{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5RRD27MGG7GWU4IBIGLKTOSE2W","short_pith_number":"pith:5RRD27MG","schema_version":"1.0","canonical_sha256":"ec623d7d8637cd6a71014196a9ba44d5859599fa578965e9ec3c87eafe352836","source":{"kind":"arxiv","id":"2504.02441","version":2},"attestation_state":"computed","paper":{"title":"Cognitive Memory in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lianlei Shan, Shixian Luo, Yong Wu, Yu Yuan, Zezhou Zhu","submitted_at":"2025-04-03T09:58:19Z","abstract_excerpt":"This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures. The text-based memory section covers acquisition (selection and summarization), management (updating, accessing, storing, and resolving conflicts), and utilization (full-text search, SQL qu"},"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":"2504.02441","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T09:58:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"313ed8e56aac0a77b782bce3763783e4f921d0304f459e127d580e3962e41824","abstract_canon_sha256":"204a5448416213ba0bc6cceab2c6395a525ea6512f5dad46702fe389dac19e98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:16.748268Z","signature_b64":"ZOqbk8LYMbXf5ENYYweyOfIWr2wGnKvT/5rbIPJcvoa2IFnZgwMJ3rAOTsQ1D0OPij7LHGAIKVhcY1HJHUlXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec623d7d8637cd6a71014196a9ba44d5859599fa578965e9ec3c87eafe352836","last_reissued_at":"2026-07-05T10:53:16.747771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:16.747771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive Memory in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lianlei Shan, Shixian Luo, Yong Wu, Yu Yuan, Zezhou Zhu","submitted_at":"2025-04-03T09:58:19Z","abstract_excerpt":"This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures. The text-based memory section covers acquisition (selection and summarization), management (updating, accessing, storing, and resolving conflicts), and utilization (full-text search, SQL qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02441","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/2504.02441/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":"2504.02441","created_at":"2026-07-05T10:53:16.747826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02441v2","created_at":"2026-07-05T10:53:16.747826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02441","created_at":"2026-07-05T10:53:16.747826+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RRD27MGG7GW","created_at":"2026-07-05T10:53:16.747826+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RRD27MGG7GWU4IB","created_at":"2026-07-05T10:53:16.747826+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RRD27MG","created_at":"2026-07-05T10:53:16.747826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31650","citing_title":"ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26105","citing_title":"Context Recycling for Long-Horizon LLM Inference","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18854","citing_title":"Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14724","citing_title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2507.03724","citing_title":"MemOS: A Memory OS for AI System","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07957","citing_title":"MIRIX: Multi-Agent Memory System for LLM-Based Agents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04514","citing_title":"SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W","json":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W.json","graph_json":"https://pith.science/api/pith-number/5RRD27MGG7GWU4IBIGLKTOSE2W/graph.json","events_json":"https://pith.science/api/pith-number/5RRD27MGG7GWU4IBIGLKTOSE2W/events.json","paper":"https://pith.science/paper/5RRD27MG"},"agent_actions":{"view_html":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W","download_json":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W.json","view_paper":"https://pith.science/paper/5RRD27MG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02441&json=true","fetch_graph":"https://pith.science/api/pith-number/5RRD27MGG7GWU4IBIGLKTOSE2W/graph.json","fetch_events":"https://pith.science/api/pith-number/5RRD27MGG7GWU4IBIGLKTOSE2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W/action/storage_attestation","attest_author":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W/action/author_attestation","sign_citation":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W/action/citation_signature","submit_replication":"https://pith.science/pith/5RRD27MGG7GWU4IBIGLKTOSE2W/action/replication_record"}},"created_at":"2026-07-05T10:53:16.747826+00:00","updated_at":"2026-07-05T10:53:16.747826+00:00"}