{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TKTUBDUL7IQHB4JXUFDFJ5PEYL","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":"acd642dd5fe2d155cb11d1bfb135b94a52e6d2bad3221ee8d96ee385926dcd9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:58:41Z","title_canon_sha256":"cb553a97b75de55a697b69e93cedf388b32979c58d2636da7aa2006512382329"},"schema_version":"1.0","source":{"id":"2507.18202","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18202","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18202v1","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18202","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"TKTUBDUL7IQH","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_16","alias_value":"TKTUBDUL7IQHB4JX","created_at":"2026-07-05T11:42:43Z"},{"alias_kind":"pith_short_8","alias_value":"TKTUBDUL","created_at":"2026-07-05T11:42:43Z"}],"graph_snapshots":[{"event_id":"sha256:2542ac3c031e13859bed1229f89c7750ef4e6298566354f2a3ccc75ae0131f9e","target":"graph","created_at":"2026-07-05T11:42:43Z","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/2507.18202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by providing external knowledge for accurate and up-to-date responses. However, this reliance on external sources exposes a security risk, attackers can inject poisoned documents into the knowledge base to steer the generation process toward harmful or misleading outputs. In this paper, we propose Gradient-based Masked Token Probability (GMTP), a novel defense method to detect and filter out adversarially crafted documents. Specifically, GMTP identifies high-impact tokens by examining gradients of the retriever's simila","authors_text":"Gary Geunbae Lee, Jonghwi Kim, San Kim, Yejin Jeon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:58:41Z","title":"Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18202","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":"sha256:34afaf14665c0cab4147cbde613ce7af9932c928200ad4e17ff5123a2ed783fa","target":"record","created_at":"2026-07-05T11:42:43Z","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":"acd642dd5fe2d155cb11d1bfb135b94a52e6d2bad3221ee8d96ee385926dcd9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T08:58:41Z","title_canon_sha256":"cb553a97b75de55a697b69e93cedf388b32979c58d2636da7aa2006512382329"},"schema_version":"1.0","source":{"id":"2507.18202","kind":"arxiv","version":1}},"canonical_sha256":"9aa7408e8bfa2070f137a14654f5e4c2d350c8883f87d0c83207ed5eea069fe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9aa7408e8bfa2070f137a14654f5e4c2d350c8883f87d0c83207ed5eea069fe4","first_computed_at":"2026-07-05T11:42:43.569932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:43.569932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bIsiE8CFP4sFB+sR3H8a72hyLLH6wg4rIVfez1giWBqgih2z9up00loU8ZIcbYNYy3ZEGqc+1RpVhkOpOceQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:43.570354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18202","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34afaf14665c0cab4147cbde613ce7af9932c928200ad4e17ff5123a2ed783fa","sha256:2542ac3c031e13859bed1229f89c7750ef4e6298566354f2a3ccc75ae0131f9e"],"state_sha256":"40e2d2adb323698a02729e241eb9433f84361f7a91154c02d4eab9cc21dbade3"}