{"url":"/task/visual-commonsense-tests","name":"Visual Commonsense Tests","slug":"visual-commonsense-tests","description_markdown":"Predict 5 property types (color, shape, material, size, and visual co-occurrence) for over 5000 subjects.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2,"papers_with_code":2,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-commonsense-tests-on-vicomte-color","slug":"visual-commonsense-tests-on-vicomte-color","dataset":"ViComTe-color","dataset_url":null,"rows_in_archive":2,"metrics":["Spearman's Rho"],"first_row_in_archive_order":{"model":"BERT-large","paper_title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","paper_url":"/paper/visual-commonsense-in-pretrained-unimodal-and-1","paper_date":"2022-05-04","arxiv_id":"2205.01850","code_links":[{"title":"chenyuheidizhang/vl-commonsense","url":"https://github.com/chenyuheidizhang/vl-commonsense"}],"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}}}],"datasets":[{"url":"/dataset/whoops","name":"WHOOPS!","full_name":"","num_papers_in_archive":14}],"subtasks":[],"parent_tasks":[{"url":"/task/common-sense-reasoning","name":"Common Sense Reasoning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":2,"items":[{"url":"/paper/z-lavi-zero-shot-language-solver-fueled-by","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","date":"2022-10-21","arxiv_id":"2210.12261","repositories_listed":1,"syntology":null},{"url":"/paper/visual-commonsense-in-pretrained-unimodal-and-1","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","date":"2022-05-04","arxiv_id":"2205.01850","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}