{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ZY4NUA4LKAMTBBH4ZEZUREINL","short_pith_number":"pith:4ZY4NUA4","schema_version":"1.0","canonical_sha256":"e671c6d01c5a80c98427e6499a44886af0e1eac5f6208f462b417e542b63ff0d","source":{"kind":"arxiv","id":"2507.21892","version":2},"attestation_state":"computed","paper":{"title":"Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangzhi Xu, Guanting Chen, Haihong E, Haoran Luo, Luu Anh Tuan, Meina Song, Qika Lin, Xiaobao Wu, Yifan Zhu, Yikai Guo, Zemin Kuang","submitted_at":"2025-07-29T15:01:26Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, the first agentic GraphRAG framework via end-to-end reinforcement learning (RL). It introduces lightweight knowledge hypergraph construction, models retrieval a"},"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":"2507.21892","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-29T15:01:26Z","cross_cats_sorted":[],"title_canon_sha256":"ace1768d1d4d317c859c57acad8d300f83fcad795fbd4641d2a858e522c6cf56","abstract_canon_sha256":"321f01dbd6faa7c9e6c1888a9487298cd91217dde6d7a811609f7f68f3e4f2b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:12.054441Z","signature_b64":"sDDZ8ePaJ1KMGrZf/EfuZxFqWa7dTBdATG+BeBIJ2mCTqGJPq0DJju/VGy+lXU21K4mIBZJHFnftgsUkoxIoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e671c6d01c5a80c98427e6499a44886af0e1eac5f6208f462b417e542b63ff0d","last_reissued_at":"2026-06-04T01:08:12.053852Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:12.053852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangzhi Xu, Guanting Chen, Haihong E, Haoran Luo, Luu Anh Tuan, Meina Song, Qika Lin, Xiaobao Wu, Yifan Zhu, Yikai Guo, Zemin Kuang","submitted_at":"2025-07-29T15:01:26Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as entity-relation graphs, but still face challenges in high construction cost, fixed one-time retrieval, and reliance on long-context reasoning and prompt design. To address these challenges, we propose Graph-R1, the first agentic GraphRAG framework via end-to-end reinforcement learning (RL). It introduces lightweight knowledge hypergraph construction, models retrieval a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21892","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.21892/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":"2507.21892","created_at":"2026-06-04T01:08:12.053922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21892v2","created_at":"2026-06-04T01:08:12.053922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21892","created_at":"2026-06-04T01:08:12.053922+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZY4NUA4LKAM","created_at":"2026-06-04T01:08:12.053922+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZY4NUA4LKAMTBBH","created_at":"2026-06-04T01:08:12.053922+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZY4NUA4","created_at":"2026-06-04T01:08:12.053922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2604.20844","citing_title":"AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01410","citing_title":"GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning","ref_index":37,"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":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10488","citing_title":"DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17265","citing_title":"MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20719","citing_title":"ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL","json":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL.json","graph_json":"https://pith.science/api/pith-number/4ZY4NUA4LKAMTBBH4ZEZUREINL/graph.json","events_json":"https://pith.science/api/pith-number/4ZY4NUA4LKAMTBBH4ZEZUREINL/events.json","paper":"https://pith.science/paper/4ZY4NUA4"},"agent_actions":{"view_html":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL","download_json":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL.json","view_paper":"https://pith.science/paper/4ZY4NUA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21892&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZY4NUA4LKAMTBBH4ZEZUREINL/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZY4NUA4LKAMTBBH4ZEZUREINL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL/action/storage_attestation","attest_author":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL/action/author_attestation","sign_citation":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL/action/citation_signature","submit_replication":"https://pith.science/pith/4ZY4NUA4LKAMTBBH4ZEZUREINL/action/replication_record"}},"created_at":"2026-06-04T01:08:12.053922+00:00","updated_at":"2026-06-04T01:08:12.053922+00:00"}