{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ONGIS45PU2TTD2GBW42WFTEQIL","short_pith_number":"pith:ONGIS45P","schema_version":"1.0","canonical_sha256":"734c8973afa6a731e8c1b73562cc9042fe76a0b0468f082e7b65725a64db592b","source":{"kind":"arxiv","id":"2502.06864","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Graph-Guided Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wei Hu, Xiangrong Zhu, Yaliang Li, Yi Liu, Yuexiang Xie","submitted_at":"2025-02-08T02:14:31Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based approaches to retrieve isolated relevant chunks, which ignore their intrinsic relationships. In this paper, we propose a novel Knowledge Graph-Guided Retrieval Augmented Generation (KG$^2$RAG) framework that utilizes knowledge graphs (KGs) to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results. Specif"},"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":"2502.06864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-08T02:14:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f93f1902d36fd389cc84abb1b9ce631c49e359140923e41b511c02502f9cd2b","abstract_canon_sha256":"4d8a8a749bc4c233850df28af6174412cafa05945c21fe3460cb27917ece807d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:29.064026Z","signature_b64":"z+5hSvWkDZyUMvzaWlz7IYE5wvdLcQoMJdf28igDNZSENVdl5LgO3cdt/occyZnJJ044z5k8w2TN2sOMuLMWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"734c8973afa6a731e8c1b73562cc9042fe76a0b0468f082e7b65725a64db592b","last_reissued_at":"2026-07-05T10:12:29.063549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:29.063549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph-Guided Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wei Hu, Xiangrong Zhu, Yaliang Li, Yi Liu, Yuexiang Xie","submitted_at":"2025-02-08T02:14:31Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based approaches to retrieve isolated relevant chunks, which ignore their intrinsic relationships. In this paper, we propose a novel Knowledge Graph-Guided Retrieval Augmented Generation (KG$^2$RAG) framework that utilizes knowledge graphs (KGs) to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results. Specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06864","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/2502.06864/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":"2502.06864","created_at":"2026-07-05T10:12:29.063604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06864v1","created_at":"2026-07-05T10:12:29.063604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06864","created_at":"2026-07-05T10:12:29.063604+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONGIS45PU2TT","created_at":"2026-07-05T10:12:29.063604+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONGIS45PU2TTD2GB","created_at":"2026-07-05T10:12:29.063604+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONGIS45P","created_at":"2026-07-05T10:12:29.063604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00013","citing_title":"GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26383","citing_title":"Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2508.00933","citing_title":"OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05318","citing_title":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21577","citing_title":"Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20848","citing_title":"MATRAG: Multi-Agent Transparent Retrieval-Augmented Generation for Explainable Recommendations","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01495","citing_title":"FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL","json":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL.json","graph_json":"https://pith.science/api/pith-number/ONGIS45PU2TTD2GBW42WFTEQIL/graph.json","events_json":"https://pith.science/api/pith-number/ONGIS45PU2TTD2GBW42WFTEQIL/events.json","paper":"https://pith.science/paper/ONGIS45P"},"agent_actions":{"view_html":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL","download_json":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL.json","view_paper":"https://pith.science/paper/ONGIS45P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06864&json=true","fetch_graph":"https://pith.science/api/pith-number/ONGIS45PU2TTD2GBW42WFTEQIL/graph.json","fetch_events":"https://pith.science/api/pith-number/ONGIS45PU2TTD2GBW42WFTEQIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL/action/storage_attestation","attest_author":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL/action/author_attestation","sign_citation":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL/action/citation_signature","submit_replication":"https://pith.science/pith/ONGIS45PU2TTD2GBW42WFTEQIL/action/replication_record"}},"created_at":"2026-07-05T10:12:29.063604+00:00","updated_at":"2026-07-05T10:12:29.063604+00:00"}