{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TFCULT3ZGTKGQXN625NHYFIBCQ","short_pith_number":"pith:TFCULT3Z","schema_version":"1.0","canonical_sha256":"994545cf7934d4685dbed75a7c1501141722b862771c9c06ac09ada24895986a","source":{"kind":"arxiv","id":"2502.06872","version":1},"attestation_state":"computed","paper":{"title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Ni, Erik Blasch, Franck Dernoncourt, Krishnaram Kenthapadi, Leyao Wang, Luna Dong, Md Mehrab Tanjim, Meng Jiang, Nesreen Ahmed, Qingkai Zeng, Ryan Rossi, Tyler Derr, Wenqi Fan, Xiaorui Liu, Xueqi Cheng, Yinglong Xia, Yongjia Lei, Yu Wang, Yuying Zhao, Zheyuan Liu","submitted_at":"2025-02-08T06:50:47Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is an advanced technique designed to address the challenges of Artificial Intelligence-Generated Content (AIGC). By integrating context retrieval into content generation, RAG provides reliable and up-to-date external knowledge, reduces hallucinations, and ensures relevant context across a wide range of tasks. However, despite RAG's success and potential, recent studies have shown that the RAG paradigm also introduces new risks, including robustness issues, privacy concerns, adversarial attacks, and accountability issues. Addressing these risks is critical f"},"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":"2502.06872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T06:50:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b3e7ea7809a3c9376e47f0694e41a3746b6bda1206a5ef90a1bfb247d4033e8","abstract_canon_sha256":"267c7c86f434a57b3e72a417874cca8581743413679c3805849c92fc05f3d9cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:29.322757Z","signature_b64":"msH/96UY5XszyrZMba/pm9Nq2BaQkR/l7oMGTnm4EtFXVglgRMpnu0VU9jIaUqcnZ4bwnLsyAGCCWTO//RZlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994545cf7934d4685dbed75a7c1501141722b862771c9c06ac09ada24895986a","last_reissued_at":"2026-07-05T10:12:29.322264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:29.322264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Ni, Erik Blasch, Franck Dernoncourt, Krishnaram Kenthapadi, Leyao Wang, Luna Dong, Md Mehrab Tanjim, Meng Jiang, Nesreen Ahmed, Qingkai Zeng, Ryan Rossi, Tyler Derr, Wenqi Fan, Xiaorui Liu, Xueqi Cheng, Yinglong Xia, Yongjia Lei, Yu Wang, Yuying Zhao, Zheyuan Liu","submitted_at":"2025-02-08T06:50:47Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is an advanced technique designed to address the challenges of Artificial Intelligence-Generated Content (AIGC). By integrating context retrieval into content generation, RAG provides reliable and up-to-date external knowledge, reduces hallucinations, and ensures relevant context across a wide range of tasks. However, despite RAG's success and potential, recent studies have shown that the RAG paradigm also introduces new risks, including robustness issues, privacy concerns, adversarial attacks, and accountability issues. Addressing these risks is critical f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06872","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/2502.06872/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":"2502.06872","created_at":"2026-07-05T10:12:29.322324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06872v1","created_at":"2026-07-05T10:12:29.322324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06872","created_at":"2026-07-05T10:12:29.322324+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFCULT3ZGTKG","created_at":"2026-07-05T10:12:29.322324+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFCULT3ZGTKGQXN6","created_at":"2026-07-05T10:12:29.322324+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFCULT3Z","created_at":"2026-07-05T10:12:29.322324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06641","citing_title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25533","citing_title":"Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22728","citing_title":"When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07783","citing_title":"Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01040","citing_title":"As It Was: Aligning LLM Search Evaluation with Historical User Preferences","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25039","citing_title":"AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13340","citing_title":"Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05318","citing_title":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2507.03724","citing_title":"MemOS: A Memory OS for AI System","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10253","citing_title":"Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11141","citing_title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08304","citing_title":"Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ","json":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ.json","graph_json":"https://pith.science/api/pith-number/TFCULT3ZGTKGQXN625NHYFIBCQ/graph.json","events_json":"https://pith.science/api/pith-number/TFCULT3ZGTKGQXN625NHYFIBCQ/events.json","paper":"https://pith.science/paper/TFCULT3Z"},"agent_actions":{"view_html":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ","download_json":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ.json","view_paper":"https://pith.science/paper/TFCULT3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06872&json=true","fetch_graph":"https://pith.science/api/pith-number/TFCULT3ZGTKGQXN625NHYFIBCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TFCULT3ZGTKGQXN625NHYFIBCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ/action/storage_attestation","attest_author":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ/action/author_attestation","sign_citation":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ/action/citation_signature","submit_replication":"https://pith.science/pith/TFCULT3ZGTKGQXN625NHYFIBCQ/action/replication_record"}},"created_at":"2026-07-05T10:12:29.322324+00:00","updated_at":"2026-07-05T10:12:29.322324+00:00"}