{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BB3SZFPFBZWYOBONJ2EM6OZYHA","short_pith_number":"pith:BB3SZFPF","schema_version":"1.0","canonical_sha256":"08772c95e50e6d8705cd4e88cf3b383828493a294bfbe6fc87b791268ec12d64","source":{"kind":"arxiv","id":"2407.21276","version":3},"attestation_state":"computed","paper":{"title":"Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jiaxin Wu, Qing Li, Rubing Chen, Wenqi Fan, Xiao-Yong Wei, Xulu Zhang","submitted_at":"2024-07-31T01:51:24Z","abstract_excerpt":"This paper addresses the need for improved precision in existing knowledge-enhanced question-answering frameworks, specifically Retrieval-Augmented Generation (RAG) methods that primarily focus on enhancing recall. We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall. The knowledge pyramid consists of three layers: Ontologies, Knowledge Graphs (KGs), and chunk-based raw text. We employ cross-layer augmentation techniques for comprehensive knowledge coverage and dynamic updates of the Ontology schema and instances."},"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":"2407.21276","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-31T01:51:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8c6bfe9d77773c9de7fbcb789c6f81747afc4bc5b7fab2fb1fcd20678367f00e","abstract_canon_sha256":"fa65288ec8250ee5666f0dea6c49d0b372b3c0dd5e4f32ffaa6988c03e3cd92d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:48.393127Z","signature_b64":"oqrkzL8Gfq5RlAQbSRqn4zu95NV/GLYsc4fyCIlPtp/7HEiNV12u7J0Ir0r79PpXU557ceSXPHZrX1hYh9vaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08772c95e50e6d8705cd4e88cf3b383828493a294bfbe6fc87b791268ec12d64","last_reissued_at":"2026-07-05T10:17:48.392657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:48.392657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jiaxin Wu, Qing Li, Rubing Chen, Wenqi Fan, Xiao-Yong Wei, Xulu Zhang","submitted_at":"2024-07-31T01:51:24Z","abstract_excerpt":"This paper addresses the need for improved precision in existing knowledge-enhanced question-answering frameworks, specifically Retrieval-Augmented Generation (RAG) methods that primarily focus on enhancing recall. We propose a multi-layer knowledge pyramid approach within the RAG framework to achieve a better balance between precision and recall. The knowledge pyramid consists of three layers: Ontologies, Knowledge Graphs (KGs), and chunk-based raw text. We employ cross-layer augmentation techniques for comprehensive knowledge coverage and dynamic updates of the Ontology schema and instances."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21276","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/2407.21276/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":"2407.21276","created_at":"2026-07-05T10:17:48.392712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21276v3","created_at":"2026-07-05T10:17:48.392712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21276","created_at":"2026-07-05T10:17:48.392712+00:00"},{"alias_kind":"pith_short_12","alias_value":"BB3SZFPFBZWY","created_at":"2026-07-05T10:17:48.392712+00:00"},{"alias_kind":"pith_short_16","alias_value":"BB3SZFPFBZWYOBON","created_at":"2026-07-05T10:17:48.392712+00:00"},{"alias_kind":"pith_short_8","alias_value":"BB3SZFPF","created_at":"2026-07-05T10:17:48.392712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03608","citing_title":"Benchmarking Vector, Graph and Hybrid Retrieval Augmented Generation (RAG) Pipelines for Open Radio Access Networks (ORAN)","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA","json":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA.json","graph_json":"https://pith.science/api/pith-number/BB3SZFPFBZWYOBONJ2EM6OZYHA/graph.json","events_json":"https://pith.science/api/pith-number/BB3SZFPFBZWYOBONJ2EM6OZYHA/events.json","paper":"https://pith.science/paper/BB3SZFPF"},"agent_actions":{"view_html":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA","download_json":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA.json","view_paper":"https://pith.science/paper/BB3SZFPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21276&json=true","fetch_graph":"https://pith.science/api/pith-number/BB3SZFPFBZWYOBONJ2EM6OZYHA/graph.json","fetch_events":"https://pith.science/api/pith-number/BB3SZFPFBZWYOBONJ2EM6OZYHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA/action/storage_attestation","attest_author":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA/action/author_attestation","sign_citation":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA/action/citation_signature","submit_replication":"https://pith.science/pith/BB3SZFPFBZWYOBONJ2EM6OZYHA/action/replication_record"}},"created_at":"2026-07-05T10:17:48.392712+00:00","updated_at":"2026-07-05T10:17:48.392712+00:00"}