{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LQY2CCXPTQ6JTLHGIBIGALZZR6","short_pith_number":"pith:LQY2CCXP","schema_version":"1.0","canonical_sha256":"5c31a10aef9c3c99ace64050602f398fa0e7b5dc09bc5b5e0725c0e2526a7078","source":{"kind":"arxiv","id":"2501.08686","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.DB","authors_text":"Arijit Khan, B\\'alint Moln\\'ar, Chuangtao Ma, Sriom Chakrabarti","submitted_at":"2025-01-15T09:32:37Z","abstract_excerpt":"Traditional similarity-based schema matching methods are incapable of resolving semantic ambiguities and conflicts in domain-specific complex mapping scenarios due to missing commonsense and domain-specific knowledge. The hallucination problem of large language models (LLMs) also makes it challenging for LLM-based schema matching to address the above issues. Therefore, we propose a Knowledge Graph-based Retrieval-Augmented Generation model for Schema Matching, referred to as the KG-RAG4SM. In particular, KG-RAG4SM introduces novel vector-based, graph traversal-based, and query-based graph retr"},"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":"2501.08686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-01-15T09:32:37Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"314b67acd0c5c0195ac801f91f5a0e85fef536d99d7359286c6df84eae77292e","abstract_canon_sha256":"fc4614296cc24d36fee404c8d53031741a9382b4fb578ef38d984d9a9c1b3a93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:24.296938Z","signature_b64":"5Z6ju8Ysiq/hVmoONFO/uFdgd9Nj6raqzDR8k95rY/DF6NzoXbDx0GoBym0rVDZmZ3HWDn5BhdBpB5hQ7nIEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c31a10aef9c3c99ace64050602f398fa0e7b5dc09bc5b5e0725c0e2526a7078","last_reissued_at":"2026-07-05T10:01:24.296487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:24.296487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.DB","authors_text":"Arijit Khan, B\\'alint Moln\\'ar, Chuangtao Ma, Sriom Chakrabarti","submitted_at":"2025-01-15T09:32:37Z","abstract_excerpt":"Traditional similarity-based schema matching methods are incapable of resolving semantic ambiguities and conflicts in domain-specific complex mapping scenarios due to missing commonsense and domain-specific knowledge. The hallucination problem of large language models (LLMs) also makes it challenging for LLM-based schema matching to address the above issues. Therefore, we propose a Knowledge Graph-based Retrieval-Augmented Generation model for Schema Matching, referred to as the KG-RAG4SM. In particular, KG-RAG4SM introduces novel vector-based, graph traversal-based, and query-based graph retr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08686","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/2501.08686/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":"2501.08686","created_at":"2026-07-05T10:01:24.296546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08686v1","created_at":"2026-07-05T10:01:24.296546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08686","created_at":"2026-07-05T10:01:24.296546+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQY2CCXPTQ6J","created_at":"2026-07-05T10:01:24.296546+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQY2CCXPTQ6JTLHG","created_at":"2026-07-05T10:01:24.296546+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQY2CCXP","created_at":"2026-07-05T10:01:24.296546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11560","citing_title":"LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00008","citing_title":"SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26578","citing_title":"Graph Construction and Matching for Imperative Programs using Neural and Structural Methods","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20482","citing_title":"ConStruM: A Structure-Guided LLM Framework for Context-Aware Schema Matching","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02861","citing_title":"LLM+Graph@VLDB'2025 Workshop Summary","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26578","citing_title":"Graph Construction and Matching for Imperative Programs using Neural and Structural Methods","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6","json":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6.json","graph_json":"https://pith.science/api/pith-number/LQY2CCXPTQ6JTLHGIBIGALZZR6/graph.json","events_json":"https://pith.science/api/pith-number/LQY2CCXPTQ6JTLHGIBIGALZZR6/events.json","paper":"https://pith.science/paper/LQY2CCXP"},"agent_actions":{"view_html":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6","download_json":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6.json","view_paper":"https://pith.science/paper/LQY2CCXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08686&json=true","fetch_graph":"https://pith.science/api/pith-number/LQY2CCXPTQ6JTLHGIBIGALZZR6/graph.json","fetch_events":"https://pith.science/api/pith-number/LQY2CCXPTQ6JTLHGIBIGALZZR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6/action/storage_attestation","attest_author":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6/action/author_attestation","sign_citation":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6/action/citation_signature","submit_replication":"https://pith.science/pith/LQY2CCXPTQ6JTLHGIBIGALZZR6/action/replication_record"}},"created_at":"2026-07-05T10:01:24.296546+00:00","updated_at":"2026-07-05T10:01:24.296546+00:00"}