{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WYXCY5SSLLLJAG6IDPSKNURBLP","short_pith_number":"pith:WYXCY5SS","schema_version":"1.0","canonical_sha256":"b62e2c76525ad6901bc81be4a6d2215bd153b808a0b43f147742f1ad408d1883","source":{"kind":"arxiv","id":"2505.22921","version":1},"attestation_state":"computed","paper":{"title":"Structured Memory Mechanisms for Stable Context Representation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Honghui Xin, Minggu Wei, Tao Yang, Yijiashun Qi, Yu Cheng, Yue Xing","submitted_at":"2025-05-28T22:49:04Z","abstract_excerpt":"This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to improve the retention and retrieval of semantic information across paragraphs and dialogue turns. The model integrates explicit memory units, gated writing mechanisms, and attention-based reading modules. A forgetting function is introduced to enable dynamic updates of memory content, enhancing the model's ability to manage historical information. To further improve the effectiveness of memory operations, the study desi"},"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":"2505.22921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T22:49:04Z","cross_cats_sorted":[],"title_canon_sha256":"9c7313f2b1b7ab00ff033cbcecea0bbc73e8b37be4757f15856685edace241da","abstract_canon_sha256":"88d4bd0591d61f7200721736e7ff56d5b654379b97bb31009ef070bc8930ede2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:51.805947Z","signature_b64":"3p8EBYRXwjkiRynZa1sy9JM5KNulXNm9wU4BM+OY1Te2t+jj1cIYg+Ynp3WLOe2j62un159hiGDYvbxNSDReAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b62e2c76525ad6901bc81be4a6d2215bd153b808a0b43f147742f1ad408d1883","last_reissued_at":"2026-07-05T11:11:51.805449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:51.805449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Memory Mechanisms for Stable Context Representation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Honghui Xin, Minggu Wei, Tao Yang, Yijiashun Qi, Yu Cheng, Yue Xing","submitted_at":"2025-05-28T22:49:04Z","abstract_excerpt":"This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to improve the retention and retrieval of semantic information across paragraphs and dialogue turns. The model integrates explicit memory units, gated writing mechanisms, and attention-based reading modules. A forgetting function is introduced to enable dynamic updates of memory content, enhancing the model's ability to manage historical information. To further improve the effectiveness of memory operations, the study desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22921","kind":"arxiv","version":1},"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/2505.22921/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":"2505.22921","created_at":"2026-07-05T11:11:51.805509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22921v1","created_at":"2026-07-05T11:11:51.805509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22921","created_at":"2026-07-05T11:11:51.805509+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYXCY5SSLLLJ","created_at":"2026-07-05T11:11:51.805509+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYXCY5SSLLLJAG6I","created_at":"2026-07-05T11:11:51.805509+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYXCY5SS","created_at":"2026-07-05T11:11:51.805509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04973","citing_title":"Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP","json":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP.json","graph_json":"https://pith.science/api/pith-number/WYXCY5SSLLLJAG6IDPSKNURBLP/graph.json","events_json":"https://pith.science/api/pith-number/WYXCY5SSLLLJAG6IDPSKNURBLP/events.json","paper":"https://pith.science/paper/WYXCY5SS"},"agent_actions":{"view_html":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP","download_json":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP.json","view_paper":"https://pith.science/paper/WYXCY5SS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22921&json=true","fetch_graph":"https://pith.science/api/pith-number/WYXCY5SSLLLJAG6IDPSKNURBLP/graph.json","fetch_events":"https://pith.science/api/pith-number/WYXCY5SSLLLJAG6IDPSKNURBLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP/action/storage_attestation","attest_author":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP/action/author_attestation","sign_citation":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP/action/citation_signature","submit_replication":"https://pith.science/pith/WYXCY5SSLLLJAG6IDPSKNURBLP/action/replication_record"}},"created_at":"2026-07-05T11:11:51.805509+00:00","updated_at":"2026-07-05T11:11:51.805509+00:00"}