{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3PHZHKAPEIQ5X3LVAJ66SMDIGZ","short_pith_number":"pith:3PHZHKAP","schema_version":"1.0","canonical_sha256":"dbcf93a80f2221dbed75027de93068364d1d49583347c2e1c4615108bc14dfa3","source":{"kind":"arxiv","id":"2506.20963","version":2},"attestation_state":"computed","paper":{"title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Di Jiang, Fangyuan Zhang, Qintian Guo, Wensheng Luo, Xiaofang Zhou, Yingli Zhou, Yixiang Fang, Zhengjun Huang, Zhixun Li","submitted_at":"2025-06-26T03:01:33Z","abstract_excerpt":"Graph-based Retrieval-Augmented Generation (Graph-RAG) enhances large language models (LLMs) by structuring retrieval over an external corpus. However, existing approaches typically assume a static corpus, requiring expensive full-graph reconstruction whenever new documents arrive, limiting their scalability in dynamic, evolving environments. To address these limitations, we introduce EraRAG, a novel multi-layered Graph-RAG framework that supports efficient and scalable dynamic updates. Our method leverages hyperplane-based Locality-Sensitive Hashing (LSH) to partition and organize the origina"},"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":"2506.20963","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-26T03:01:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a2d2710516f129c784da042cfb6523c82edd1670cfd4768f163cdd2db7e28e3d","abstract_canon_sha256":"764e600e0cd12199bc4e183374b1e1361e20bed74e4440c514cf26fd0d6d1d1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:46.778303Z","signature_b64":"NiQgdUq4AKifS4jvKtkDE7dpngXTGhxUTy2hTlA3E4i5bKQ+UNPY3XtDNTeDpQruJoMH1d7XPxwkerWeSIBLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbcf93a80f2221dbed75027de93068364d1d49583347c2e1c4615108bc14dfa3","last_reissued_at":"2026-07-05T11:31:46.777862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:46.777862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Di Jiang, Fangyuan Zhang, Qintian Guo, Wensheng Luo, Xiaofang Zhou, Yingli Zhou, Yixiang Fang, Zhengjun Huang, Zhixun Li","submitted_at":"2025-06-26T03:01:33Z","abstract_excerpt":"Graph-based Retrieval-Augmented Generation (Graph-RAG) enhances large language models (LLMs) by structuring retrieval over an external corpus. However, existing approaches typically assume a static corpus, requiring expensive full-graph reconstruction whenever new documents arrive, limiting their scalability in dynamic, evolving environments. To address these limitations, we introduce EraRAG, a novel multi-layered Graph-RAG framework that supports efficient and scalable dynamic updates. Our method leverages hyperplane-based Locality-Sensitive Hashing (LSH) to partition and organize the origina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20963","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/2506.20963/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":"2506.20963","created_at":"2026-07-05T11:31:46.777930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20963v2","created_at":"2026-07-05T11:31:46.777930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20963","created_at":"2026-07-05T11:31:46.777930+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PHZHKAPEIQ5","created_at":"2026-07-05T11:31:46.777930+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PHZHKAPEIQ5X3LV","created_at":"2026-07-05T11:31:46.777930+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PHZHKAP","created_at":"2026-07-05T11:31:46.777930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18075","citing_title":"A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00610","citing_title":"MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":230,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":220,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":144,"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":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02452","citing_title":"Position: How can Graphs Help Large Language Models?","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ","json":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ.json","graph_json":"https://pith.science/api/pith-number/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/graph.json","events_json":"https://pith.science/api/pith-number/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/events.json","paper":"https://pith.science/paper/3PHZHKAP"},"agent_actions":{"view_html":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ","download_json":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ.json","view_paper":"https://pith.science/paper/3PHZHKAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20963&json=true","fetch_graph":"https://pith.science/api/pith-number/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/action/storage_attestation","attest_author":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/action/author_attestation","sign_citation":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/action/citation_signature","submit_replication":"https://pith.science/pith/3PHZHKAPEIQ5X3LVAJ66SMDIGZ/action/replication_record"}},"created_at":"2026-07-05T11:31:46.777930+00:00","updated_at":"2026-07-05T11:31:46.777930+00:00"}