{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D5VOAAXRQV3MZRNTWSFYB4UREY","short_pith_number":"pith:D5VOAAXR","schema_version":"1.0","canonical_sha256":"1f6ae002f18576ccc5b3b48b80f2912604662ec368a137d70635ad65c8f51d69","source":{"kind":"arxiv","id":"2504.11544","version":1},"attestation_state":"computed","paper":{"title":"NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengze Li, Haojie Zheng, Haoxiang Chen, Lichao Sun, Ruoxi Chen, Tianyang Xu, Yixin Liu","submitted_at":"2025-04-15T18:24:00Z","abstract_excerpt":"Retrieval-augmented generation (RAG) empowers large language models to access external and private corpus, enabling factually consistent responses in specific domains. By exploiting the inherent structure of the corpus, graph-based RAG methods further enrich this process by building a knowledge graph index and leveraging the structural nature of graphs. However, current graph-based RAG approaches seldom prioritize the design of graph structures. Inadequately designed graph not only impede the seamless integration of diverse graph algorithms but also result in workflow inconsistencies and degra"},"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":"2504.11544","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-15T18:24:00Z","cross_cats_sorted":[],"title_canon_sha256":"7f7022dfe70fb5be13f485b66d6fc520d1c2becef4542dc3407311cc56dc974b","abstract_canon_sha256":"253e49cded39d4d33b45585171225fef9210ee62c1db3327cd9e742235ab6353"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:36.703414Z","signature_b64":"TvkE/Q36tCScWEBDgUNeUgXpo+SSkVbQ4+E0SorFGiTXlKmvUZ3mqthMXqA8h/ZUKrWoYdbCbCU84jh2g9cwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f6ae002f18576ccc5b3b48b80f2912604662ec368a137d70635ad65c8f51d69","last_reissued_at":"2026-07-05T10:49:36.702845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:36.702845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengze Li, Haojie Zheng, Haoxiang Chen, Lichao Sun, Ruoxi Chen, Tianyang Xu, Yixin Liu","submitted_at":"2025-04-15T18:24:00Z","abstract_excerpt":"Retrieval-augmented generation (RAG) empowers large language models to access external and private corpus, enabling factually consistent responses in specific domains. By exploiting the inherent structure of the corpus, graph-based RAG methods further enrich this process by building a knowledge graph index and leveraging the structural nature of graphs. However, current graph-based RAG approaches seldom prioritize the design of graph structures. Inadequately designed graph not only impede the seamless integration of diverse graph algorithms but also result in workflow inconsistencies and degra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11544","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/2504.11544/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":"2504.11544","created_at":"2026-07-05T10:49:36.702902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11544v1","created_at":"2026-07-05T10:49:36.702902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11544","created_at":"2026-07-05T10:49:36.702902+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5VOAAXRQV3M","created_at":"2026-07-05T10:49:36.702902+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5VOAAXRQV3MZRNT","created_at":"2026-07-05T10:49:36.702902+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5VOAAXR","created_at":"2026-07-05T10:49:36.702902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26511","citing_title":"Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge","ref_index":4,"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":265,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY","json":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY.json","graph_json":"https://pith.science/api/pith-number/D5VOAAXRQV3MZRNTWSFYB4UREY/graph.json","events_json":"https://pith.science/api/pith-number/D5VOAAXRQV3MZRNTWSFYB4UREY/events.json","paper":"https://pith.science/paper/D5VOAAXR"},"agent_actions":{"view_html":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY","download_json":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY.json","view_paper":"https://pith.science/paper/D5VOAAXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11544&json=true","fetch_graph":"https://pith.science/api/pith-number/D5VOAAXRQV3MZRNTWSFYB4UREY/graph.json","fetch_events":"https://pith.science/api/pith-number/D5VOAAXRQV3MZRNTWSFYB4UREY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY/action/storage_attestation","attest_author":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY/action/author_attestation","sign_citation":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY/action/citation_signature","submit_replication":"https://pith.science/pith/D5VOAAXRQV3MZRNTWSFYB4UREY/action/replication_record"}},"created_at":"2026-07-05T10:49:36.702902+00:00","updated_at":"2026-07-05T10:49:36.702902+00:00"}