{"url":"/sota/tabular-data-generation-on-heloc","task":{"name":"Tabular Data Generation","url":"/task/tabular-data-generation","note":null},"dataset":{"name":"HELOC","url":"/dataset/heloc"},"category":"Miscellaneous","categories":["Miscellaneous"],"category_note":null,"description":"Generation of the tabular data using generative models","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["DT Accuracy","LR Accuracy","Parameters(M)","RF Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"DT Accuracy":"higher","LR Accuracy":"higher","Parameters(M)":null,"RF Accuracy":"higher"}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Distill-GReaT","metrics":{"DT Accuracy":"81.4","LR Accuracy":"70.58","Parameters(M)":"82","RF Accuracy":"82.14"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/language-models-are-realistic-tabular-data","paper_url":"https://arxiv.org/abs/2210.06280v2","paper_title":"Language Models are Realistic Tabular Data Generators","code":"https://github.com/kathrinse/be_great","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"GReaT","metrics":{"DT Accuracy":"79.1","LR Accuracy":"71.9","Parameters(M)":"355","RF Accuracy":"80.93"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/language-models-are-realistic-tabular-data","paper_url":"https://arxiv.org/abs/2210.06280v2","paper_title":"Language Models are Realistic Tabular Data Generators","code":"https://github.com/kathrinse/be_great","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"TVAE","metrics":{"DT Accuracy":"76.39","LR Accuracy":"71.04","Parameters(M)":"62","RF Accuracy":"77.24"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/modeling-tabular-data-using-conditional-gan","paper_url":"https://arxiv.org/abs/1907.00503v2","paper_title":"Modeling Tabular data using Conditional GAN","code":"https://github.com/ydataai/ydata-synthetic/tree/dev/src/ydata_synthetic/synthesizers/regular/ctgan","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Binary Diffusion","metrics":{"DT Accuracy":"70.25","LR Accuracy":"71.76","Parameters(M)":"2.6","RF Accuracy":"70.47"},"uses_additional_data":false,"paper_date":"2024-09-20","paper":"/paper/tabular-data-generation-using-binary","paper_url":"https://arxiv.org/abs/2409.13882v2","paper_title":"Tabular Data Generation using Binary Diffusion","code":"https://github.com/vkinakh/binary-diffusion-tabular","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"CTGAN","metrics":{"DT Accuracy":"61.34","LR Accuracy":"57.72","Parameters(M)":"0.277","RF Accuracy":"62.35"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/modeling-tabular-data-using-conditional-gan","paper_url":"https://arxiv.org/abs/1907.00503v2","paper_title":"Modeling Tabular data using Conditional GAN","code":"https://github.com/ydataai/ydata-synthetic/tree/dev/src/ydata_synthetic/synthesizers/regular/ctgan","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CopulaGAN","metrics":{"DT Accuracy":"42.36","LR Accuracy":"42.03","Parameters(M)":"0.276","RF Accuracy":"42.35"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/modeling-tabular-data-using-conditional-gan","paper_url":"https://arxiv.org/abs/1907.00503v2","paper_title":"Modeling Tabular data using Conditional GAN","code":"https://github.com/ydataai/ydata-synthetic/tree/dev/src/ydata_synthetic/synthesizers/regular/ctgan","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":12,"n_unverified":7,"n_samples":19,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":16,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}