{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TJFN5OIAPE6ZLD4HV2ZQOO7RJ4","short_pith_number":"pith:TJFN5OIA","schema_version":"1.0","canonical_sha256":"9a4adeb900793d958f87aeb3073bf14f1adc635a9b00c59e5d50dac3c5bac7d8","source":{"kind":"arxiv","id":"2405.20139","version":1},"attestation_state":"computed","paper":{"title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Costas Mavromatis, George Karypis","submitted_at":"2024-05-30T15:14:24Z","abstract_excerpt":"Knowledge Graphs (KGs) represent human-crafted factual knowledge in the form of triplets (head, relation, tail), which collectively form a graph. Question Answering over KGs (KGQA) is the task of answering natural questions grounding the reasoning to the information provided by the KG. Large Language Models (LLMs) are the state-of-the-art models for QA tasks due to their remarkable ability to understand natural language. On the other hand, Graph Neural Networks (GNNs) have been widely used for KGQA as they can handle the complex graph information stored in the KG. In this work, we introduce GN"},"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":"2405.20139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T15:14:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aec847174885a13935dff26f2e33212b692c3aa564e62058bd2d0af48098d601","abstract_canon_sha256":"e444f6aaf4890ca0244775378c17560c843b3a77b1491b77319068ea1ad71246"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:24.078655Z","signature_b64":"yJ/Qd7H/3osaTeFjEo+umADrDRy+Y+RVk5lr68IVdNX78wDep3YWRPwwnXBb9/b8uDNvf/+XHVLeXrGwHTgbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4adeb900793d958f87aeb3073bf14f1adc635a9b00c59e5d50dac3c5bac7d8","last_reissued_at":"2026-07-05T08:25:24.077931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:24.077931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Costas Mavromatis, George Karypis","submitted_at":"2024-05-30T15:14:24Z","abstract_excerpt":"Knowledge Graphs (KGs) represent human-crafted factual knowledge in the form of triplets (head, relation, tail), which collectively form a graph. Question Answering over KGs (KGQA) is the task of answering natural questions grounding the reasoning to the information provided by the KG. Large Language Models (LLMs) are the state-of-the-art models for QA tasks due to their remarkable ability to understand natural language. On the other hand, Graph Neural Networks (GNNs) have been widely used for KGQA as they can handle the complex graph information stored in the KG. In this work, we introduce GN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20139","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/2405.20139/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":"2405.20139","created_at":"2026-07-05T08:25:24.078004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20139v1","created_at":"2026-07-05T08:25:24.078004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20139","created_at":"2026-07-05T08:25:24.078004+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJFN5OIAPE6Z","created_at":"2026-07-05T08:25:24.078004+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJFN5OIAPE6ZLD4H","created_at":"2026-07-05T08:25:24.078004+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJFN5OIA","created_at":"2026-07-05T08:25:24.078004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00052","citing_title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23467","citing_title":"S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17086","citing_title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18760","citing_title":"DOTRAG: Retrieval-Time Reasoning Along Paths","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11541","citing_title":"Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17934","citing_title":"AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM","ref_index":22,"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":23,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":289,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":283,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12061","citing_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04449","citing_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08603","citing_title":"From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15951","citing_title":"Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval","ref_index":49,"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":55,"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":153,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4","json":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4.json","graph_json":"https://pith.science/api/pith-number/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/graph.json","events_json":"https://pith.science/api/pith-number/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/events.json","paper":"https://pith.science/paper/TJFN5OIA"},"agent_actions":{"view_html":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4","download_json":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4.json","view_paper":"https://pith.science/paper/TJFN5OIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20139&json=true","fetch_graph":"https://pith.science/api/pith-number/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/action/storage_attestation","attest_author":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/action/author_attestation","sign_citation":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/action/citation_signature","submit_replication":"https://pith.science/pith/TJFN5OIAPE6ZLD4HV2ZQOO7RJ4/action/replication_record"}},"created_at":"2026-07-05T08:25:24.078004+00:00","updated_at":"2026-07-05T08:25:24.078004+00:00"}