{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5QTKQIZYEVR4RRTJUDXB7JG33X","short_pith_number":"pith:5QTKQIZY","schema_version":"1.0","canonical_sha256":"ec26a823382563c8c669a0ee1fa4dbdde0345a00b39e991ca68edb13b4bfe4fd","source":{"kind":"arxiv","id":"2410.08815","version":2},"attestation_state":"computed","paper":{"title":"StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haiyang Yu, Hongyu Lin, Le Sun, Qiaoyu Tang, Xianpei Han, Xuanang Chen, Yaojie Lu, Yongbin Li, Zhuoqun Li","submitted_at":"2024-10-11T13:52:44Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information required to these tasks are badly scattered. This characteristic makes it difficult for existing RAG methods to accurately identify key information and perform global reasoning with such noisy augmentation. In this paper, motivated by the cognitive theories that humans convert raw information into various structured knowledge when tackling knowledge-inten"},"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":"2410.08815","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T13:52:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b688601e349e40e5e7afb77b23629bda164d264176e8b3d1f229a38d1605cc09","abstract_canon_sha256":"d7c95b3034af9a66427662e0d73f041d236d701c5599a5f7fc1d2b761e157c85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:47.929865Z","signature_b64":"+kFh+a+vCd1phZ11rKSG7lEqvB6hVmxgSKHo/6heb4mMUAmNDHSDonsBmzumKTmMz35KT61ZOXB6RXcH+Jv1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec26a823382563c8c669a0ee1fa4dbdde0345a00b39e991ca68edb13b4bfe4fd","last_reissued_at":"2026-07-05T09:25:47.929364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:47.929364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haiyang Yu, Hongyu Lin, Le Sun, Qiaoyu Tang, Xianpei Han, Xuanang Chen, Yaojie Lu, Yongbin Li, Zhuoqun Li","submitted_at":"2024-10-11T13:52:44Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information required to these tasks are badly scattered. This characteristic makes it difficult for existing RAG methods to accurately identify key information and perform global reasoning with such noisy augmentation. In this paper, motivated by the cognitive theories that humans convert raw information into various structured knowledge when tackling knowledge-inten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08815","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/2410.08815/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":"2410.08815","created_at":"2026-07-05T09:25:47.929424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08815v2","created_at":"2026-07-05T09:25:47.929424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08815","created_at":"2026-07-05T09:25:47.929424+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QTKQIZYEVR4","created_at":"2026-07-05T09:25:47.929424+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QTKQIZYEVR4RRTJ","created_at":"2026-07-05T09:25:47.929424+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QTKQIZY","created_at":"2026-07-05T09:25:47.929424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":243,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20844","citing_title":"AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02690","citing_title":"AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04372","citing_title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15676","citing_title":"EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X","json":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X.json","graph_json":"https://pith.science/api/pith-number/5QTKQIZYEVR4RRTJUDXB7JG33X/graph.json","events_json":"https://pith.science/api/pith-number/5QTKQIZYEVR4RRTJUDXB7JG33X/events.json","paper":"https://pith.science/paper/5QTKQIZY"},"agent_actions":{"view_html":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X","download_json":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X.json","view_paper":"https://pith.science/paper/5QTKQIZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08815&json=true","fetch_graph":"https://pith.science/api/pith-number/5QTKQIZYEVR4RRTJUDXB7JG33X/graph.json","fetch_events":"https://pith.science/api/pith-number/5QTKQIZYEVR4RRTJUDXB7JG33X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X/action/storage_attestation","attest_author":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X/action/author_attestation","sign_citation":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X/action/citation_signature","submit_replication":"https://pith.science/pith/5QTKQIZYEVR4RRTJUDXB7JG33X/action/replication_record"}},"created_at":"2026-07-05T09:25:47.929424+00:00","updated_at":"2026-07-05T09:25:47.929424+00:00"}