{"url":"/task/synthetic-data-generation","name":"Synthetic Data Generation","slug":"synthetic-data-generation","description_markdown":"The generation of tabular data by any means possible.","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":822,"papers_with_code":325,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":11,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/synthetic-data-generation-on-uci-epileptic-1","slug":"synthetic-data-generation-on-uci-epileptic-1","dataset":"UCI Epileptic Seizure Recognition","dataset_url":"/dataset/uci-machine-learning-repository","rows_in_archive":2,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"corGAN","paper_title":"CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records","paper_url":"/paper/cor-gan-correlation-capturing-convolutional","paper_date":"2020-01-25","arxiv_id":"2001.09346","code_links":[{"title":"astorfi/cor-gan","url":"https://github.com/astorfi/cor-gan"}],"syntology":null}},{"leaderboard":"/sota/synthetic-data-generation-on-unsw-nb15","slug":"synthetic-data-generation-on-unsw-nb15","dataset":"UNSW-NB15","dataset_url":"/dataset/unsw-nb15","rows_in_archive":2,"metrics":["EMD"],"first_row_in_archive_order":{"model":"kiNETGAN","paper_title":"KiNETGAN: Enabling Distributed Network Intrusion Detection through Knowledge-Infused Synthetic Data Generation","paper_url":"/paper/kinetgan-enabling-distributed-network","paper_date":"2024-05-26","arxiv_id":"2405.16476","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/unsw-nb15","name":"UNSW-NB15","full_name":"UNSQ-NB15","num_papers_in_archive":156},{"url":"/dataset/uci-machine-learning-repository","name":"UCI Machine Learning Repository","full_name":null,"num_papers_in_archive":56},{"url":"/dataset/creative-flow-dataset","name":"Creative Flow+ Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/titanic","name":"Titanic","full_name":"Titanic - Machine Learning from Disaster","num_papers_in_archive":2},{"url":"/dataset/cbtex","name":"CBTex","full_name":"Synthetic CardBoard Textures","num_papers_in_archive":1},{"url":"/dataset/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","num_papers_in_archive":1},{"url":"/dataset/medibeng","name":"MediBeng","full_name":"Synthetic Code-Switched Bengali-English Speech Conversations for Healthcare Applications","num_papers_in_archive":1},{"url":"/dataset/sickle","name":"SICKLE","full_name":"Satellite Imagery for Cropping annotated with Keyparameter LabEls","num_papers_in_archive":1},{"url":"/dataset/synthetic-covid-19-cxr-dataset","name":"Synthetic COVID-19 CXR Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/synthetic-plant-dataset","name":"Synthetic Plant Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tf1-en-3m","name":"TF1-EN-3M","full_name":"klusai/ds-tf1-en-3m","num_papers_in_archive":1}],"subtasks":[{"url":"/task/synthetic-data-evaluation","name":"Synthetic Data Evaluation"},{"url":"/task/synthetic-outliers-evaluation","name":"Synthetic Outliers Evaluation"}],"parent_tasks":[],"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":30,"of":325,"tagged_in_all":822,"items":[{"url":"/paper/wasserstein-gan","title":"Wasserstein GAN","date":"2017-01-26","arxiv_id":"1701.07875","repositories_listed":120,"syntology":{"n":22,"n_ran":13,"n_unverified":9,"n_pointer_only":13}},{"url":"/paper/improved-training-of-wasserstein-gans","title":"Improved Training of Wasserstein GANs","date":"2017-03-31","arxiv_id":"1704.00028","repositories_listed":110,"syntology":{"n":49,"n_ran":27,"n_unverified":22,"n_pointer_only":20}},{"url":"/paper/generating-multidimensional-clusters-with","title":"Generating Multidimensional Clusters With Support Lines","date":"2023-01-24","arxiv_id":"2301.10327","repositories_listed":4,"syntology":null},{"url":"/paper/singan-seg-synthetic-training-data-generation","title":"SinGAN-Seg: Synthetic training data generation for medical image segmentation","date":"2021-06-29","arxiv_id":"2107.00471","repositories_listed":4,"syntology":null},{"url":"/paper/generating-high-fidelity-synthetic-time","title":"Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions","date":"2019-09-30","arxiv_id":"1909.13403","repositories_listed":4,"syntology":null},{"url":"/paper/synthetic-qa-corpora-generation-with","title":"Synthetic QA Corpora Generation with Roundtrip Consistency","date":"2019-06-12","arxiv_id":"1906.05416","repositories_listed":4,"syntology":null},{"url":"/paper/realtabformer-generating-realistic-relational","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","date":"2023-02-04","arxiv_id":"2302.02041","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/characterization-and-greedy-learning-of","title":"Characterization and Greedy Learning of Gaussian Structural Causal Models under Unknown Interventions","date":"2022-11-27","arxiv_id":"2211.14897","repositories_listed":3,"syntology":null},{"url":"/paper/scrape-cut-paste-and-learn-automated-dataset","title":"Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics","date":"2022-10-18","arxiv_id":"2210.09814","repositories_listed":3,"syntology":null},{"url":"/paper/rlip-relational-language-image-pre-training","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","date":"2022-09-05","arxiv_id":"2209.01814","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/delving-into-high-quality-synthetic-face","title":"Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets","date":"2022-05-12","arxiv_id":"2205.06218","repositories_listed":3,"syntology":null},{"url":"/paper/crossloc-scalable-aerial-localization","title":"CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data","date":"2021-12-16","arxiv_id":"2112.09081","repositories_listed":3,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/timevae-a-variational-auto-encoder-for-1","title":"TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation","date":"2021-11-15","arxiv_id":"2111.08095","repositories_listed":3,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/burst-denoising-with-kernel-prediction","title":"Burst Denoising with Kernel Prediction Networks","date":"2017-12-06","arxiv_id":"1712.02327","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/hp-gan-probabilistic-3d-human-motion","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","date":"2017-11-27","arxiv_id":"1711.09561","repositories_listed":3,"syntology":null},{"url":"/paper/annif-at-semeval-2025-task-5-traditional-xmtc","title":"Annif at SemEval-2025 Task 5: Traditional XMTC augmented by LLMs","date":"2025-04-28","arxiv_id":"2504.19675","repositories_listed":2,"syntology":null},{"url":"/paper/tabularargn-a-flexible-and-efficient-auto-1","title":"TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Data","date":"2025-01-21","arxiv_id":"2501.12012","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/using-matrix-product-states-for-time-series","title":"Using matrix-product states for time-series machine learning","date":"2024-12-20","arxiv_id":"2412.15826","repositories_listed":2,"syntology":null},{"url":"/paper/qwen2-5-coder-technical-report","title":"Qwen2.5-Coder Technical Report","date":"2024-09-18","arxiv_id":"2409.12186","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/a-synthetic-dataset-for-personal-attribute","title":"A Synthetic Dataset for Personal Attribute Inference","date":"2024-06-11","arxiv_id":"2406.07217","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/megactor-harness-the-power-of-raw-video-for","title":"MegActor: Harness the Power of Raw Video for Vivid Portrait Animation","date":"2024-05-31","arxiv_id":"2405.20851","repositories_listed":2,"syntology":{"n":17,"n_ran":9,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/ir2-information-regularization-for","title":"IR2: Information Regularization for Information Retrieval","date":"2024-02-25","arxiv_id":"2402.16200","repositories_listed":2,"syntology":null},{"url":"/paper/relation-extraction-in-underexplored","title":"Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach","date":"2023-11-10","arxiv_id":"2311.06364","repositories_listed":2,"syntology":null},{"url":"/paper/reimagining-synthetic-tabular-data-generation-1","title":"Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark","date":"2023-10-25","arxiv_id":"2310.16981","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/anthronet-conditional-generation-of-humans-1","title":"AnthroNet: Conditional Generation of Humans via Anthropometrics","date":"2023-09-07","arxiv_id":"2309.03812","repositories_listed":2,"syntology":null},{"url":"/paper/improving-2d-human-pose-estimation-across","title":"Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data","date":"2023-07-13","arxiv_id":"2307.06737","repositories_listed":2,"syntology":null},{"url":"/paper/bedlam-a-synthetic-dataset-of-bodies-1","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","date":"2023-06-29","arxiv_id":"2306.16940","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/trueteacher-learning-factual-consistency","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","date":"2023-05-18","arxiv_id":"2305.11171","repositories_listed":2,"syntology":null},{"url":"/paper/noise-aware-statistical-inference-with","title":"Noise-Aware Statistical Inference with Differentially Private Synthetic Data","date":"2022-05-28","arxiv_id":"2205.14485","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/generative-wind-power-curve-modeling-via","title":"Generative Wind Power Curve Modeling Via Machine Vision: A Self-learning Deep Convolutional Network Based Method","date":"2021-08-19","arxiv_id":"2109.00894","repositories_listed":2,"syntology":null}],"syntology_records":14,"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"}}