{"url":"/task/temporal-casual-qa","name":"Temporal/Casual QA","slug":"temporal-casual-qa","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"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":6,"papers_with_code":5,"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":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/temporal-casual-qa-on-next-qa","slug":"temporal-casual-qa-on-next-qa","dataset":"NExT-QA","dataset_url":"/dataset/next-qa","rows_in_archive":8,"metrics":["WUPS"],"first_row_in_archive_order":{"model":"PaLI-X","paper_title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","paper_url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","paper_date":"2023-05-29","arxiv_id":"2305.18565","code_links":[{"title":"kyegomez/PALI","url":"https://github.com/kyegomez/PALI"},{"title":"doc-doc/NExT-OE","url":"https://github.com/doc-doc/NExT-OE"}],"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/next-qa","name":"NExT-QA","full_name":"","num_papers_in_archive":174},{"url":"/dataset/timeqa","name":"TimeQA","full_name":"Time-Sensitive QA","num_papers_in_archive":22},{"url":"/dataset/timelinekgqa","name":"TimelineKGQA","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"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":5,"of":5,"tagged_in_all":6,"items":[{"url":"/paper/flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","repositories_listed":5,"syntology":{"n":24,"n_ran":18,"n_unverified":6,"n_pointer_only":7}},{"url":"/paper/generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/gemini-a-family-of-highly-capable-multimodal-1","title":"Gemini: A Family of Highly Capable Multimodal Models","date":"2023-12-19","arxiv_id":"2312.11805","repositories_listed":1,"syntology":null},{"url":"/paper/pali-3-vision-language-models-smaller-faster","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","date":"2023-10-13","arxiv_id":"2310.09199","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":4,"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"}}