{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CWWXZ3TMWAY3TEJ4O5AIW6CIYQ","short_pith_number":"pith:CWWXZ3TM","schema_version":"1.0","canonical_sha256":"15ad7cee6cb031b9913c77408b7848c42936db06db54f540a0ded7bed8108917","source":{"kind":"arxiv","id":"2304.13343","version":4},"attestation_state":"computed","paper":{"title":"SCM: Enhancing Large Language Model with Self-Controlled Memory Framework","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Wang, Hui Huang, Jian Yang, Lu Lu, Peihao Wu, Shuangzhi Wu, Xinnian Liang, Zejun Ma, Zhoujun Li","submitted_at":"2023-04-26T07:25:31Z","abstract_excerpt":"Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information. Our SCM framework comprises three key components: an LLM-based agent serving as the backbone of the framework, a memory stream storing agent memories, and a memory controller updating memories and determining when and how to utilize memories from memory stream."},"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":"2304.13343","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-26T07:25:31Z","cross_cats_sorted":[],"title_canon_sha256":"8127203dce608ff6e5a5fa47ffa8042276a28cb38d477325b55c747228f12317","abstract_canon_sha256":"8b2317bd648179ad4c0b2ee02e7391e3f045f4c05f82daed8bc798ba611f2f5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:01.621950Z","signature_b64":"O6i6FglnCVMu/x76ScyJ2xMfavWQmfyc+EqFFLKsH62yeQqR7+qZZ7TJWutz1DN3/7qRcytt4oOHm/l6kmSMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15ad7cee6cb031b9913c77408b7848c42936db06db54f540a0ded7bed8108917","last_reissued_at":"2026-07-05T10:33:01.621444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:01.621444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCM: Enhancing Large Language Model with Self-Controlled Memory Framework","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Wang, Hui Huang, Jian Yang, Lu Lu, Peihao Wu, Shuangzhi Wu, Xinnian Liang, Zejun Ma, Zhoujun Li","submitted_at":"2023-04-26T07:25:31Z","abstract_excerpt":"Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM) framework to enhance the ability of LLMs to maintain long-term memory and recall relevant information. Our SCM framework comprises three key components: an LLM-based agent serving as the backbone of the framework, a memory stream storing agent memories, and a memory controller updating memories and determining when and how to utilize memories from memory stream."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13343","kind":"arxiv","version":4},"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/2304.13343/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":"2304.13343","created_at":"2026-07-05T10:33:01.621503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13343v4","created_at":"2026-07-05T10:33:01.621503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13343","created_at":"2026-07-05T10:33:01.621503+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWWXZ3TMWAY3","created_at":"2026-07-05T10:33:01.621503+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWWXZ3TMWAY3TEJ4","created_at":"2026-07-05T10:33:01.621503+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWWXZ3TM","created_at":"2026-07-05T10:33:01.621503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09659","citing_title":"End-to-End Context Compression at Scale","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14906","citing_title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25971","citing_title":"Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15710","citing_title":"SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory","ref_index":24,"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":67,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13941","citing_title":"EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":35,"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":36,"is_internal_anchor":false},{"citing_arxiv_id":"2308.14508","citing_title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17753","citing_title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09942","citing_title":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12110","citing_title":"A-MEM: Agentic Memory for LLM Agents","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06845","citing_title":"HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16839","citing_title":"HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ","json":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ.json","graph_json":"https://pith.science/api/pith-number/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/graph.json","events_json":"https://pith.science/api/pith-number/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/events.json","paper":"https://pith.science/paper/CWWXZ3TM"},"agent_actions":{"view_html":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ","download_json":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ.json","view_paper":"https://pith.science/paper/CWWXZ3TM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13343&json=true","fetch_graph":"https://pith.science/api/pith-number/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/action/storage_attestation","attest_author":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/action/author_attestation","sign_citation":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/action/citation_signature","submit_replication":"https://pith.science/pith/CWWXZ3TMWAY3TEJ4O5AIW6CIYQ/action/replication_record"}},"created_at":"2026-07-05T10:33:01.621503+00:00","updated_at":"2026-07-05T10:33:01.621503+00:00"}