{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZX3PLUPHLY4EOTHP6RMOPF2EUB","short_pith_number":"pith:ZX3PLUPH","schema_version":"1.0","canonical_sha256":"cdf6f5d1e75e38474ceff458e79744a07481c841ed85f63a981789e7142afdcd","source":{"kind":"arxiv","id":"2311.07838","version":3},"attestation_state":"computed","paper":{"title":"LLatrieval: LLM-Verified Retrieval for Verifiable Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Changtai Zhu, Linyang Li, Tianxiang Sun, Xiaonan Li, Xipeng Qiu, Zhangyue Yin","submitted_at":"2023-11-14T01:38:02Z","abstract_excerpt":"Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM's output more reliable. Retrieval plays a crucial role in verifiable generation. Specifically, the retrieved documents not only supplement knowledge to help the LLM generate correct answers, but also serve as supporting evidence for the user to verify the LLM's output. However, the widely used retrievers become the bottleneck of the entire pipeline and limit the overall performance. Their capabilities are usually inferi"},"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":"2311.07838","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T01:38:02Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"3e0de16b5cf87bf1582d53a7df2226834bd51da880bfe0791597be1e0d16c024","abstract_canon_sha256":"2c340a9506e185d3e38337a5703dae8f24d5027baedfd186c82d622e09cbab2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:16.830179Z","signature_b64":"3oy+RREygbYKd+hb3BXyMlM+zoeMosI6T5wSS3DePp4k7IR6NqTrp+oPJG9d1zLifflWCxwTl7ow8bxDt9FlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdf6f5d1e75e38474ceff458e79744a07481c841ed85f63a981789e7142afdcd","last_reissued_at":"2026-07-05T08:01:16.829700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:16.829700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLatrieval: LLM-Verified Retrieval for Verifiable Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Changtai Zhu, Linyang Li, Tianxiang Sun, Xiaonan Li, Xipeng Qiu, Zhangyue Yin","submitted_at":"2023-11-14T01:38:02Z","abstract_excerpt":"Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM's output more reliable. Retrieval plays a crucial role in verifiable generation. Specifically, the retrieved documents not only supplement knowledge to help the LLM generate correct answers, but also serve as supporting evidence for the user to verify the LLM's output. However, the widely used retrievers become the bottleneck of the entire pipeline and limit the overall performance. Their capabilities are usually inferi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07838","kind":"arxiv","version":3},"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/2311.07838/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":"2311.07838","created_at":"2026-07-05T08:01:16.829759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07838v3","created_at":"2026-07-05T08:01:16.829759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07838","created_at":"2026-07-05T08:01:16.829759+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZX3PLUPHLY4E","created_at":"2026-07-05T08:01:16.829759+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZX3PLUPHLY4EOTHP","created_at":"2026-07-05T08:01:16.829759+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZX3PLUPH","created_at":"2026-07-05T08:01:16.829759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08920","citing_title":"Beyond Relevance: Utility-Centric Retrieval in the LLM Era","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB","json":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB.json","graph_json":"https://pith.science/api/pith-number/ZX3PLUPHLY4EOTHP6RMOPF2EUB/graph.json","events_json":"https://pith.science/api/pith-number/ZX3PLUPHLY4EOTHP6RMOPF2EUB/events.json","paper":"https://pith.science/paper/ZX3PLUPH"},"agent_actions":{"view_html":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB","download_json":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB.json","view_paper":"https://pith.science/paper/ZX3PLUPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07838&json=true","fetch_graph":"https://pith.science/api/pith-number/ZX3PLUPHLY4EOTHP6RMOPF2EUB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZX3PLUPHLY4EOTHP6RMOPF2EUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB/action/storage_attestation","attest_author":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB/action/author_attestation","sign_citation":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB/action/citation_signature","submit_replication":"https://pith.science/pith/ZX3PLUPHLY4EOTHP6RMOPF2EUB/action/replication_record"}},"created_at":"2026-07-05T08:01:16.829759+00:00","updated_at":"2026-07-05T08:01:16.829759+00:00"}