071098079012123021091117074022125008&EXT=pdf&INDEX=TRUE","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"datagene-a-framework-for-dataset-similarity","repo_url":"https://github.com/firmai/datagene","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}