{"url":"/task/synthetic-data-evaluation","name":"Synthetic Data Evaluation","slug":"synthetic-data-evaluation","description_markdown":"The task involves evaluating the quality of synthetic data using ML metrics, which allows assessing the data quality from the perspective of its application to practical tasks.","categories":[{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":7,"papers_with_code":1,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/synthetic-data-evaluation-on-titanic","slug":"synthetic-data-evaluation-on-titanic","dataset":"Titanic","dataset_url":"/dataset/titanic","rows_in_archive":7,"metrics":["AUC"],"first_row_in_archive_order":{"model":"zGAN","paper_title":"zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation","paper_url":"/paper/zgan-an-outlier-focused-generative","paper_date":"2024-10-28","arxiv_id":"2410.20808","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/titanic","name":"Titanic","full_name":"Titanic - Machine Learning from Disaster","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/synthetic-data-generation","name":"Synthetic Data Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":1,"of":1,"tagged_in_all":7,"items":[{"url":"/paper/what-s-wrong-with-your-synthetic-tabular-data","title":"What's Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models","date":"2025-04-29","arxiv_id":"2504.20687","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}