{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CHWBJQKRSOKQJVBABHF4XGG7MV","short_pith_number":"pith:CHWBJQKR","canonical_record":{"source":{"id":"2406.14773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-20T22:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"2e2be7fbef9d929f5b55eb4abd43c2135899a01eee3911af6b6e1e20baf994f7","abstract_canon_sha256":"f87e1009292faa5dd8e6848d55e43aa54cf879bc91d7fb93cb2fdc85e8e8a618"},"schema_version":"1.0"},"canonical_sha256":"11ec14c151939504d42009cbcb98df65575ca877f89e125c54ed7c065cdf9ce7","source":{"kind":"arxiv","id":"2406.14773","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14773","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14773v2","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14773","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"CHWBJQKRSOKQ","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"CHWBJQKRSOKQJVBA","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"CHWBJQKR","created_at":"2026-07-05T10:17:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CHWBJQKRSOKQJVBABHF4XGG7MV","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-20T22:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"2e2be7fbef9d929f5b55eb4abd43c2135899a01eee3911af6b6e1e20baf994f7","abstract_canon_sha256":"f87e1009292faa5dd8e6848d55e43aa54cf879bc91d7fb93cb2fdc85e8e8a618"},"schema_version":"1.0"},"canonical_sha256":"11ec14c151939504d42009cbcb98df65575ca877f89e125c54ed7c065cdf9ce7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:09.179957Z","signature_b64":"QeuZF+8qUQHhm20ZwaOCNKni9uPGBONI7iteqnzbV+MqvXU+oBUPh7QNhz7cYpyYYWT1icjCbydY52rik9njCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11ec14c151939504d42009cbcb98df65575ca877f89e125c54ed7c065cdf9ce7","last_reissued_at":"2026-07-05T10:17:09.179478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:09.179478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14773","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4n3vQhXZniFBFOFa6RK0BY1kmLqMgFMWLGTWHfECMAKyX+IH47GpuUGUxDVsgB5OiAkbjwej+EkcY7M4yJrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:27:25.945062Z"},"content_sha256":"8ad37f2e6f5b2abfd5cd6e1d8d92c6c2475b39556dceb97fbee84b05d5a9fb6c","schema_version":"1.0","event_id":"sha256:8ad37f2e6f5b2abfd5cd6e1d8d92c6c2475b39556dceb97fbee84b05d5a9fb6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CHWBJQKRSOKQJVBABHF4XGG7MV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Hanqing Lu, Han Xu, Hui Liu, Jiankun Zhang, Jie Ren, Jiliang Tang, Pengfei He, Shenglai Zeng, Tianqi Zheng, Yue Xing","submitted_at":"2024-06-20T22:53:09Z","abstract_excerpt":"Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrieval process involves private data, RAG systems may face severe privacy risks, potentially leading to the leakage of sensitive information. To address this issue, we propose using synthetic data as a privacy-preserving alternative for the retrieval data. We propose SAGE, a novel two-stage synthetic data generation paradigm. In the stage-1, we employ an attribute-based extraction and generation approach to preserve key"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14773","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/2406.14773/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+L3mRg4jZ+Yl71uW/i4f2E7xNoNpR4m1xwoMXxW9gR6T5Mp/kC0jCmulWIWvGsixA/HfYz+qCWyqUxuDX8OoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:27:25.946141Z"},"content_sha256":"86154778f6d2f69be558aa3d8dad7806caf6fb79f229edd7105bc9b5a5045212","schema_version":"1.0","event_id":"sha256:86154778f6d2f69be558aa3d8dad7806caf6fb79f229edd7105bc9b5a5045212"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CHWBJQKRSOKQJVBABHF4XGG7MV/bundle.json","state_url":"https://pith.science/pith/CHWBJQKRSOKQJVBABHF4XGG7MV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CHWBJQKRSOKQJVBABHF4XGG7MV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T09:27:25Z","links":{"resolver":"https://pith.science/pith/CHWBJQKRSOKQJVBABHF4XGG7MV","bundle":"https://pith.science/pith/CHWBJQKRSOKQJVBABHF4XGG7MV/bundle.json","state":"https://pith.science/pith/CHWBJQKRSOKQJVBABHF4XGG7MV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CHWBJQKRSOKQJVBABHF4XGG7MV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CHWBJQKRSOKQJVBABHF4XGG7MV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f87e1009292faa5dd8e6848d55e43aa54cf879bc91d7fb93cb2fdc85e8e8a618","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-20T22:53:09Z","title_canon_sha256":"2e2be7fbef9d929f5b55eb4abd43c2135899a01eee3911af6b6e1e20baf994f7"},"schema_version":"1.0","source":{"id":"2406.14773","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14773","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14773v2","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14773","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"CHWBJQKRSOKQ","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"CHWBJQKRSOKQJVBA","created_at":"2026-07-05T10:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"CHWBJQKR","created_at":"2026-07-05T10:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:86154778f6d2f69be558aa3d8dad7806caf6fb79f229edd7105bc9b5a5045212","target":"graph","created_at":"2026-07-05T10:17:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.14773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrieval process involves private data, RAG systems may face severe privacy risks, potentially leading to the leakage of sensitive information. To address this issue, we propose using synthetic data as a privacy-preserving alternative for the retrieval data. We propose SAGE, a novel two-stage synthetic data generation paradigm. In the stage-1, we employ an attribute-based extraction and generation approach to preserve key","authors_text":"Hanqing Lu, Han Xu, Hui Liu, Jiankun Zhang, Jie Ren, Jiliang Tang, Pengfei He, Shenglai Zeng, Tianqi Zheng, Yue Xing","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-20T22:53:09Z","title":"Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14773","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8ad37f2e6f5b2abfd5cd6e1d8d92c6c2475b39556dceb97fbee84b05d5a9fb6c","target":"record","created_at":"2026-07-05T10:17:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f87e1009292faa5dd8e6848d55e43aa54cf879bc91d7fb93cb2fdc85e8e8a618","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-20T22:53:09Z","title_canon_sha256":"2e2be7fbef9d929f5b55eb4abd43c2135899a01eee3911af6b6e1e20baf994f7"},"schema_version":"1.0","source":{"id":"2406.14773","kind":"arxiv","version":2}},"canonical_sha256":"11ec14c151939504d42009cbcb98df65575ca877f89e125c54ed7c065cdf9ce7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11ec14c151939504d42009cbcb98df65575ca877f89e125c54ed7c065cdf9ce7","first_computed_at":"2026-07-05T10:17:09.179478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:09.179478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QeuZF+8qUQHhm20ZwaOCNKni9uPGBONI7iteqnzbV+MqvXU+oBUPh7QNhz7cYpyYYWT1icjCbydY52rik9njCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:09.179957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14773","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ad37f2e6f5b2abfd5cd6e1d8d92c6c2475b39556dceb97fbee84b05d5a9fb6c","sha256:86154778f6d2f69be558aa3d8dad7806caf6fb79f229edd7105bc9b5a5045212"],"state_sha256":"350bac3e63545960445182fa18dccaf2a2dba5a4ad15caccb53961821425fa80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKr9qM05p47cwHMf7PXRjzhyKVp+p5igXWmKcRMw/ZKTGVE1WkYSY5x73s5GW+U+xWjUCVMXTGp0OySS30DJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:27:25.952988Z","bundle_sha256":"59825f9f47546c1be919ab9e55a7a6361e9ca75f228cb588bbe49995556cb2d3"}}