{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/table-retrieval","name":"Table Retrieval","slug":"table-retrieval","description_markdown":"When given a query, the goal of this task is to retrieve a relevant table from a (potentially large) collection of tables. The query could be a single sentence (such as a question), or it could also be a conversation. As for the retrieval, the tables could be in the raw form (i.e. the values of each cells), the metadata (such as the title, description), or summary statistics.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"},{"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":27,"papers_with_code":15,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/table-retrieval-on-statcan-dialogue-dataset","slug":"table-retrieval-on-statcan-dialogue-dataset","dataset":"Statcan Dialogue Dataset","dataset_url":"/dataset/statcan-dialogue-dataset","rows_in_archive":5,"metrics":["Recall@10"],"first_row_in_archive_order":{"model":"DPR (retrieving basic info + member items)","paper_title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","paper_url":"/paper/the-statcan-dialogue-dataset-retrieving-data","paper_date":"2023-04-03","arxiv_id":"2304.01412","code_links":[{"title":"McGill-NLP/statcan-dialogue-dataset","url":"https://github.com/McGill-NLP/statcan-dialogue-dataset"}],"syntology":null}}],"datasets":[{"url":"/dataset/compmix-ir","name":"CompMix-IR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/statcan-dialogue-dataset","name":"Statcan Dialogue Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/retrieval","name":"Retrieval"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":27,"of":27,"of_with_code":15,"tagged_in_all":27,"counts":{"archive_papers_tagged":27,"with_a_code_link":15,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":27,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/ad-hoc-table-retrieval-using-semantic","slug":"ad-hoc-table-retrieval-using-semantic","title":"Ad Hoc Table Retrieval using Semantic Similarity","date":"2018-02-16","arxiv_id":"1802.06159","repositories_listed":2,"syntology":null},{"url":"/paper/pneuma-leveraging-llms-for-tabular-data","slug":"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/multi-hop-table-retrieval-for-open-domain","slug":"multi-hop-table-retrieval-for-open-domain","title":"MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL","date":"2024-02-16","arxiv_id":"2402.10666","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-users-in-interactive-web-table","slug":"simulating-users-in-interactive-web-table","title":"Simulating Users in Interactive Web Table Retrieval","date":"2023-10-18","arxiv_id":"2310.11931","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-open-domain-table-question","slug":"enhancing-open-domain-table-question","title":"Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval","date":"2023-09-19","arxiv_id":"2309.10506","repositories_listed":1,"syntology":null},{"url":"/paper/the-statcan-dialogue-dataset-retrieving-data","slug":"the-statcan-dialogue-dataset-retrieving-data","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","date":"2023-04-03","arxiv_id":"2304.01412","repositories_listed":1,"syntology":null},{"url":"/paper/ctbl-augmenting-large-language-models-for","slug":"ctbl-augmenting-large-language-models-for","title":"cTBLS: Augmenting Large Language Models with Conversational Tables","date":"2023-03-21","arxiv_id":"2303.12024","repositories_listed":1,"syntology":null},{"url":"/paper/table-retrieval-may-not-necessitate-table","slug":"table-retrieval-may-not-necessitate-table","title":"Table Retrieval May Not Necessitate Table-specific Model Design","date":"2022-05-19","arxiv_id":"2205.09843","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/table-retrieval-may-not-necessitate-table#ran","syntology_url":"https://syntology.ai/paper/2205.09843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09843"}},"official":{"repos":["zorazrw/nqt-retrieval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/strubert-structure-aware-bert-for-table","slug":"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":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/strubert-structure-aware-bert-for-table#ran","syntology_url":"https://syntology.ai/paper/2203.14278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14278"}},"official":{"repos":["medtray/StruBERT"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cltr-an-end-to-end-transformer-based-system","slug":"cltr-an-end-to-end-transformer-based-system","title":"CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering","date":"2021-06-08","arxiv_id":"2106.04441","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-table-retrieval-using-keyword-and","slug":"semantic-table-retrieval-using-keyword-and","title":"Semantic Table Retrieval using Keyword and Table Queries","date":"2021-05-13","arxiv_id":"2105.06365","repositories_listed":1,"syntology":null},{"url":"/paper/wtr-a-test-collection-for-web-table-retrieval","slug":"wtr-a-test-collection-for-web-table-retrieval","title":"WTR: A Test Collection for Web Table Retrieval","date":"2021-05-05","arxiv_id":"2105.02354","repositories_listed":1,"syntology":null},{"url":"/paper/retrieving-complex-tables-with-multi-granular","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/retrieving-complex-tables-with-multi-granular#ran","syntology_url":"https://syntology.ai/paper/2105.01736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01736"}},"official":{"repos":["FeiWang96/GTR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/table-search-using-a-deep-contextualized","slug":"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},{"url":"/paper/190600041","slug":"190600041","title":"Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval","date":"2019-05-31","arxiv_id":"1906.00041","repositories_listed":1,"syntology":null},{"url":null,"slug":"opentable-r1-a-reinforcement-learning","title":"OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering","date":"2025-07-02","arxiv_id":"2507.03018","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-benchmarking-table-retrieval-for","title":"TARGET: Benchmarking Table Retrieval for Generative Tasks","date":"2025-05-14","arxiv_id":"2505.11545","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-queries-and-tables-through-entities","title":"Bridging Queries and Tables through Entities in Table Retrieval","date":"2025-04-09","arxiv_id":"2504.06551","repositories_listed":0,"syntology":null},{"url":null,"slug":"tailoring-table-retrieval-from-a-field-aware","title":"Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspective","date":"2025-03-04","arxiv_id":"2503.02251","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-table-retrieval-a-solved-problem-join","title":"Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrieval","date":"2024-04-15","arxiv_id":"2404.09889","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-the-gap-between-language-models-and","title":"Bridge the Gap between Language models and Tabular Understanding","date":"2023-02-16","arxiv_id":"2302.09302","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-table-question-answering-via","title":"End-to-End Table Question Answering via Retrieval-Augmented Generation","date":"2022-03-30","arxiv_id":"2203.16714","repositories_listed":0,"syntology":null},{"url":null,"slug":"table-retrieval-does-not-necessitate-table","title":"Table Retrieval Does Not Necessitate Table-specific Model Design","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cltr-an-end-to-end-transformer-based-system-1","title":"CLTR: An End-to-End, Transformer-Based System for Cell-Level Table Retrieval and Table Question Answering","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-schema-labels-to-enhance-dataset","title":"Leveraging Schema Labels to Enhance Dataset Search","date":"2020-01-27","arxiv_id":"2001.10112","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-answering-via-web-extracted-tables","title":"Question Answering via Web Extracted Tables and Pipelined Models","date":"2019-03-17","arxiv_id":"1903.07113","repositories_listed":0,"syntology":null},{"url":null,"slug":"content-based-table-retrieval-for-web-queries","title":"Content-Based Table Retrieval for Web Queries","date":"2017-06-08","arxiv_id":"1706.02427","repositories_listed":0,"syntology":null}],"syntology_records":3,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/table-retrieval/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/table-retrieval/papers/ran/1","json":"/task/table-retrieval/papers/ran/1.json","rows":2}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"d84fdaf675b9700a3f35db3f8515b2754dfbfe83dec5abf0ba242453f1b9e68c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}