{"url":"/dataset/adult-data-set","name":"Adult","full_name":null,"description_markdown":"Data Set Information:\r\nExtraction was done by Barry Becker from the 1994 Census database. A set of reasonably clean records was extracted using the following conditions: ((AAGE>16) && (AGI>100) && (AFNLWGT>1)&& (HRSWK>0))\r\n\r\nPrediction task is to determine whether a person makes over 50K a year.","description_withheld":null,"homepage":"https://archive.ics.uci.edu/ml/datasets/adult","introduced_date":"1996-05-01","introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons Attribution 4.0 International license (CC BY 4.0)","url":"https://archive.ics.uci.edu/ml/citation_policy.html"},"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Imputation","url":"/task/imputation","datasets_with_task":"/datasets/task/imputation"},{"name":"General Classification","url":"/task/classification","datasets_with_task":"/datasets/task/classification"},{"name":"single catogory classification","url":"/task/single-catogory-classification","datasets_with_task":"/datasets/task/single-catogory-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Adult"],"data_loaders":[],"num_papers_in_archive":56,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/classification-on-adult","task":"Classification","dataset_variant":"Adult","rows":1,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"MambaNet","paper":"/paper/mambatab-a-simple-yet-effective-approach-for","metrics":{"AUROC":"0.914"},"code_links":[{"title":"atik-ahamed/mambatab","url":"https://github.com/atik-ahamed/mambatab"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/imputation-on-adult-data-set","task":"Imputation","dataset_variant":"Adult","rows":1,"metrics":["Test error"],"first_row_in_archive_order":{"model":"ANN","paper":"/paper/missing-data-imputation-for-supervised","metrics":{"Test error":"0.144 ± 0.06"},"code_links":[{"title":"rafaelvalle/MDI","url":"https://github.com/rafaelvalle/MDI"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mambatab-a-simple-yet-effective-approach-for","title":"MambaTab: A Plug-and-Play Model for Learning Tabular Data","date":"2024-01-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/missing-data-imputation-for-supervised","title":"Missing Data Imputation for Supervised Learning","date":"2016-10-28","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}