{"url":"/dataset/housekeep","name":"Housekeep","full_name":null,"description_markdown":"**Housekeep** a benchmark to evaluate common sense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. The dataset contains where humans typically place objects in tidy and untidy houses constituting 1799 objects, 268 object categories, 585 placements, and 105 rooms.\r\n\r\nSource: [Housekeep: Tidying Virtual Households using Commonsense Reasoning](https://arxiv.org/pdf/2205.10712v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2205.10712v1.pdf](https://arxiv.org/pdf/2205.10712v1.pdf)","description_withheld":null,"homepage":"https://yashkant.github.io/housekeep/","introduced_date":"2022-05-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/housekeep-tidying-virtual-households-using","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","first_author":"Yash Kant","url":null},"license":null,"modalities":[{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Housekeep"],"data_loaders":[],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"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."}