{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OEWIM2OPDD4XUT7WNJT2WZ3WEF","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":"b6478fefe321cca3b3f9893cfdc700b3a62cb982bd0a0b22f9ef7c1a0216e17c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-15T04:56:45Z","title_canon_sha256":"5ebae0a9a63ccad872673983b4352b99b54b8d06b60f72a5ac498276ad65e298"},"schema_version":"1.0","source":{"id":"2502.10673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10673","created_at":"2026-07-05T10:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10673v1","created_at":"2026-07-05T10:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10673","created_at":"2026-07-05T10:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"OEWIM2OPDD4X","created_at":"2026-07-05T10:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"OEWIM2OPDD4XUT7W","created_at":"2026-07-05T10:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"OEWIM2OP","created_at":"2026-07-05T10:14:56Z"}],"graph_snapshots":[{"event_id":"sha256:dc24acd9dd85e6b65b31e2ee301741c5fd1cec209f0050e071e7e89d36e9a01c","target":"graph","created_at":"2026-07-05T10:14:56Z","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/2502.10673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become an effective method for enhancing large language models (LLMs) with up-to-date knowledge. However, it poses a significant risk of IP infringement, as IP datasets may be incorporated into the knowledge database by malicious Retrieval-Augmented LLMs (RA-LLMs) without authorization. To protect the rights of the dataset owner, an effective dataset membership inference algorithm for RA-LLMs is needed. In this work, we introduce a novel approach to safeguard the ownership of text datasets and effectively detect unauthorized use by the RA-LLMs. Our appr","authors_text":"Dawn Song, Xuandong Zhao, Yepeng Liu, Yuheng Bu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-15T04:56:45Z","title":"Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10673","kind":"arxiv","version":1},"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":"sha256:7208e9f53789dba9da3ddee9b600703649d097b7014ace52fc205c92953c8fa4","target":"record","created_at":"2026-07-05T10:14:56Z","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":"b6478fefe321cca3b3f9893cfdc700b3a62cb982bd0a0b22f9ef7c1a0216e17c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-15T04:56:45Z","title_canon_sha256":"5ebae0a9a63ccad872673983b4352b99b54b8d06b60f72a5ac498276ad65e298"},"schema_version":"1.0","source":{"id":"2502.10673","kind":"arxiv","version":1}},"canonical_sha256":"712c8669cf18f97a4ff66a67ab6776215844ca9b9462265b424d1c8024050109","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"712c8669cf18f97a4ff66a67ab6776215844ca9b9462265b424d1c8024050109","first_computed_at":"2026-07-05T10:14:56.157144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:56.157144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SEW/vue3pR6Aaee0hjUr2p9iujzmcQfSt4YBksUOzISywUFi3orp6DIxVvdW0JhoBhdX5B5aH/ZInbQ0Y4JSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:56.157630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7208e9f53789dba9da3ddee9b600703649d097b7014ace52fc205c92953c8fa4","sha256:dc24acd9dd85e6b65b31e2ee301741c5fd1cec209f0050e071e7e89d36e9a01c"],"state_sha256":"bc8d766315fe823fd69f1657dc61e16d4daf7aa771ee746200230e980cf02ccb"}