{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LBP7OHRXU45BNBWOENTHXBCZYX","short_pith_number":"pith:LBP7OHRX","schema_version":"1.0","canonical_sha256":"585ff71e37a73a1686ce23667b8459c5c28748155445e3c7216aeba920d2dd56","source":{"kind":"arxiv","id":"2509.04502","version":1},"attestation_state":"computed","paper":{"title":"VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hengyuan Zhao, Kaiyou Song, LinJiang Huang, Qingpei Guo, Qixin Sun, Si Liu, Xiaolin Hu, Yilin Li, Ziqin Wang","submitted_at":"2025-09-02T04:49:51Z","abstract_excerpt":"Retrieval Augmented Generation enhances the response accuracy of Large Language Models (LLMs) by integrating retrieval and generation modules with external knowledge, demonstrating particular strength in real-time queries and Visual Question Answering tasks. However, the effectiveness of RAG is frequently hindered by the precision of the retriever: many retrieved samples fed into the generation phase are irrelevant or misleading, posing a critical bottleneck to LLMs' performance. To address this challenge, we introduce VaccineRAG, a novel Chain-of-Thought-based retrieval-augmented generation d"},"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":"2509.04502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T04:49:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc186c4ba5e7f8aa466e00936001a9b10ea47a9ffddeb6dafb56657db08400fc","abstract_canon_sha256":"e6c50b993382489052ba4cbd2ccde2cdb3be81e2a8fcef03bf644f224bb37d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:24.134970Z","signature_b64":"qeYtRVWZoi1e98Tq1zUSPZgek7ftYv1rPamQlRb8LHIsufnbGxYdjItejk0pLPPPpMxEiFRs+upzP56MGClBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"585ff71e37a73a1686ce23667b8459c5c28748155445e3c7216aeba920d2dd56","last_reissued_at":"2026-07-05T12:05:24.134479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:24.134479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hengyuan Zhao, Kaiyou Song, LinJiang Huang, Qingpei Guo, Qixin Sun, Si Liu, Xiaolin Hu, Yilin Li, Ziqin Wang","submitted_at":"2025-09-02T04:49:51Z","abstract_excerpt":"Retrieval Augmented Generation enhances the response accuracy of Large Language Models (LLMs) by integrating retrieval and generation modules with external knowledge, demonstrating particular strength in real-time queries and Visual Question Answering tasks. However, the effectiveness of RAG is frequently hindered by the precision of the retriever: many retrieved samples fed into the generation phase are irrelevant or misleading, posing a critical bottleneck to LLMs' performance. To address this challenge, we introduce VaccineRAG, a novel Chain-of-Thought-based retrieval-augmented generation d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04502","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/2509.04502/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":"2509.04502","created_at":"2026-07-05T12:05:24.134536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04502v1","created_at":"2026-07-05T12:05:24.134536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04502","created_at":"2026-07-05T12:05:24.134536+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBP7OHRXU45B","created_at":"2026-07-05T12:05:24.134536+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBP7OHRXU45BNBWO","created_at":"2026-07-05T12:05:24.134536+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBP7OHRX","created_at":"2026-07-05T12:05:24.134536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX","json":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX.json","graph_json":"https://pith.science/api/pith-number/LBP7OHRXU45BNBWOENTHXBCZYX/graph.json","events_json":"https://pith.science/api/pith-number/LBP7OHRXU45BNBWOENTHXBCZYX/events.json","paper":"https://pith.science/paper/LBP7OHRX"},"agent_actions":{"view_html":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX","download_json":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX.json","view_paper":"https://pith.science/paper/LBP7OHRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04502&json=true","fetch_graph":"https://pith.science/api/pith-number/LBP7OHRXU45BNBWOENTHXBCZYX/graph.json","fetch_events":"https://pith.science/api/pith-number/LBP7OHRXU45BNBWOENTHXBCZYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX/action/storage_attestation","attest_author":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX/action/author_attestation","sign_citation":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX/action/citation_signature","submit_replication":"https://pith.science/pith/LBP7OHRXU45BNBWOENTHXBCZYX/action/replication_record"}},"created_at":"2026-07-05T12:05:24.134536+00:00","updated_at":"2026-07-05T12:05:24.134536+00:00"}