{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKBFLMUXNI2V7GELQQBFV6X3XB","short_pith_number":"pith:QKBFLMUX","schema_version":"1.0","canonical_sha256":"828255b2976a355f988b84025afafbb840f62fc2816fc2f965692885aa99a29c","source":{"kind":"arxiv","id":"2405.16506","version":3},"attestation_state":"computed","paper":{"title":"GRAG: Graph Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Pan, Chen Ling, Liang Zhao, Yuntong Hu, Zheng Zhang, Zhihan Lei","submitted_at":"2024-05-26T10:11:40Z","abstract_excerpt":"Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and knowledge graphs. To overcome this limitation, we introduce Graph Retrieval-Augmented Generation (GRAG), which tackles the fundamental challenges in retrieving textual subgraphs and integrating the joint textual and topological information into Large Language Models (LLMs) to enhance its generation. To enable efficient textual subgraph retrieval, we propose"},"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":"2405.16506","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T10:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"8afba13af2fb9c643fdc1b04679bea95d312842e03c090201a9fbf6a681e52dc","abstract_canon_sha256":"f4181480738a261bcddabd67dfa1b8eaf9dd5022e7110e7a4bc0252fec1c1fcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:49.525266Z","signature_b64":"kW17UFe6u+4w4OzkrCmo2XXrWl06F90rNIsYKVJRmJBDVtnX4K7cj+U1vMu9T0j7BQAay0IhYY1/INlr5pevDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"828255b2976a355f988b84025afafbb840f62fc2816fc2f965692885aa99a29c","last_reissued_at":"2026-07-05T11:35:49.524528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:49.524528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRAG: Graph Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Pan, Chen Ling, Liang Zhao, Yuntong Hu, Zheng Zhang, Zhihan Lei","submitted_at":"2024-05-26T10:11:40Z","abstract_excerpt":"Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and knowledge graphs. To overcome this limitation, we introduce Graph Retrieval-Augmented Generation (GRAG), which tackles the fundamental challenges in retrieving textual subgraphs and integrating the joint textual and topological information into Large Language Models (LLMs) to enhance its generation. To enable efficient textual subgraph retrieval, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16506","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/2405.16506/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":"2405.16506","created_at":"2026-07-05T11:35:49.524619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16506v3","created_at":"2026-07-05T11:35:49.524619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16506","created_at":"2026-07-05T11:35:49.524619+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKBFLMUXNI2V","created_at":"2026-07-05T11:35:49.524619+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKBFLMUXNI2V7GEL","created_at":"2026-07-05T11:35:49.524619+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKBFLMUX","created_at":"2026-07-05T11:35:49.524619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26458","citing_title":"MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18075","citing_title":"A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11560","citing_title":"LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00052","citing_title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27164","citing_title":"Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20505","citing_title":"RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20844","citing_title":"AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB","json":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB.json","graph_json":"https://pith.science/api/pith-number/QKBFLMUXNI2V7GELQQBFV6X3XB/graph.json","events_json":"https://pith.science/api/pith-number/QKBFLMUXNI2V7GELQQBFV6X3XB/events.json","paper":"https://pith.science/paper/QKBFLMUX"},"agent_actions":{"view_html":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB","download_json":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB.json","view_paper":"https://pith.science/paper/QKBFLMUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16506&json=true","fetch_graph":"https://pith.science/api/pith-number/QKBFLMUXNI2V7GELQQBFV6X3XB/graph.json","fetch_events":"https://pith.science/api/pith-number/QKBFLMUXNI2V7GELQQBFV6X3XB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB/action/storage_attestation","attest_author":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB/action/author_attestation","sign_citation":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB/action/citation_signature","submit_replication":"https://pith.science/pith/QKBFLMUXNI2V7GELQQBFV6X3XB/action/replication_record"}},"created_at":"2026-07-05T11:35:49.524619+00:00","updated_at":"2026-07-05T11:35:49.524619+00:00"}