{"url":"/task/table-search","name":"Table Search","slug":"table-search","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":15,"papers_with_code":10,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/pylon-benchmark","name":"Pylon Benchmark","full_name":"Pylon Table Union Search Benchmark","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/information-retrieval","name":"Information Retrieval"}],"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":10,"of":10,"tagged_in_all":15,"items":[{"url":"/paper/table-pretraining-a-survey-on-model","title":"Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks","date":"2022-01-24","arxiv_id":"2201.09745","repositories_listed":3,"syntology":null},{"url":"/paper/pneuma-leveraging-llms-for-tabular-data","title":"Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System","date":"2025-04-12","arxiv_id":"2504.09207","repositories_listed":1,"syntology":null},{"url":"/paper/tabsketchfm-sketch-based-tabular","title":"TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes","date":"2024-06-28","arxiv_id":"2407.01619","repositories_listed":1,"syntology":null},{"url":"/paper/toward-conversational-agents-with-context-and","title":"Toward Conversational Agents with Context and Time Sensitive Long-term Memory","date":"2024-05-29","arxiv_id":"2406.00057","repositories_listed":1,"syntology":null},{"url":"/paper/from-specific-to-generic-learned-sorted-set","title":"From Specific to Generic Learned Sorted Set Dictionaries: A Theoretically Sound Paradigm Yelding Competitive Data Structural Boosters in Practice","date":"2023-09-02","arxiv_id":"2309.00946","repositories_listed":1,"syntology":null},{"url":"/paper/generative-benchmark-creation-for-table-union","title":"Generative Benchmark Creation for Table Union Search","date":"2023-08-07","arxiv_id":"2308.03883","repositories_listed":1,"syntology":null},{"url":"/paper/strubert-structure-aware-bert-for-table","title":"StruBERT: Structure-aware BERT for Table Search and Matching","date":"2022-03-27","arxiv_id":"2203.14278","repositories_listed":1,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/learned-sorted-table-search-and-static","title":"Learned Sorted Table Search and Static Indexes in Small Model Space","date":"2021-07-19","arxiv_id":"2107.09480","repositories_listed":1,"syntology":null},{"url":"/paper/retrieving-complex-tables-with-multi-granular","title":"Retrieving Complex Tables with Multi-Granular Graph Representation Learning","date":"2021-05-04","arxiv_id":"2105.01736","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/table-search-using-a-deep-contextualized","title":"Table Search Using a Deep Contextualized Language Model","date":"2020-05-19","arxiv_id":"2005.09207","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"}}