{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BC4I4CJGZOXAA7IV4SSZWUDG6Q","short_pith_number":"pith:BC4I4CJG","schema_version":"1.0","canonical_sha256":"08b88e0926cbae007d15e4a59b5066f436582db2ba96dec873c5f43f7f9277fc","source":{"kind":"arxiv","id":"2507.14376","version":1},"attestation_state":"computed","paper":{"title":"Schemora: schema matching via multi-stage recommendation and metadata enrichment using off-the-shelf llms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Derak Paulsen, Osman Erman Gungor, William Kang","submitted_at":"2025-07-18T21:50:36Z","abstract_excerpt":"Schema matching is essential for integrating heterogeneous data sources and enhancing dataset discovery, yet it remains a complex and resource-intensive problem. We introduce SCHEMORA, a schema matching framework that combines large language models with hybrid retrieval techniques in a prompt-based approach, enabling efficient identification of candidate matches without relying on labeled training data or exhaustive pairwise comparisons. By enriching schema metadata and leveraging both vector-based and lexical retrieval, SCHEMORA improves matching accuracy and scalability. Evaluated on the MIM"},"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":"2507.14376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T21:50:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a8f46abcc7ed94ceec912f9170cfb8c3d87efa47a279186cf43b21658c9d37fa","abstract_canon_sha256":"533b3ce5cf83ced65c664a587e22f45d75d5a93039a8bd9a87d43657b71f47d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:05.091184Z","signature_b64":"ALU4M/1CBO3wIH1tSyTN57B1v7st6M8BrkxbiT5vknZNdjMLGBC7XWT4GeAkELHZa8wGQpA5sjJP3PpQOjSFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b88e0926cbae007d15e4a59b5066f436582db2ba96dec873c5f43f7f9277fc","last_reissued_at":"2026-07-05T11:40:05.090748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:05.090748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Schemora: schema matching via multi-stage recommendation and metadata enrichment using off-the-shelf llms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Derak Paulsen, Osman Erman Gungor, William Kang","submitted_at":"2025-07-18T21:50:36Z","abstract_excerpt":"Schema matching is essential for integrating heterogeneous data sources and enhancing dataset discovery, yet it remains a complex and resource-intensive problem. We introduce SCHEMORA, a schema matching framework that combines large language models with hybrid retrieval techniques in a prompt-based approach, enabling efficient identification of candidate matches without relying on labeled training data or exhaustive pairwise comparisons. By enriching schema metadata and leveraging both vector-based and lexical retrieval, SCHEMORA improves matching accuracy and scalability. Evaluated on the MIM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14376","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/2507.14376/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":"2507.14376","created_at":"2026-07-05T11:40:05.090803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14376v1","created_at":"2026-07-05T11:40:05.090803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14376","created_at":"2026-07-05T11:40:05.090803+00:00"},{"alias_kind":"pith_short_12","alias_value":"BC4I4CJGZOXA","created_at":"2026-07-05T11:40:05.090803+00:00"},{"alias_kind":"pith_short_16","alias_value":"BC4I4CJGZOXAA7IV","created_at":"2026-07-05T11:40:05.090803+00:00"},{"alias_kind":"pith_short_8","alias_value":"BC4I4CJG","created_at":"2026-07-05T11:40:05.090803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.20482","citing_title":"ConStruM: A Structure-Guided LLM Framework for Context-Aware Schema Matching","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q","json":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q.json","graph_json":"https://pith.science/api/pith-number/BC4I4CJGZOXAA7IV4SSZWUDG6Q/graph.json","events_json":"https://pith.science/api/pith-number/BC4I4CJGZOXAA7IV4SSZWUDG6Q/events.json","paper":"https://pith.science/paper/BC4I4CJG"},"agent_actions":{"view_html":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q","download_json":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q.json","view_paper":"https://pith.science/paper/BC4I4CJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14376&json=true","fetch_graph":"https://pith.science/api/pith-number/BC4I4CJGZOXAA7IV4SSZWUDG6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/BC4I4CJGZOXAA7IV4SSZWUDG6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/action/storage_attestation","attest_author":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/action/author_attestation","sign_citation":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/action/citation_signature","submit_replication":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/action/replication_record"}},"created_at":"2026-07-05T11:40:05.090803+00:00","updated_at":"2026-07-05T11:40:05.090803+00:00"}