{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W2GAWQYIAJMQ74GLUVJKVJJCP6","short_pith_number":"pith:W2GAWQYI","schema_version":"1.0","canonical_sha256":"b68c0b430802590ff0cba552aaa5227f9f2d65d7e74afa264c9966dfce8b4da3","source":{"kind":"arxiv","id":"2501.00309","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Amin Javari, Bo Long, Haoyu Han, Harry Shomer, Jiayuan Ding, Jiliang Tang, Kai Guo, Mahantesh Halappanavar, Neil Shah, Qi He, Ryan A. Rossi, Subhabrata Mukherjee, Tong Zhao, Xianfeng Tang, Yinglong Xia, Yongjia Lei, Yu Wang, Zhigang Hua","submitted_at":"2024-12-31T06:59:35Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic \"nodes connected by edges\" nature, encodes massive heterogeneous and relational information, making it a golden resource for RAG in tremendous real-world applications. As a result, we have recently witnessed increasing attention on equipping RAG with Graph, i.e., GraphRAG. However, unlike conventional RAG, where the retriever, generator, and external data sources can be unif"},"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":"2501.00309","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-31T06:59:35Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"904f6610687da917b75703d923d26d07a87313e7d8454521079246ade9bcc104","abstract_canon_sha256":"184642171f7a256a2016939a35815dba51a1192ff3aa131baee5df4db06e93fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:28:55.116390Z","signature_b64":"kXSh1sNoW7SQAHeoj3TKlwgqhIOX5Uu5SZQmIT7vIX0/2odFsKqhuVj8W1CS5xot8uzlsLbr4wpEBdunc+lADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b68c0b430802590ff0cba552aaa5227f9f2d65d7e74afa264c9966dfce8b4da3","last_reissued_at":"2026-05-18T04:28:55.115820Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:28:55.115820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Amin Javari, Bo Long, Haoyu Han, Harry Shomer, Jiayuan Ding, Jiliang Tang, Kai Guo, Mahantesh Halappanavar, Neil Shah, Qi He, Ryan A. Rossi, Subhabrata Mukherjee, Tong Zhao, Xianfeng Tang, Yinglong Xia, Yongjia Lei, Yu Wang, Zhigang Hua","submitted_at":"2024-12-31T06:59:35Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic \"nodes connected by edges\" nature, encodes massive heterogeneous and relational information, making it a golden resource for RAG in tremendous real-world applications. As a result, we have recently witnessed increasing attention on equipping RAG with Graph, i.e., GraphRAG. However, unlike conventional RAG, where the retriever, generator, and external data sources can be unif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00309","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":""},"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":"2501.00309","created_at":"2026-05-18T04:28:55.115895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00309v2","created_at":"2026-05-18T04:28:55.115895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00309","created_at":"2026-05-18T04:28:55.115895+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2GAWQYIAJMQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2GAWQYIAJMQ74GL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2GAWQYI","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2509.03540","citing_title":"Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24276","citing_title":"G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2510.07048","citing_title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2510.22628","citing_title":"Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29875","citing_title":"UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13933","citing_title":"HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14192","citing_title":"Why Retrieval-Augmented Generation Fails: A Graph Perspective","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14259","citing_title":"Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19776","citing_title":"Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09666","citing_title":"Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01707","citing_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16422","citing_title":"Injecting Structured Biomedical Knowledge into Language Models: Continual Pretraining vs. GraphRAG","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03174","citing_title":"Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27852","citing_title":"NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08831","citing_title":"AssemPlanner: A Multi-Agent Based Task Planning Framework for Flexible Assembly System","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24623","citing_title":"XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20795","citing_title":"Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07517","citing_title":"LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04372","citing_title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17305","citing_title":"BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6","json":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6.json","graph_json":"https://pith.science/api/pith-number/W2GAWQYIAJMQ74GLUVJKVJJCP6/graph.json","events_json":"https://pith.science/api/pith-number/W2GAWQYIAJMQ74GLUVJKVJJCP6/events.json","paper":"https://pith.science/paper/W2GAWQYI"},"agent_actions":{"view_html":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6","download_json":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6.json","view_paper":"https://pith.science/paper/W2GAWQYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00309&json=true","fetch_graph":"https://pith.science/api/pith-number/W2GAWQYIAJMQ74GLUVJKVJJCP6/graph.json","fetch_events":"https://pith.science/api/pith-number/W2GAWQYIAJMQ74GLUVJKVJJCP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6/action/storage_attestation","attest_author":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6/action/author_attestation","sign_citation":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6/action/citation_signature","submit_replication":"https://pith.science/pith/W2GAWQYIAJMQ74GLUVJKVJJCP6/action/replication_record"}},"created_at":"2026-05-18T04:28:55.115895+00:00","updated_at":"2026-05-18T04:28:55.115895+00:00"}