{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GMQNTUQEBQXD4IDBN4OWW7FZKY","short_pith_number":"pith:GMQNTUQE","schema_version":"1.0","canonical_sha256":"3320d9d2040c2e3e20616f1d6b7cb956061bef79280466c76dc5b354d0ca80ba","source":{"kind":"arxiv","id":"2506.09200","version":2},"attestation_state":"computed","paper":{"title":"FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex Cheung, Amandeep Singh, David B. Emerson, Izuki Matsuba, Marcelo Lotif, Ravi Theja, Val Andrei Fajardo, Veronica Chatrath","submitted_at":"2025-06-10T19:42:07Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems have been shown to be effective in addressing many of the drawbacks of relying solely on the parametric memory of large language models. Recent work has demonstrated that RAG systems can be improved via fine-tuning of their retriever and generator models. In this work, we introduce FedRAG, a framework for fine-tuning RAG systems across centralized and federated architectures. FedRAG supports state-of-the-art fine-tuning methods, offering a simple and intuitive interface and a seamless conversion from centralized to federated training tasks. FedRAG i"},"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":"2506.09200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T19:42:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"453c6b492684fce54da7deb979568d298e7e886ae736675b56bf9002a31f3ede","abstract_canon_sha256":"cda50cb16862bd959e7ec57d0bb5895f263d6808e10f072b5c0c13fa46023c5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:14.504004Z","signature_b64":"lKhQ8F1mPjOXSvFi5Xi+cIDf3HXPnb5bSTLgVCirl0bI6wI8hncUsFhhLogcco7+mG9q7QLiYNrdg3c650uXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3320d9d2040c2e3e20616f1d6b7cb956061bef79280466c76dc5b354d0ca80ba","last_reissued_at":"2026-07-05T11:20:14.503470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:14.503470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex Cheung, Amandeep Singh, David B. Emerson, Izuki Matsuba, Marcelo Lotif, Ravi Theja, Val Andrei Fajardo, Veronica Chatrath","submitted_at":"2025-06-10T19:42:07Z","abstract_excerpt":"Retrieval-augmented generation (RAG) systems have been shown to be effective in addressing many of the drawbacks of relying solely on the parametric memory of large language models. Recent work has demonstrated that RAG systems can be improved via fine-tuning of their retriever and generator models. In this work, we introduce FedRAG, a framework for fine-tuning RAG systems across centralized and federated architectures. FedRAG supports state-of-the-art fine-tuning methods, offering a simple and intuitive interface and a seamless conversion from centralized to federated training tasks. FedRAG i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09200","kind":"arxiv","version":2},"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/2506.09200/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":"2506.09200","created_at":"2026-07-05T11:20:14.503530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09200v2","created_at":"2026-07-05T11:20:14.503530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09200","created_at":"2026-07-05T11:20:14.503530+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMQNTUQEBQXD","created_at":"2026-07-05T11:20:14.503530+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMQNTUQEBQXD4IDB","created_at":"2026-07-05T11:20:14.503530+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMQNTUQE","created_at":"2026-07-05T11:20:14.503530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25533","citing_title":"Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29652","citing_title":"As We May Search","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY","json":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY.json","graph_json":"https://pith.science/api/pith-number/GMQNTUQEBQXD4IDBN4OWW7FZKY/graph.json","events_json":"https://pith.science/api/pith-number/GMQNTUQEBQXD4IDBN4OWW7FZKY/events.json","paper":"https://pith.science/paper/GMQNTUQE"},"agent_actions":{"view_html":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY","download_json":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY.json","view_paper":"https://pith.science/paper/GMQNTUQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09200&json=true","fetch_graph":"https://pith.science/api/pith-number/GMQNTUQEBQXD4IDBN4OWW7FZKY/graph.json","fetch_events":"https://pith.science/api/pith-number/GMQNTUQEBQXD4IDBN4OWW7FZKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY/action/storage_attestation","attest_author":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY/action/author_attestation","sign_citation":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY/action/citation_signature","submit_replication":"https://pith.science/pith/GMQNTUQEBQXD4IDBN4OWW7FZKY/action/replication_record"}},"created_at":"2026-07-05T11:20:14.503530+00:00","updated_at":"2026-07-05T11:20:14.503530+00:00"}