{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6ZGDMFRNU7CGNVCVYMEE77XX2D","short_pith_number":"pith:6ZGDMFRN","schema_version":"1.0","canonical_sha256":"f64c36162da7c466d455c3084ffef7d0ec953c3467240f47a568584e87377adb","source":{"kind":"arxiv","id":"2409.05591","version":3},"attestation_state":"computed","paper":{"title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Defu Lian, Hongjin Qian, Kelong Mao, Peitian Zhang, Tiejun Huang, Zheng Liu, Zhicheng Dou","submitted_at":"2024-09-09T13:20:31Z","abstract_excerpt":"Processing long contexts presents a significant challenge for large language models (LLMs). While recent advancements allow LLMs to handle much longer contexts than before (e.g., 32K or 128K tokens), it is computationally expensive and can still be insufficient for many applications. Retrieval-Augmented Generation (RAG) is considered a promising strategy to address this problem. However, conventional RAG methods face inherent limitations because of two underlying requirements: 1) explicitly stated queries, and 2) well-structured knowledge. These conditions, however, do not hold in general long"},"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":"2409.05591","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-09T13:20:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"162f20e90237ac707fb403dd9a833d6f3f9ee92b4ac12eb11c0055daa6e756db","abstract_canon_sha256":"61a5f5896e915c5c6fad7a1a8a5f628dd5115c5278451bbb7788f0896f639e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:38.269425Z","signature_b64":"LfKimaeEW/YjJE6NNFY9U8hEtoCly5d+9bdxEI4D9EKiw18h613LOi6GjRCkVuokoiwnukSpUsNIYy8qJdJZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f64c36162da7c466d455c3084ffef7d0ec953c3467240f47a568584e87377adb","last_reissued_at":"2026-07-05T10:46:38.268924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:38.268924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Defu Lian, Hongjin Qian, Kelong Mao, Peitian Zhang, Tiejun Huang, Zheng Liu, Zhicheng Dou","submitted_at":"2024-09-09T13:20:31Z","abstract_excerpt":"Processing long contexts presents a significant challenge for large language models (LLMs). While recent advancements allow LLMs to handle much longer contexts than before (e.g., 32K or 128K tokens), it is computationally expensive and can still be insufficient for many applications. Retrieval-Augmented Generation (RAG) is considered a promising strategy to address this problem. However, conventional RAG methods face inherent limitations because of two underlying requirements: 1) explicitly stated queries, and 2) well-structured knowledge. These conditions, however, do not hold in general long"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05591","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/2409.05591/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":"2409.05591","created_at":"2026-07-05T10:46:38.268993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05591v3","created_at":"2026-07-05T10:46:38.268993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05591","created_at":"2026-07-05T10:46:38.268993+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZGDMFRNU7CG","created_at":"2026-07-05T10:46:38.268993+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZGDMFRNU7CGNVCV","created_at":"2026-07-05T10:46:38.268993+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZGDMFRN","created_at":"2026-07-05T10:46:38.268993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17449","citing_title":"MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13669","citing_title":"Agents-K1: Towards Agent-native Knowledge Orchestration","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":195,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04315","citing_title":"Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13669","citing_title":"Agents-K1: Towards Agent-native Knowledge Orchestration","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00610","citing_title":"MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17238","citing_title":"Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23231","citing_title":"PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18760","citing_title":"DOTRAG: Retrieval-Time Reasoning Along Paths","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21463","citing_title":"Mem-$\\pi$: Adaptive Memory through Learning When and What to Generate","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2504.15965","citing_title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20626","citing_title":"MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16312","citing_title":"FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20844","citing_title":"AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05779","citing_title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23424","citing_title":"Evolve: A Persistent Knowledge Lifecycle for Small Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04496","citing_title":"SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22843","citing_title":"Structure Guided Retrieval-Augmented Generation for Factual Queries","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D","json":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D.json","graph_json":"https://pith.science/api/pith-number/6ZGDMFRNU7CGNVCVYMEE77XX2D/graph.json","events_json":"https://pith.science/api/pith-number/6ZGDMFRNU7CGNVCVYMEE77XX2D/events.json","paper":"https://pith.science/paper/6ZGDMFRN"},"agent_actions":{"view_html":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D","download_json":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D.json","view_paper":"https://pith.science/paper/6ZGDMFRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05591&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZGDMFRNU7CGNVCVYMEE77XX2D/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZGDMFRNU7CGNVCVYMEE77XX2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D/action/storage_attestation","attest_author":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D/action/author_attestation","sign_citation":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D/action/citation_signature","submit_replication":"https://pith.science/pith/6ZGDMFRNU7CGNVCVYMEE77XX2D/action/replication_record"}},"created_at":"2026-07-05T10:46:38.268993+00:00","updated_at":"2026-07-05T10:46:38.268993+00:00"}