{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KHLNAP4TH74PZWQVNID6SLHOKF","short_pith_number":"pith:KHLNAP4T","schema_version":"1.0","canonical_sha256":"51d6d03f933ff8fcda156a07e92cee516981e053e43b8e2891a0d5496357954a","source":{"kind":"arxiv","id":"2406.01876","version":1},"attestation_state":"computed","paper":{"title":"GRAM: Generative Retrieval Augmented Matching of Data Schemas in the Context of Data Security","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.DB","authors_text":"Austin Nevins, Davor Golac, Henrik Johnson, Luyang Kong, Nimish Amlathe, Patrick Song, Runhui Wang, Xuanqing Liu","submitted_at":"2024-06-04T01:08:00Z","abstract_excerpt":"Schema matching constitutes a pivotal phase in the data ingestion process for contemporary database systems. Its objective is to discern pairwise similarities between two sets of attributes, each associated with a distinct data table. This challenge emerges at the initial stages of data analytics, such as when incorporating a third-party table into existing databases to inform business insights. Given its significance in the realm of database systems, schema matching has been under investigation since the 2000s. This study revisits this foundational problem within the context of large language"},"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":"2406.01876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-06-04T01:08:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"bff69051d6a696db1b642a391653a8c83f38a473c611cb4c6e2efdec92c104d9","abstract_canon_sha256":"5bc86e6502edd4410383c705ad77373f851a6e6295caa90b8100db7d9ff4a8f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:11.083732Z","signature_b64":"kOF/AgGsom+Sh3IRt3Q1+QqntCKUn90cPyLEabiq2sZl7/iQt+40Pk8N5CQH3AIfh72VTohRBsmmlCToELc8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51d6d03f933ff8fcda156a07e92cee516981e053e43b8e2891a0d5496357954a","last_reissued_at":"2026-07-05T08:27:11.083324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:11.083324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRAM: Generative Retrieval Augmented Matching of Data Schemas in the Context of Data Security","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.DB","authors_text":"Austin Nevins, Davor Golac, Henrik Johnson, Luyang Kong, Nimish Amlathe, Patrick Song, Runhui Wang, Xuanqing Liu","submitted_at":"2024-06-04T01:08:00Z","abstract_excerpt":"Schema matching constitutes a pivotal phase in the data ingestion process for contemporary database systems. Its objective is to discern pairwise similarities between two sets of attributes, each associated with a distinct data table. This challenge emerges at the initial stages of data analytics, such as when incorporating a third-party table into existing databases to inform business insights. Given its significance in the realm of database systems, schema matching has been under investigation since the 2000s. This study revisits this foundational problem within the context of large language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01876","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/2406.01876/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":"2406.01876","created_at":"2026-07-05T08:27:11.083380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01876v1","created_at":"2026-07-05T08:27:11.083380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01876","created_at":"2026-07-05T08:27:11.083380+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHLNAP4TH74P","created_at":"2026-07-05T08:27:11.083380+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHLNAP4TH74PZWQV","created_at":"2026-07-05T08:27:11.083380+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHLNAP4T","created_at":"2026-07-05T08:27:11.083380+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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF","json":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF.json","graph_json":"https://pith.science/api/pith-number/KHLNAP4TH74PZWQVNID6SLHOKF/graph.json","events_json":"https://pith.science/api/pith-number/KHLNAP4TH74PZWQVNID6SLHOKF/events.json","paper":"https://pith.science/paper/KHLNAP4T"},"agent_actions":{"view_html":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF","download_json":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF.json","view_paper":"https://pith.science/paper/KHLNAP4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01876&json=true","fetch_graph":"https://pith.science/api/pith-number/KHLNAP4TH74PZWQVNID6SLHOKF/graph.json","fetch_events":"https://pith.science/api/pith-number/KHLNAP4TH74PZWQVNID6SLHOKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF/action/storage_attestation","attest_author":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF/action/author_attestation","sign_citation":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF/action/citation_signature","submit_replication":"https://pith.science/pith/KHLNAP4TH74PZWQVNID6SLHOKF/action/replication_record"}},"created_at":"2026-07-05T08:27:11.083380+00:00","updated_at":"2026-07-05T08:27:11.083380+00:00"}