{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EU7WXUBGZ7K4KRZWYN5IZ746JO","short_pith_number":"pith:EU7WXUBG","schema_version":"1.0","canonical_sha256":"253f6bd026cfd5c54736c37a8cff9e4b9ac046549eebe6db94f478f823084b30","source":{"kind":"arxiv","id":"2405.14831","version":3},"attestation_state":"computed","paper":{"title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bernal Jim\\'enez Guti\\'errez, Michihiro Yasunaga, Yiheng Shu, Yu Gu, Yu Su","submitted_at":"2024-05-23T17:47:55Z","abstract_excerpt":"In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting. Despite the impressive accomplishments, large language models (LLMs), even with retrieval-augmented generation (RAG), still struggle to efficiently and effectively integrate a large amount of new experiences after pre-training. In this work, we introduce HippoRAG, a novel retrieval framework inspired by the hippocampal indexing theory of human long-term memory to enabl"},"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":"2405.14831","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T17:47:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4be37dfdb7638fdb3d47ae0b9ee3929b38b4a6833cb14e7bc447b794bceaa8d2","abstract_canon_sha256":"640c011db535e3ea9f7fabf6be5adb92aefd8ce5a986cf6f354e4718aabf7927"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:37.271863Z","signature_b64":"97hfrwJzjC7XOaQAgb2D9fTx3eCTMp/8l8u1+2HjtRH7aaaTdguVRfT1xdIuIls/Uey49oPTmD7WTERDTB3wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"253f6bd026cfd5c54736c37a8cff9e4b9ac046549eebe6db94f478f823084b30","last_reissued_at":"2026-07-05T10:00:37.271399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:37.271399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bernal Jim\\'enez Guti\\'errez, Michihiro Yasunaga, Yiheng Shu, Yu Gu, Yu Su","submitted_at":"2024-05-23T17:47:55Z","abstract_excerpt":"In order to thrive in hostile and ever-changing natural environments, mammalian brains evolved to store large amounts of knowledge about the world and continually integrate new information while avoiding catastrophic forgetting. Despite the impressive accomplishments, large language models (LLMs), even with retrieval-augmented generation (RAG), still struggle to efficiently and effectively integrate a large amount of new experiences after pre-training. In this work, we introduce HippoRAG, a novel retrieval framework inspired by the hippocampal indexing theory of human long-term memory to enabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14831","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/2405.14831/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":"2405.14831","created_at":"2026-07-05T10:00:37.271459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14831v3","created_at":"2026-07-05T10:00:37.271459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14831","created_at":"2026-07-05T10:00:37.271459+00:00"},{"alias_kind":"pith_short_12","alias_value":"EU7WXUBGZ7K4","created_at":"2026-07-05T10:00:37.271459+00:00"},{"alias_kind":"pith_short_16","alias_value":"EU7WXUBGZ7K4KRZW","created_at":"2026-07-05T10:00:37.271459+00:00"},{"alias_kind":"pith_short_8","alias_value":"EU7WXUBG","created_at":"2026-07-05T10:00:37.271459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":41,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08032","citing_title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26806","citing_title":"Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15903","citing_title":"Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01935","citing_title":"A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12290","citing_title":"Selection Integrity for LLM Graph Memory: An Accumulability Criterion for Information-Flow-Blind Retrieval","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10299","citing_title":"What Spatial Memory Must Store: Occlusion as the Test for Language-Agent Memory","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06240","citing_title":"TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00692","citing_title":"Self-GC: Self-Governing Context for Long-Horizon LLM Agents","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04555","citing_title":"Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03374","citing_title":"eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30949","citing_title":"AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20571","citing_title":"Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14906","citing_title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14790","citing_title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28365","citing_title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29916","citing_title":"EVAF: A Test-Retest Protocol for Selective Parametric Consolidation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29399","citing_title":"LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30133","citing_title":"Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28773","citing_title":"Rethinking Memory as Continuously Evolving Connectivity","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08216","citing_title":"MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20724","citing_title":"CALMem : Application-Layer Dual Memory for Conversational AI","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15701","citing_title":"H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO","json":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO.json","graph_json":"https://pith.science/api/pith-number/EU7WXUBGZ7K4KRZWYN5IZ746JO/graph.json","events_json":"https://pith.science/api/pith-number/EU7WXUBGZ7K4KRZWYN5IZ746JO/events.json","paper":"https://pith.science/paper/EU7WXUBG"},"agent_actions":{"view_html":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO","download_json":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO.json","view_paper":"https://pith.science/paper/EU7WXUBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14831&json=true","fetch_graph":"https://pith.science/api/pith-number/EU7WXUBGZ7K4KRZWYN5IZ746JO/graph.json","fetch_events":"https://pith.science/api/pith-number/EU7WXUBGZ7K4KRZWYN5IZ746JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO/action/storage_attestation","attest_author":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO/action/author_attestation","sign_citation":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO/action/citation_signature","submit_replication":"https://pith.science/pith/EU7WXUBGZ7K4KRZWYN5IZ746JO/action/replication_record"}},"created_at":"2026-07-05T10:00:37.271459+00:00","updated_at":"2026-07-05T10:00:37.271459+00:00"}