{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JLEVZPD4MUFSY4L2FYV4QNEDQH","short_pith_number":"pith:JLEVZPD4","schema_version":"1.0","canonical_sha256":"4ac95cbc7c650b2c717a2e2bc8348381ff8ed60fd662e3fa099ef871869ac96a","source":{"kind":"arxiv","id":"2503.18596","version":4},"attestation_state":"computed","paper":{"title":"LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Peiyu Liu, Xin Yang, Yihan Wang","submitted_at":"2025-03-24T11:53:06Z","abstract_excerpt":"Schema linking is a critical bottleneck in applying existing Text-to-SQL models to real-world, large-scale, multi-database environments. Through error analysis, we identify two major challenges in schema linking: (1) Database Retrieval: accurately selecting the target database from a large schema pool, while effectively filtering out irrelevant ones; and (2) Schema Item Grounding: precisely identifying the relevant tables and columns within complex and often redundant schemas for SQL generation. Based on these, we introduce LinkAlign, a novel framework tailored for large-scale databases with t"},"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":"2503.18596","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T11:53:06Z","cross_cats_sorted":[],"title_canon_sha256":"acdec1590dc67a3cde5754370404e9a81d3b55efee4d09bd2405a88a5a424aa5","abstract_canon_sha256":"b4ee76ef7ebcb77232d8aa549a3da82b822a816c04d12df8dd8568fc8b15e200"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:08.245955Z","signature_b64":"TcM+oV8PeOGuOaeX63dlC/urpdM0hH95NrE5ZNIApe5far82iSexIvXe8z7t8iN3FvHp+VmC5EF6RpWucvIwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ac95cbc7c650b2c717a2e2bc8348381ff8ed60fd662e3fa099ef871869ac96a","last_reissued_at":"2026-07-05T12:06:08.245456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:08.245456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Peiyu Liu, Xin Yang, Yihan Wang","submitted_at":"2025-03-24T11:53:06Z","abstract_excerpt":"Schema linking is a critical bottleneck in applying existing Text-to-SQL models to real-world, large-scale, multi-database environments. Through error analysis, we identify two major challenges in schema linking: (1) Database Retrieval: accurately selecting the target database from a large schema pool, while effectively filtering out irrelevant ones; and (2) Schema Item Grounding: precisely identifying the relevant tables and columns within complex and often redundant schemas for SQL generation. Based on these, we introduce LinkAlign, a novel framework tailored for large-scale databases with t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18596","kind":"arxiv","version":4},"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/2503.18596/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":"2503.18596","created_at":"2026-07-05T12:06:08.245513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18596v4","created_at":"2026-07-05T12:06:08.245513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18596","created_at":"2026-07-05T12:06:08.245513+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLEVZPD4MUFS","created_at":"2026-07-05T12:06:08.245513+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLEVZPD4MUFSY4L2","created_at":"2026-07-05T12:06:08.245513+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLEVZPD4","created_at":"2026-07-05T12:06:08.245513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00675","citing_title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH","json":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH.json","graph_json":"https://pith.science/api/pith-number/JLEVZPD4MUFSY4L2FYV4QNEDQH/graph.json","events_json":"https://pith.science/api/pith-number/JLEVZPD4MUFSY4L2FYV4QNEDQH/events.json","paper":"https://pith.science/paper/JLEVZPD4"},"agent_actions":{"view_html":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH","download_json":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH.json","view_paper":"https://pith.science/paper/JLEVZPD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18596&json=true","fetch_graph":"https://pith.science/api/pith-number/JLEVZPD4MUFSY4L2FYV4QNEDQH/graph.json","fetch_events":"https://pith.science/api/pith-number/JLEVZPD4MUFSY4L2FYV4QNEDQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH/action/storage_attestation","attest_author":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH/action/author_attestation","sign_citation":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH/action/citation_signature","submit_replication":"https://pith.science/pith/JLEVZPD4MUFSY4L2FYV4QNEDQH/action/replication_record"}},"created_at":"2026-07-05T12:06:08.245513+00:00","updated_at":"2026-07-05T12:06:08.245513+00:00"}