{"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":"/dataset/bird-sql","name":"BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)","full_name":null,"description_markdown":"BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation) represents a pioneering, cross-domain dataset that examines the impact of extensive database contents on text-to-SQL parsing. BIRD contains over 12,751 unique question-SQL pairs and 95 big databases with a total size of 33.4 GB. It also covers more than 37 professional domains, such as blockchain, hockey, healthcare and education, etc.","description_withheld":null,"homepage":"https://bird-bench.github.io/","introduced_date":"2023-05-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/can-llm-already-serve-as-a-database-interface","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","first_author":"Jinyang Li","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text-To-SQL","url":"/task/text-to-sql","datasets_with_task":"/datasets/task/text-to-sql"}],"languages":[],"variants":["BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-sql-on-bird-big-bench-for-large-scale","task":"Text-To-SQL","dataset_variant":"BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)","rows":41,"metrics":["Execution Accuracy % (Test)","Execution Accuracy % (Dev)","Execution Accurarcy (Human)"],"first_row_in_archive_order":{"model":"XiYan-SQL","paper":"/paper/xiyan-sql-a-multi-generator-ensemble","metrics":{"Execution Accuracy % (Dev)":"73.34","Execution Accuracy % (Test)":"75.63"},"code_links":[{"title":"XGenerationLab/XiYan-SQL","url":"https://github.com/XGenerationLab/XiYan-SQL"},{"title":"xgenerationlab/xiyan_mcp_server","url":"https://github.com/xgenerationlab/xiyan_mcp_server"},{"title":"XGenerationLab/M-Schema","url":"https://github.com/XGenerationLab/M-Schema"},{"title":"xgenerationlab/xiyan-dbdescgen","url":"https://github.com/xgenerationlab/xiyan-dbdescgen"},{"title":"XGenerationLab/XiYan-DateResolver","url":"https://github.com/XGenerationLab/XiYan-DateResolver"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":11,"of":11,"counts":{"papers_with_a_benchmark_row":11,"with_a_code_link":9,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":2,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/xiyan-sql-a-multi-generator-ensemble","slug":"xiyan-sql-a-multi-generator-ensemble","title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","date":"2024-11-13","arxiv_id":"2411.08599","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/msc-sql-multi-sample-critiquing-small","slug":"msc-sql-multi-sample-critiquing-small","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","date":"2024-10-16","arxiv_id":"2410.12916","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["layer6ai-labs/msc-sql"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/msc-sql-multi-sample-critiquing-small#ran","syntology_url":"https://syntology.ai/paper/2410.12916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12916"}}}},{"paper":"/paper/chase-sql-multi-path-reasoning-and-preference","slug":"chase-sql-multi-path-reasoning-and-preference","title":"CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL","date":"2024-10-02","arxiv_id":"2410.01943","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-death-of-schema-linking-text-to-sql-in","slug":"the-death-of-schema-linking-text-to-sql-in","title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","date":"2024-08-14","arxiv_id":"2408.07702","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/chess-contextual-harnessing-for-efficient-sql","slug":"chess-contextual-harnessing-for-efficient-sql","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","date":"2024-05-27","arxiv_id":"2405.16755","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["shayantalaei/chess"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chess-contextual-harnessing-for-efficient-sql#ran","syntology_url":"https://syntology.ai/paper/2405.16755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16755"}}}},{"paper":"/paper/knowledge-to-sql-enhancing-sql-generation","slug":"knowledge-to-sql-enhancing-sql-generation","title":"Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM","date":"2024-02-18","arxiv_id":"2402.11517","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["Rcrossmeister/Knowledge-to-SQL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/knowledge-to-sql-enhancing-sql-generation#ran","syntology_url":"https://syntology.ai/paper/2402.11517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11517"}}}},{"paper":"/paper/mac-sql-multi-agent-collaboration-for-text-to","slug":"mac-sql-multi-agent-collaboration-for-text-to","title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","date":"2023-12-18","arxiv_id":"2312.11242","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["wbbeyourself/mac-sql"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mac-sql-multi-agent-collaboration-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2312.11242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11242"}}}},{"paper":"/paper/can-llms-effectively-leverage-structural","slug":"can-llms-effectively-leverage-structural","title":"Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?","date":"2023-09-28","arxiv_id":"2309.16595","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":8,"official":{"repos":["trais-lab/llm-structured-data"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-llms-effectively-leverage-structural#ran","syntology_url":"https://syntology.ai/paper/2309.16595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16595"}}}},{"paper":"/paper/text-to-sql-empowered-by-large-language","slug":"text-to-sql-empowered-by-large-language","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","date":"2023-08-29","arxiv_id":"2308.15363","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["beachwang/dail-sql"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/text-to-sql-empowered-by-large-language#ran","syntology_url":"https://syntology.ai/paper/2308.15363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15363"}}}},{"paper":"/paper/can-llm-already-serve-as-a-database-interface","slug":"can-llm-already-serve-as-a-database-interface","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","date":"2023-05-04","arxiv_id":"2305.03111","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":0,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-llm-already-serve-as-a-database-interface#ran","syntology_url":"https://syntology.ai/paper/2305.03111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03111"}}}},{"paper":"/paper/din-sql-decomposed-in-context-learning-of-1","slug":"din-sql-decomposed-in-context-learning-of-1","title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","date":"2023-04-21","arxiv_id":"2304.11015","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["mohammadrezapourreza/few-shot-nl2sql-with-prompting"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/din-sql-decomposed-in-context-learning-of-1#ran","syntology_url":"https://syntology.ai/paper/2304.11015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11015"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/xiyan-sql-a-multi-generator-ensemble","slug":"xiyan-sql-a-multi-generator-ensemble","title":"A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL","date":"2024-11-13","arxiv_id":"2411.08599","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/msc-sql-multi-sample-critiquing-small","slug":"msc-sql-multi-sample-critiquing-small","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","date":"2024-10-16","arxiv_id":"2410.12916","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":5,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["layer6ai-labs/msc-sql"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/msc-sql-multi-sample-critiquing-small#ran","syntology_url":"https://syntology.ai/paper/2410.12916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12916"}}}},{"paper":"/paper/chase-sql-multi-path-reasoning-and-preference","slug":"chase-sql-multi-path-reasoning-and-preference","title":"CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL","date":"2024-10-02","arxiv_id":"2410.01943","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-death-of-schema-linking-text-to-sql-in","slug":"the-death-of-schema-linking-text-to-sql-in","title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","date":"2024-08-14","arxiv_id":"2408.07702","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/chess-contextual-harnessing-for-efficient-sql","slug":"chess-contextual-harnessing-for-efficient-sql","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","date":"2024-05-27","arxiv_id":"2405.16755","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["shayantalaei/chess"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chess-contextual-harnessing-for-efficient-sql#ran","syntology_url":"https://syntology.ai/paper/2405.16755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16755"}}}},{"paper":"/paper/knowledge-to-sql-enhancing-sql-generation","slug":"knowledge-to-sql-enhancing-sql-generation","title":"Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM","date":"2024-02-18","arxiv_id":"2402.11517","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["Rcrossmeister/Knowledge-to-SQL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/knowledge-to-sql-enhancing-sql-generation#ran","syntology_url":"https://syntology.ai/paper/2402.11517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11517"}}}},{"paper":"/paper/mac-sql-multi-agent-collaboration-for-text-to","slug":"mac-sql-multi-agent-collaboration-for-text-to","title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","date":"2023-12-18","arxiv_id":"2312.11242","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["wbbeyourself/mac-sql"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mac-sql-multi-agent-collaboration-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2312.11242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11242"}}}},{"paper":"/paper/can-llms-effectively-leverage-structural","slug":"can-llms-effectively-leverage-structural","title":"Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?","date":"2023-09-28","arxiv_id":"2309.16595","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":8,"official":{"repos":["trais-lab/llm-structured-data"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-llms-effectively-leverage-structural#ran","syntology_url":"https://syntology.ai/paper/2309.16595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16595"}}}},{"paper":"/paper/text-to-sql-empowered-by-large-language","slug":"text-to-sql-empowered-by-large-language","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","date":"2023-08-29","arxiv_id":"2308.15363","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["beachwang/dail-sql"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/text-to-sql-empowered-by-large-language#ran","syntology_url":"https://syntology.ai/paper/2308.15363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15363"}}}},{"paper":"/paper/can-llm-already-serve-as-a-database-interface","slug":"can-llm-already-serve-as-a-database-interface","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","date":"2023-05-04","arxiv_id":"2305.03111","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":0,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-llm-already-serve-as-a-database-interface#ran","syntology_url":"https://syntology.ai/paper/2305.03111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03111"}}}},{"paper":"/paper/din-sql-decomposed-in-context-learning-of-1","slug":"din-sql-decomposed-in-context-learning-of-1","title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","date":"2023-04-21","arxiv_id":"2304.11015","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["mohammadrezapourreza/few-shot-nl2sql-with-prompting"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/din-sql-decomposed-in-context-learning-of-1#ran","syntology_url":"https://syntology.ai/paper/2304.11015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11015"}}}}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/bird-sql/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/bird-sql/papers/ran/1","json":"/dataset/bird-sql/papers/ran/1.json","rows":8}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":8,"samples_harvested":49,"samples_ran":40,"samples_constructed":0,"samples_ran_checked":19,"samples_ran_instrument_failed":21,"samples_unverified":9,"pointer_only_for_licence":17,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":6,"papers_where_every_run_was_an_instrument_failure":2,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"2ca842332634cc58213dcb6836e5f9ef3c02179ba2612ac8f0f0a818ec4698b7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}