{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FCQGKJ5UOTTYEY2SUFKTIEECPW","short_pith_number":"pith:FCQGKJ5U","schema_version":"1.0","canonical_sha256":"28a06527b474e7826352a1553410827da9d028f10e38d8114efe5df55e644d80","source":{"kind":"arxiv","id":"2410.13272","version":1},"attestation_state":"computed","paper":{"title":"FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CR","authors_text":"Dongfang Zhao","submitted_at":"2024-10-17T06:57:29Z","abstract_excerpt":"This paper introduces \\textit{Federated Retrieval-Augmented Generation (FRAG)}, a novel database management paradigm tailored for the growing needs of retrieval-augmented generation (RAG) systems, which are increasingly powered by large-language models (LLMs). FRAG enables mutually-distrusted parties to collaboratively perform Approximate $k$-Nearest Neighbor (ANN) searches on encrypted query vectors and encrypted data stored in distributed vector databases, all while ensuring that no party can gain any knowledge about the queries or data of others. Achieving this paradigm presents two key cha"},"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":"2410.13272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-17T06:57:29Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"99e39eacef405882788ebb4dfeded4702928d4f4bb33911f7e96367960716576","abstract_canon_sha256":"620337a2dffb26c4a3ee832db4847380fee5e334ea4e1cabd22496501968d5e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:57.930973Z","signature_b64":"VmNHQOJjgbDLnUjbNdPE/4tFBheHXXGjN0LeebBUD6R+sOjjXmtDk57BXd4kl+JStRbRFooJs1OIAnIe8ad4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a06527b474e7826352a1553410827da9d028f10e38d8114efe5df55e644d80","last_reissued_at":"2026-07-05T09:21:57.930525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:57.930525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CR","authors_text":"Dongfang Zhao","submitted_at":"2024-10-17T06:57:29Z","abstract_excerpt":"This paper introduces \\textit{Federated Retrieval-Augmented Generation (FRAG)}, a novel database management paradigm tailored for the growing needs of retrieval-augmented generation (RAG) systems, which are increasingly powered by large-language models (LLMs). FRAG enables mutually-distrusted parties to collaboratively perform Approximate $k$-Nearest Neighbor (ANN) searches on encrypted query vectors and encrypted data stored in distributed vector databases, all while ensuring that no party can gain any knowledge about the queries or data of others. Achieving this paradigm presents two key cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13272","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/2410.13272/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":"2410.13272","created_at":"2026-07-05T09:21:57.930574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13272v1","created_at":"2026-07-05T09:21:57.930574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13272","created_at":"2026-07-05T09:21:57.930574+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCQGKJ5UOTTY","created_at":"2026-07-05T09:21:57.930574+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCQGKJ5UOTTYEY2S","created_at":"2026-07-05T09:21:57.930574+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCQGKJ5U","created_at":"2026-07-05T09:21:57.930574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.19280","citing_title":"Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26525","citing_title":"PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW","json":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW.json","graph_json":"https://pith.science/api/pith-number/FCQGKJ5UOTTYEY2SUFKTIEECPW/graph.json","events_json":"https://pith.science/api/pith-number/FCQGKJ5UOTTYEY2SUFKTIEECPW/events.json","paper":"https://pith.science/paper/FCQGKJ5U"},"agent_actions":{"view_html":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW","download_json":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW.json","view_paper":"https://pith.science/paper/FCQGKJ5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13272&json=true","fetch_graph":"https://pith.science/api/pith-number/FCQGKJ5UOTTYEY2SUFKTIEECPW/graph.json","fetch_events":"https://pith.science/api/pith-number/FCQGKJ5UOTTYEY2SUFKTIEECPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW/action/storage_attestation","attest_author":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW/action/author_attestation","sign_citation":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW/action/citation_signature","submit_replication":"https://pith.science/pith/FCQGKJ5UOTTYEY2SUFKTIEECPW/action/replication_record"}},"created_at":"2026-07-05T09:21:57.930574+00:00","updated_at":"2026-07-05T09:21:57.930574+00:00"}