{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IHOBR7ACIFA7IE5EJCDZQGGNIG","short_pith_number":"pith:IHOBR7AC","schema_version":"1.0","canonical_sha256":"41dc18fc024141f413a448879818cd41bf57a8a9efa1c0a89387448244e72eda","source":{"kind":"arxiv","id":"2408.07702","version":2},"attestation_state":"computed","paper":{"title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amine Mhedhbi, Daniel Jaroslawicz, Fadhil Abubaker, Karime Maamari","submitted_at":"2024-08-14T17:59:04Z","abstract_excerpt":"Schema linking is a crucial step in Text-to-SQL pipelines. Its goal is to retrieve the relevant tables and columns of a target database for a user's query while disregarding irrelevant ones. However, imperfect schema linking can often exclude required columns needed for accurate query generation. In this work, we revisit schema linking when using the latest generation of large language models (LLMs). We find empirically that newer models are adept at utilizing relevant schema elements during generation even in the presence of large numbers of irrelevant ones. As such, our Text-to-SQL pipeline "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.07702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-14T17:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"b8cb69cfe4abb23c870c097655a4d5616f323fbffaa00c31a51732c36fad211a","abstract_canon_sha256":"84acbd79123bf17fa6d81db1fdb8f5745966860d66668be84180e8d52f98cb94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:24.433115Z","signature_b64":"1Hxduj0RIh6ZiNs+b5MMw54+/gtauAelza6ABIUi5eGnAYu/ggiwtIdcOyAOrq/2LQqVJ7GwEhnS6vhbt2U4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41dc18fc024141f413a448879818cd41bf57a8a9efa1c0a89387448244e72eda","last_reissued_at":"2026-07-05T08:56:24.432706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:24.432706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amine Mhedhbi, Daniel Jaroslawicz, Fadhil Abubaker, Karime Maamari","submitted_at":"2024-08-14T17:59:04Z","abstract_excerpt":"Schema linking is a crucial step in Text-to-SQL pipelines. Its goal is to retrieve the relevant tables and columns of a target database for a user's query while disregarding irrelevant ones. However, imperfect schema linking can often exclude required columns needed for accurate query generation. In this work, we revisit schema linking when using the latest generation of large language models (LLMs). We find empirically that newer models are adept at utilizing relevant schema elements during generation even in the presence of large numbers of irrelevant ones. As such, our Text-to-SQL pipeline "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07702","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.07702/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.07702","created_at":"2026-07-05T08:56:24.432763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07702v2","created_at":"2026-07-05T08:56:24.432763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07702","created_at":"2026-07-05T08:56:24.432763+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHOBR7ACIFA7","created_at":"2026-07-05T08:56:24.432763+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHOBR7ACIFA7IE5E","created_at":"2026-07-05T08:56:24.432763+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHOBR7AC","created_at":"2026-07-05T08:56:24.432763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23693","citing_title":"EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25838","citing_title":"Same Data, Different Schemas: Robustness of LLM-based Text-to-SQL","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29670","citing_title":"EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14174","citing_title":"Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18766","citing_title":"Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17586","citing_title":"DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13045","citing_title":"Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12319","citing_title":"Data-aware candidate selection in NL2SQL translation via small separating instances","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00628","citing_title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08057","citing_title":"CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG","json":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG.json","graph_json":"https://pith.science/api/pith-number/IHOBR7ACIFA7IE5EJCDZQGGNIG/graph.json","events_json":"https://pith.science/api/pith-number/IHOBR7ACIFA7IE5EJCDZQGGNIG/events.json","paper":"https://pith.science/paper/IHOBR7AC"},"agent_actions":{"view_html":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG","download_json":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG.json","view_paper":"https://pith.science/paper/IHOBR7AC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07702&json=true","fetch_graph":"https://pith.science/api/pith-number/IHOBR7ACIFA7IE5EJCDZQGGNIG/graph.json","fetch_events":"https://pith.science/api/pith-number/IHOBR7ACIFA7IE5EJCDZQGGNIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG/action/storage_attestation","attest_author":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG/action/author_attestation","sign_citation":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG/action/citation_signature","submit_replication":"https://pith.science/pith/IHOBR7ACIFA7IE5EJCDZQGGNIG/action/replication_record"}},"created_at":"2026-07-05T08:56:24.432763+00:00","updated_at":"2026-07-05T08:56:24.432763+00:00"}