{"url":"/task/factual-probe","name":"Factual probe","slug":"factual-probe","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3,"papers_with_code":3,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/t-rex","name":"T-REx","full_name":"","num_papers_in_archive":117},{"url":"/dataset/bear-big","name":"BEAR-probe","full_name":"Benchmark for Evaluating Associative Reasoning","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":3,"of":3,"tagged_in_all":3,"items":[{"url":"/paper/bear-a-unified-framework-for-evaluating","title":"BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models","date":"2024-04-05","arxiv_id":"2404.04113","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/deepstruct-pretraining-of-language-models-for-1","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","date":"2022-05-21","arxiv_id":"2205.10475","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/zero-shot-information-extraction-as-a-unified","title":"Zero-Shot Information Extraction as a Unified Text-to-Triple Translation","date":"2021-09-23","arxiv_id":"2109.11171","repositories_listed":1,"syntology":null}],"syntology_records":2,"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"}}