{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CEZU4Y6H7IPMNCQMC3HQBSZBSZ","short_pith_number":"pith:CEZU4Y6H","schema_version":"1.0","canonical_sha256":"11334e63c7fa1ec68a0c16cf00cb219657e480d41adf792c56bef8df44deaa0b","source":{"kind":"arxiv","id":"2410.07176","version":2},"attestation_state":"computed","paper":{"title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fei Wang, Jiefeng Chen, Ruoxi Sun, Sercan \\\"O. Ar{\\i}k, Xingchen Wan","submitted_at":"2024-10-09T17:59:58Z","abstract_excerpt":"Retrieval augmented generation (RAG), while effectively integrating external knowledge to address the inherent limitations of large language models (LLMs), can be hindered by imperfect retrieval that contain irrelevant, misleading, or even malicious information. Previous studies have rarely connected the behavior of RAG through joint analysis, particularly regarding error propagation coming from imperfect retrieval and potential conflicts between LLMs' internal knowledge and external sources. Through comprehensive and controlled analyses under realistic conditions, we find that imperfect retri"},"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":"2410.07176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T17:59:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9fc228901f8612543bf911b0240ccc17a6737569b7f2f0460c7420cb5017cdf4","abstract_canon_sha256":"fe375b61fc267a1b3b6805097df695a26a1f32985e9d49dfc1bf9b01b6bf8b01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:13.856131Z","signature_b64":"iE47huyZuLLAaHXZHMgQIe9IQa2CwfzdTpkfgU3xDzc3fqRAntq+bFFvXSw6Ngnv5eP3FZzKsa0HwPnvfi84Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11334e63c7fa1ec68a0c16cf00cb219657e480d41adf792c56bef8df44deaa0b","last_reissued_at":"2026-07-05T11:13:13.855526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:13.855526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fei Wang, Jiefeng Chen, Ruoxi Sun, Sercan \\\"O. Ar{\\i}k, Xingchen Wan","submitted_at":"2024-10-09T17:59:58Z","abstract_excerpt":"Retrieval augmented generation (RAG), while effectively integrating external knowledge to address the inherent limitations of large language models (LLMs), can be hindered by imperfect retrieval that contain irrelevant, misleading, or even malicious information. Previous studies have rarely connected the behavior of RAG through joint analysis, particularly regarding error propagation coming from imperfect retrieval and potential conflicts between LLMs' internal knowledge and external sources. Through comprehensive and controlled analyses under realistic conditions, we find that imperfect retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07176","kind":"arxiv","version":2},"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/2410.07176/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":"2410.07176","created_at":"2026-07-05T11:13:13.855607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07176v2","created_at":"2026-07-05T11:13:13.855607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07176","created_at":"2026-07-05T11:13:13.855607+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEZU4Y6H7IPM","created_at":"2026-07-05T11:13:13.855607+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEZU4Y6H7IPMNCQM","created_at":"2026-07-05T11:13:13.855607+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEZU4Y6H","created_at":"2026-07-05T11:13:13.855607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00012","citing_title":"PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01581","citing_title":"Agent System Operations: Categorization, Challenges, and Future Directions","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14473","citing_title":"Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2506.00077","citing_title":"Gaussian mixture models as a proxy for interacting language models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00798","citing_title":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11122","citing_title":"Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14473","citing_title":"Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05244","citing_title":"Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ","json":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ.json","graph_json":"https://pith.science/api/pith-number/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/graph.json","events_json":"https://pith.science/api/pith-number/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/events.json","paper":"https://pith.science/paper/CEZU4Y6H"},"agent_actions":{"view_html":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ","download_json":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ.json","view_paper":"https://pith.science/paper/CEZU4Y6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07176&json=true","fetch_graph":"https://pith.science/api/pith-number/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/action/storage_attestation","attest_author":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/action/author_attestation","sign_citation":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/action/citation_signature","submit_replication":"https://pith.science/pith/CEZU4Y6H7IPMNCQMC3HQBSZBSZ/action/replication_record"}},"created_at":"2026-07-05T11:13:13.855607+00:00","updated_at":"2026-07-05T11:13:13.855607+00:00"}