{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BBC72WKNNMJEQKVEGP3CFLGRDL","short_pith_number":"pith:BBC72WKN","schema_version":"1.0","canonical_sha256":"0845fd594d6b12482aa433f622acd11af15c507efdab210bc7d18c0f9ed88531","source":{"kind":"arxiv","id":"2410.05801","version":1},"attestation_state":"computed","paper":{"title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bolei He, Jinchang Luo, Lingyong Yan, Nuo Chen, Xinran He, Zhen-Hua Ling, Zhenkai Wei","submitted_at":"2024-10-08T08:34:54Z","abstract_excerpt":"Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) by incorporating extensive knowledge retrieved from external sources. However, such approach encounters some challenges: Firstly, the original queries may not be suitable for precise retrieval, resulting in erroneous contextual knowledge; Secondly, the language model can easily generate inconsistent answer with external references due to their knowledge boundary limitation. To address these issues, we propose the chain-of-verification (CoV-RAG) to enhance the external retrieval correctness and internal gen"},"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":"2410.05801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T08:34:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87c5a3ff03818dd0f51dd0b3739f25e4b06b00f2ccaf284af2a522ca0d4e0773","abstract_canon_sha256":"33feed5399867382c97c390f32834f91954e875e1b0572723a269a13e68bb7be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:25.017549Z","signature_b64":"AS344oXCc4/0OafqoAuy1JIH6SDM8vVeAvmxiApShvzBYKHQAGFeqfBYOulZLvutzP+DTowMP14wSqz7QeGsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0845fd594d6b12482aa433f622acd11af15c507efdab210bc7d18c0f9ed88531","last_reissued_at":"2026-07-05T09:17:25.017022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:25.017022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bolei He, Jinchang Luo, Lingyong Yan, Nuo Chen, Xinran He, Zhen-Hua Ling, Zhenkai Wei","submitted_at":"2024-10-08T08:34:54Z","abstract_excerpt":"Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) by incorporating extensive knowledge retrieved from external sources. However, such approach encounters some challenges: Firstly, the original queries may not be suitable for precise retrieval, resulting in erroneous contextual knowledge; Secondly, the language model can easily generate inconsistent answer with external references due to their knowledge boundary limitation. To address these issues, we propose the chain-of-verification (CoV-RAG) to enhance the external retrieval correctness and internal gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05801","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/2410.05801/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":"2410.05801","created_at":"2026-07-05T09:17:25.017074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05801v1","created_at":"2026-07-05T09:17:25.017074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05801","created_at":"2026-07-05T09:17:25.017074+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBC72WKNNMJE","created_at":"2026-07-05T09:17:25.017074+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBC72WKNNMJEQKVE","created_at":"2026-07-05T09:17:25.017074+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBC72WKN","created_at":"2026-07-05T09:17:25.017074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09666","citing_title":"Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL","json":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL.json","graph_json":"https://pith.science/api/pith-number/BBC72WKNNMJEQKVEGP3CFLGRDL/graph.json","events_json":"https://pith.science/api/pith-number/BBC72WKNNMJEQKVEGP3CFLGRDL/events.json","paper":"https://pith.science/paper/BBC72WKN"},"agent_actions":{"view_html":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL","download_json":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL.json","view_paper":"https://pith.science/paper/BBC72WKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05801&json=true","fetch_graph":"https://pith.science/api/pith-number/BBC72WKNNMJEQKVEGP3CFLGRDL/graph.json","fetch_events":"https://pith.science/api/pith-number/BBC72WKNNMJEQKVEGP3CFLGRDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL/action/storage_attestation","attest_author":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL/action/author_attestation","sign_citation":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL/action/citation_signature","submit_replication":"https://pith.science/pith/BBC72WKNNMJEQKVEGP3CFLGRDL/action/replication_record"}},"created_at":"2026-07-05T09:17:25.017074+00:00","updated_at":"2026-07-05T09:17:25.017074+00:00"}