{"url":"/dataset/vsr","name":"VSR","full_name":"Visual Spatial Reasoning","description_markdown":"The Visual Spatial Reasoning (VSR) corpus is a collection of caption-image pairs with true/false labels. Each caption describes the spatial relation of two individual objects in the image, and a vision-language model (VLM) needs to judge whether the caption is correctly describing the image (True) or not (False).","description_withheld":null,"homepage":"https://github.com/cambridgeltl/visual-spatial-reasoning","introduced_date":"2022-04-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/visual-spatial-reasoning","title":"Visual Spatial Reasoning","first_author":"Fangyu Liu","url":null},"license":{"name":"Apache License 2.0","url":"https://github.com/cambridgeltl/visual-spatial-reasoning/blob/master/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Reasoning","url":"/task/visual-reasoning","datasets_with_task":"/datasets/task/visual-reasoning"},{"name":"Visual Entailment","url":"/task/visual-entailment","datasets_with_task":"/datasets/task/visual-entailment"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VSR"],"data_loaders":[],"num_papers_in_archive":69,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-reasoning-on-vsr","task":"Visual Reasoning","dataset_variant":"VSR","rows":5,"metrics":["accuracy"],"first_row_in_archive_order":{"model":"LXMERT","paper":"/paper/visual-spatial-reasoning","metrics":{"accuracy":"70.1"},"code_links":[{"title":"cambridgeltl/visual-spatial-reasoning","url":"https://github.com/cambridgeltl/visual-spatial-reasoning"},{"title":"ziyan-xiaoyu/spatialmqa","url":"https://github.com/ziyan-xiaoyu/spatialmqa"},{"title":"sohojoe/clip_visual-spatial-reasoning","url":"https://github.com/sohojoe/clip_visual-spatial-reasoning"},{"title":"MindCode-4/code-1","url":"https://github.com/MindCode-4/code-1/tree/main/vilt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/visual-spatial-reasoning","title":"Visual Spatial Reasoning","date":"2022-04-30","rows_on_this_dataset":5,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"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":1,"samples_harvested":10,"samples_ran":5,"samples_unverified":5,"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."}