{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V27WPBAMN76BLH53VFVLHGGVGH","short_pith_number":"pith:V27WPBAM","schema_version":"1.0","canonical_sha256":"aebf67840c6ffc159fbba96ab398d531dce9261cd03876c578e3604006b4a3fa","source":{"kind":"arxiv","id":"2507.10897","version":1},"attestation_state":"computed","paper":{"title":"LLMATCH: A Unified Schema Matching Framework with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bing Tian Dai, Hanhua Xiao, Lambert Deng, Roy Ka-Wei Lee, Sha Wang, Yanfei Dong, Yuchen Li","submitted_at":"2025-07-15T01:24:49Z","abstract_excerpt":"Schema matching is a foundational task in enterprise data integration, aiming to align disparate data sources. While traditional methods handle simple one-to-one table mappings, they often struggle with complex multi-table schema matching in real-world applications. We present LLMatch, a unified and modular schema matching framework. LLMatch decomposes schema matching into three distinct stages: schema preparation, table-candidate selection, and column-level alignment, enabling component-level evaluation and future-proof compatibility. It includes a novel two-stage optimization strategy: a Rol"},"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":"2507.10897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-15T01:24:49Z","cross_cats_sorted":[],"title_canon_sha256":"d8091112941c058c19f9b9d80417be093d44527f5d9770c2a4f36852f40475f9","abstract_canon_sha256":"d48cbf3704ec34464b583064d8275261e8c35b14b723397adb729a6ddcd10382"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:27.986053Z","signature_b64":"D1gnWYsfjEe7fm3Fp6KUcbK36ORFA+OP0QXQS6uFpDU4DQkt+xcUkSbj1C55Aw+9oyIHw7apiEKLcB8P+TUXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aebf67840c6ffc159fbba96ab398d531dce9261cd03876c578e3604006b4a3fa","last_reissued_at":"2026-07-05T11:37:27.985506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:27.985506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMATCH: A Unified Schema Matching Framework with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bing Tian Dai, Hanhua Xiao, Lambert Deng, Roy Ka-Wei Lee, Sha Wang, Yanfei Dong, Yuchen Li","submitted_at":"2025-07-15T01:24:49Z","abstract_excerpt":"Schema matching is a foundational task in enterprise data integration, aiming to align disparate data sources. While traditional methods handle simple one-to-one table mappings, they often struggle with complex multi-table schema matching in real-world applications. We present LLMatch, a unified and modular schema matching framework. LLMatch decomposes schema matching into three distinct stages: schema preparation, table-candidate selection, and column-level alignment, enabling component-level evaluation and future-proof compatibility. It includes a novel two-stage optimization strategy: a Rol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10897","kind":"arxiv","version":1},"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/2507.10897/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":"2507.10897","created_at":"2026-07-05T11:37:27.985622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10897v1","created_at":"2026-07-05T11:37:27.985622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10897","created_at":"2026-07-05T11:37:27.985622+00:00"},{"alias_kind":"pith_short_12","alias_value":"V27WPBAMN76B","created_at":"2026-07-05T11:37:27.985622+00:00"},{"alias_kind":"pith_short_16","alias_value":"V27WPBAMN76BLH53","created_at":"2026-07-05T11:37:27.985622+00:00"},{"alias_kind":"pith_short_8","alias_value":"V27WPBAM","created_at":"2026-07-05T11:37:27.985622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07843","citing_title":"RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20482","citing_title":"ConStruM: A Structure-Guided LLM Framework for Context-Aware Schema Matching","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH","json":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH.json","graph_json":"https://pith.science/api/pith-number/V27WPBAMN76BLH53VFVLHGGVGH/graph.json","events_json":"https://pith.science/api/pith-number/V27WPBAMN76BLH53VFVLHGGVGH/events.json","paper":"https://pith.science/paper/V27WPBAM"},"agent_actions":{"view_html":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH","download_json":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH.json","view_paper":"https://pith.science/paper/V27WPBAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10897&json=true","fetch_graph":"https://pith.science/api/pith-number/V27WPBAMN76BLH53VFVLHGGVGH/graph.json","fetch_events":"https://pith.science/api/pith-number/V27WPBAMN76BLH53VFVLHGGVGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH/action/storage_attestation","attest_author":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH/action/author_attestation","sign_citation":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH/action/citation_signature","submit_replication":"https://pith.science/pith/V27WPBAMN76BLH53VFVLHGGVGH/action/replication_record"}},"created_at":"2026-07-05T11:37:27.985622+00:00","updated_at":"2026-07-05T11:37:27.985622+00:00"}