{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V5PHTMD3BJIOBAU4TD3IUX3RUN","short_pith_number":"pith:V5PHTMD3","canonical_record":{"source":{"id":"2505.06579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-10T09:36:28Z","cross_cats_sorted":[],"title_canon_sha256":"9b389c0b8ad7cc0bb9e140c67301a609ac73cceead24586fba6b0f4d17d23b6d","abstract_canon_sha256":"ca418fd4b412a5044ec99c86e21de27cbec7ef3b399d559cc3ebbabf07729fa5"},"schema_version":"1.0"},"canonical_sha256":"af5e79b07b0a50e0829c98f68a5f71a3729dd9fb30a1514d762c6bcb0698aec8","source":{"kind":"arxiv","id":"2505.06579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06579","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06579v1","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06579","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"V5PHTMD3BJIO","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"V5PHTMD3BJIOBAU4","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"V5PHTMD3","created_at":"2026-07-05T11:01:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V5PHTMD3BJIOBAU4TD3IUX3RUN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-10T09:36:28Z","cross_cats_sorted":[],"title_canon_sha256":"9b389c0b8ad7cc0bb9e140c67301a609ac73cceead24586fba6b0f4d17d23b6d","abstract_canon_sha256":"ca418fd4b412a5044ec99c86e21de27cbec7ef3b399d559cc3ebbabf07729fa5"},"schema_version":"1.0"},"canonical_sha256":"af5e79b07b0a50e0829c98f68a5f71a3729dd9fb30a1514d762c6bcb0698aec8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:12.550350Z","signature_b64":"ib95adKqkXncvgz7UN6lfhJLalb7oz4IhI1ztzCz9gVLusMBfD6t3wUARdXxHImpiLwmY4v7QzGwSDTOpO1VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af5e79b07b0a50e0829c98f68a5f71a3729dd9fb30a1514d762c6bcb0698aec8","last_reissued_at":"2026-07-05T11:01:12.549822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:12.549822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06579","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiU0WsEWdegYlmdF7P8MBXb68+HTkHsT4tYddnBN+gGgH68Fm9n3vIfPqna9hKQjfy8b6LrMvW3kZ6v9bpuiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:59:00.459875Z"},"content_sha256":"2e3b67b58c2bc9579d68befce0bdba4d7279b945346aecd88f34071203f2f4af","schema_version":"1.0","event_id":"sha256:2e3b67b58c2bc9579d68befce0bdba4d7279b945346aecd88f34071203f2f4af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V5PHTMD3BJIOBAU4TD3IUX3RUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Chengshang Hou, Gang Xiong, Haozheng Luo, Jiahao Yu, Junzheng Shi, Xinjie Lin, Yangguang Shao","submitted_at":"2025-05-10T09:36:28Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite their impressive performance, LLMs are susceptible to hallucinations, which can lead to incorrect or misleading outputs. This is primarily due to the lack of up-to-date knowledge or domain-specific information. Retrieval-augmented generation (RAG) is a promising approach to mitigate hallucinations by leveraging external knowledge sources. However, the security of RAG systems has not been thoroughly studied. In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06579","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/2505.06579/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":"2026-07-05T11:01:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UAqSBxTN934VX8D63y3aWJO9NmHQmT0iOuvrs71JUA4zZwsajzrjUxG/JHRavdNNvy2r2axUAPuOIhg0LBvZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T09:59:00.460241Z"},"content_sha256":"82cfd618e9137037a0c017267268e2b48c1df89a08b8ca74f292de63026717d1","schema_version":"1.0","event_id":"sha256:82cfd618e9137037a0c017267268e2b48c1df89a08b8ca74f292de63026717d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5PHTMD3BJIOBAU4TD3IUX3RUN/bundle.json","state_url":"https://pith.science/pith/V5PHTMD3BJIOBAU4TD3IUX3RUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5PHTMD3BJIOBAU4TD3IUX3RUN/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":"2026-07-06T09:59:00Z","links":{"resolver":"https://pith.science/pith/V5PHTMD3BJIOBAU4TD3IUX3RUN","bundle":"https://pith.science/pith/V5PHTMD3BJIOBAU4TD3IUX3RUN/bundle.json","state":"https://pith.science/pith/V5PHTMD3BJIOBAU4TD3IUX3RUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5PHTMD3BJIOBAU4TD3IUX3RUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V5PHTMD3BJIOBAU4TD3IUX3RUN","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":"ca418fd4b412a5044ec99c86e21de27cbec7ef3b399d559cc3ebbabf07729fa5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-10T09:36:28Z","title_canon_sha256":"9b389c0b8ad7cc0bb9e140c67301a609ac73cceead24586fba6b0f4d17d23b6d"},"schema_version":"1.0","source":{"id":"2505.06579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06579","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06579v1","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06579","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"V5PHTMD3BJIO","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"V5PHTMD3BJIOBAU4","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"V5PHTMD3","created_at":"2026-07-05T11:01:12Z"}],"graph_snapshots":[{"event_id":"sha256:82cfd618e9137037a0c017267268e2b48c1df89a08b8ca74f292de63026717d1","target":"graph","created_at":"2026-07-05T11:01:12Z","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/2505.06579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite their impressive performance, LLMs are susceptible to hallucinations, which can lead to incorrect or misleading outputs. This is primarily due to the lack of up-to-date knowledge or domain-specific information. Retrieval-augmented generation (RAG) is a promising approach to mitigate hallucinations by leveraging external knowledge sources. However, the security of RAG systems has not been thoroughly studied. In this pap","authors_text":"Chengshang Hou, Gang Xiong, Haozheng Luo, Jiahao Yu, Junzheng Shi, Xinjie Lin, Yangguang Shao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-10T09:36:28Z","title":"POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06579","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":"sha256:2e3b67b58c2bc9579d68befce0bdba4d7279b945346aecd88f34071203f2f4af","target":"record","created_at":"2026-07-05T11:01:12Z","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":"ca418fd4b412a5044ec99c86e21de27cbec7ef3b399d559cc3ebbabf07729fa5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-05-10T09:36:28Z","title_canon_sha256":"9b389c0b8ad7cc0bb9e140c67301a609ac73cceead24586fba6b0f4d17d23b6d"},"schema_version":"1.0","source":{"id":"2505.06579","kind":"arxiv","version":1}},"canonical_sha256":"af5e79b07b0a50e0829c98f68a5f71a3729dd9fb30a1514d762c6bcb0698aec8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af5e79b07b0a50e0829c98f68a5f71a3729dd9fb30a1514d762c6bcb0698aec8","first_computed_at":"2026-07-05T11:01:12.549822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:12.549822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ib95adKqkXncvgz7UN6lfhJLalb7oz4IhI1ztzCz9gVLusMBfD6t3wUARdXxHImpiLwmY4v7QzGwSDTOpO1VAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:12.550350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e3b67b58c2bc9579d68befce0bdba4d7279b945346aecd88f34071203f2f4af","sha256:82cfd618e9137037a0c017267268e2b48c1df89a08b8ca74f292de63026717d1"],"state_sha256":"eadf4b6a1a678d337bf220c242969766afde264f19ffe7f003962ee34b538095"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g4E7IPRpzVCij2EX0HyKwnaZYV+5isbiUhd0LIFO7xBtwM9RkpdlCRbECCG0rOyx8IABMH3nJ0Ge1doswGgiDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T09:59:00.462150Z","bundle_sha256":"54283d2af75e84db5640e516844d6b520eb3be4cdae9d5c768651063b4fd2dac"}}