{"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/spider-realistic/papers/ran/1","list_of":"/dataset/spider-realistic","dataset":"Spider-Realistic","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","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,"rows":[1,14],"of":14,"counts":{"papers_with_a_benchmark_row":23,"with_a_code_link":21,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":23,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":4,"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"},"first_page":"/dataset/spider-realistic/papers/ran/1","prev":null,"next":null,"papers":[{"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":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"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":9,"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/pet-sql-a-prompt-enhanced-two-stage-text-to","slug":"pet-sql-a-prompt-enhanced-two-stage-text-to","title":"PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency","date":"2024-03-13","arxiv_id":"2403.09732","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["zhshlii/petsql"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pet-sql-a-prompt-enhanced-two-stage-text-to#ran","syntology_url":"https://syntology.ai/paper/2403.09732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09732"}}}},{"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":"2026-09-28T10:30:06+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/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":"2026-09-28T10:30:06+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/c3-zero-shot-text-to-sql-with-chatgpt","slug":"c3-zero-shot-text-to-sql-with-chatgpt","title":"C3: Zero-shot Text-to-SQL with ChatGPT","date":"2023-07-14","arxiv_id":"2307.07306","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bigbigwatermalon/c3sql"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/c3-zero-shot-text-to-sql-with-chatgpt#ran","syntology_url":"https://syntology.ai/paper/2307.07306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07306"}}}},{"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":"2026-09-28T10:30:06+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"}}}},{"paper":"/paper/lever-learning-to-verify-language-to-code","slug":"lever-learning-to-verify-language-to-code","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","date":"2023-02-16","arxiv_id":"2302.08468","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":22,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":18,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["niansong1996/lever"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lever-learning-to-verify-language-to-code#ran","syntology_url":"https://syntology.ai/paper/2302.08468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08468"}}}},{"paper":"/paper/rasat-integrating-relational-structures-into","slug":"rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","date":"2022-05-14","arxiv_id":"2205.06983","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["lumia-group/rasat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rasat-integrating-relational-structures-into#ran","syntology_url":"https://syntology.ai/paper/2205.06983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06983"}}}},{"paper":"/paper/sadga-structure-aware-dual-graph-aggregation","slug":"sadga-structure-aware-dual-graph-aggregation","title":"SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL","date":"2021-11-01","arxiv_id":"2111.00653","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["dmirlab-group/sadga"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sadga-structure-aware-dual-graph-aggregation#ran","syntology_url":"https://syntology.ai/paper/2111.00653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00653"}}}},{"paper":"/paper/picard-parsing-incrementally-for-constrained","slug":"picard-parsing-incrementally-for-constrained","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","date":"2021-09-10","arxiv_id":"2109.05093","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ElementAI/picard"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/picard-parsing-incrementally-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2109.05093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05093"}}}},{"paper":"/paper/grappa-grammar-augmented-pre-training-for","slug":"grappa-grammar-augmented-pre-training-for","title":"GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing","date":"2020-09-29","arxiv_id":"2009.13845","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":1,"pointer_only_for_licence":7,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/grappa-grammar-augmented-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2009.13845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13845"}}}},{"paper":"/paper/ryansql-recursively-applying-sketch-based","slug":"ryansql-recursively-applying-sketch-based","title":"RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases","date":"2020-04-07","arxiv_id":"2004.03125","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["kakaoenterprise/RYANSQL"],"state":"official (archive's flag): 1 ran","n_ran":1,"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/ryansql-recursively-applying-sketch-based#ran","syntology_url":"https://syntology.ai/paper/2004.03125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03125"}}}},{"paper":"/paper/rat-sql-relation-aware-schema-encoding-and-1","slug":"rat-sql-relation-aware-schema-encoding-and-1","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","date":"2019-11-10","arxiv_id":"1911.04942","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["Microsoft/rat-sql"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rat-sql-relation-aware-schema-encoding-and-1#ran","syntology_url":"https://syntology.ai/paper/1911.04942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04942"}}}},{"paper":"/paper/spider-a-large-scale-human-labeled-dataset","slug":"spider-a-large-scale-human-labeled-dataset","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","date":"2018-09-24","arxiv_id":"1809.08887","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["taoyds/spider"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spider-a-large-scale-human-labeled-dataset#ran","syntology_url":"https://syntology.ai/paper/1809.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.08887"}}}}],"record_sha256":"1017fd18ab8cfd2ac9bfef21ca7f725719471430c163571e3780776f4a88ed58","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}