{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V7FKHI6IKL3WWJZPUMSFEZBDLA","short_pith_number":"pith:V7FKHI6I","schema_version":"1.0","canonical_sha256":"afcaa3a3c852f76b272fa3245264235835b568ad6c1212a3ae81885c4fba7646","source":{"kind":"arxiv","id":"2412.12775","version":1},"attestation_state":"computed","paper":{"title":"RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.IR","authors_text":"Junyang Wang, Lan Zhang, Mu Yuan, Yihang Cheng, Yunhao Yao","submitted_at":"2024-12-17T10:36:52Z","abstract_excerpt":"Retrieval-augmented generation (RAG) improves the service quality of large language models by retrieving relevant documents from credible literature and integrating them into the context of the user query. Recently, the rise of the cloud RAG service has made it possible for users to query relevant documents conveniently. However, directly sending queries to the cloud brings potential privacy leakage. In this paper, we are the first to formally define the privacy-preserving cloud RAG service to protect the user query and propose RemoteRAG as a solution regarding privacy, efficiency, and accurac"},"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":"2412.12775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T10:36:52Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"84a67cb8eb974e5080ac5dc36db2c3dc99a8a0d3112c7451129a5ce1bff2ef5a","abstract_canon_sha256":"5f28d17a76e969759d8b8cf3ad3f61162f0c0eed2a2b68c6c6c68f79befb4c30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:20.488861Z","signature_b64":"jt0pajUaPINJlY+HRkocf8DvwIg877RCt+GOYooXpp6/aCXix61yDqt6wZ2pT7AlrZbZKxrhGV0/F0x/inLbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afcaa3a3c852f76b272fa3245264235835b568ad6c1212a3ae81885c4fba7646","last_reissued_at":"2026-07-05T09:50:20.488444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:20.488444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.IR","authors_text":"Junyang Wang, Lan Zhang, Mu Yuan, Yihang Cheng, Yunhao Yao","submitted_at":"2024-12-17T10:36:52Z","abstract_excerpt":"Retrieval-augmented generation (RAG) improves the service quality of large language models by retrieving relevant documents from credible literature and integrating them into the context of the user query. Recently, the rise of the cloud RAG service has made it possible for users to query relevant documents conveniently. However, directly sending queries to the cloud brings potential privacy leakage. In this paper, we are the first to formally define the privacy-preserving cloud RAG service to protect the user query and propose RemoteRAG as a solution regarding privacy, efficiency, and accurac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12775","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/2412.12775/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":"2412.12775","created_at":"2026-07-05T09:50:20.488499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12775v1","created_at":"2026-07-05T09:50:20.488499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12775","created_at":"2026-07-05T09:50:20.488499+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7FKHI6IKL3W","created_at":"2026-07-05T09:50:20.488499+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7FKHI6IKL3WWJZP","created_at":"2026-07-05T09:50:20.488499+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7FKHI6I","created_at":"2026-07-05T09:50:20.488499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16731","citing_title":"Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges","ref_index":247,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA","json":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA.json","graph_json":"https://pith.science/api/pith-number/V7FKHI6IKL3WWJZPUMSFEZBDLA/graph.json","events_json":"https://pith.science/api/pith-number/V7FKHI6IKL3WWJZPUMSFEZBDLA/events.json","paper":"https://pith.science/paper/V7FKHI6I"},"agent_actions":{"view_html":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA","download_json":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA.json","view_paper":"https://pith.science/paper/V7FKHI6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12775&json=true","fetch_graph":"https://pith.science/api/pith-number/V7FKHI6IKL3WWJZPUMSFEZBDLA/graph.json","fetch_events":"https://pith.science/api/pith-number/V7FKHI6IKL3WWJZPUMSFEZBDLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA/action/storage_attestation","attest_author":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA/action/author_attestation","sign_citation":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA/action/citation_signature","submit_replication":"https://pith.science/pith/V7FKHI6IKL3WWJZPUMSFEZBDLA/action/replication_record"}},"created_at":"2026-07-05T09:50:20.488499+00:00","updated_at":"2026-07-05T09:50:20.488499+00:00"}