{"url":"/dataset/adult-census-income","name":"Adult Census Income","full_name":"adult_census_income","description_markdown":"This data was extracted from the 1994 Census bureau database by Ronny Kohavi and Barry Becker (Data Mining and Visualization, Silicon Graphics). A set of reasonably clean records was extracted using the following conditions: ((AAGE>16) && (AGI>100) && (AFNLWGT>1) && (HRSWK>0)). The prediction task is to determine whether a person makes over $50K a year.","description_withheld":null,"homepage":"https://www.kaggle.com/datasets/uciml/adult-census-income","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"CC0: Public Domain","url":"https://creativecommons.org/publicdomain/zero/1.0/"},"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Binary Classification","url":"/task/binary-classification","datasets_with_task":"/datasets/task/binary-classification"},{"name":"Tabular Data Generation","url":"/task/tabular-data-generation","datasets_with_task":"/datasets/task/tabular-data-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Adult Census Income"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/tabular-data-generation-on-adult-census","task":"Tabular Data Generation","dataset_variant":"Adult Census Income","rows":6,"metrics":["DT Accuracy","LR Accuracy","Parameters(M)","RF Accuracy"],"first_row_in_archive_order":{"model":"Binary Diffusion","paper":"/paper/tabular-data-generation-using-binary","metrics":{"DT Accuracy":"85.27","LR Accuracy":"85.45","Parameters(M)":"1.4","RF Accuracy":"85.74"},"code_links":[{"title":"vkinakh/binary-diffusion-tabular","url":"https://github.com/vkinakh/binary-diffusion-tabular"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tabular-data-generation-using-binary","title":"Tabular Data Generation using Binary Diffusion","date":"2024-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":10,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/language-models-are-realistic-tabular-data","title":"Language Models are Realistic Tabular Data Generators","date":"2022-10-12","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/modeling-tabular-data-using-conditional-gan","title":"Modeling Tabular data using Conditional GAN","date":"2019-07-01","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":19,"samples_ran":12,"samples_unverified":7,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}