{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZOHG4JED2ORCC5QALWE7RNFZUI","short_pith_number":"pith:ZOHG4JED","schema_version":"1.0","canonical_sha256":"cb8e6e2483d3a22176005d89f8b4b9a20c2e68595a933822843e3a8803d06625","source":{"kind":"arxiv","id":"2605.14802","version":1},"attestation_state":"computed","paper":{"title":"A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lin Hujite, Li Yingshuo, Tu Haomiao, Wang Huan, Zhao Yang","submitted_at":"2026-05-14T13:12:49Z","abstract_excerpt":"Large language models often suffer from fact loss, timeline confusion, persona drift, and reduced stability during long-range interaction, especially under high-noise knowledge bases, context clearing, and cross-model transfer. To address these issues, we introduce ARPM, an external temporal memory governance framework for long-term dialogue. ARPM separates static knowledge memory from dynamic dialogue experience memory and combines vector retrieval, BM25, RRF fusion, dual-temporal reranking, chronological evidence reading, and a controlled analysis protocol for evidence verification and answe"},"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":"2605.14802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T13:12:49Z","cross_cats_sorted":[],"title_canon_sha256":"4053d8a8d966d002750d3084b136f617c8d44b0e37468913006b3b073f372a2d","abstract_canon_sha256":"ec24cf6b49a75c74b12d91cb85afa25bb7f47d4da21c714edd37e28a07781a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.345614Z","signature_b64":"/efR2An94M9SqmMxWTWA4Womou/daX05cDgDaHrMeD4E2RCQGGvNA6j94SNa4T5EHLdsMBqnKjG8RAb2eMhdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb8e6e2483d3a22176005d89f8b4b9a20c2e68595a933822843e3a8803d06625","last_reissued_at":"2026-05-17T23:38:58.344781Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.344781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Heterogeneous Temporal Memory Governance Framework for Long-Term LLM Persona Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lin Hujite, Li Yingshuo, Tu Haomiao, Wang Huan, Zhao Yang","submitted_at":"2026-05-14T13:12:49Z","abstract_excerpt":"Large language models often suffer from fact loss, timeline confusion, persona drift, and reduced stability during long-range interaction, especially under high-noise knowledge bases, context clearing, and cross-model transfer. To address these issues, we introduce ARPM, an external temporal memory governance framework for long-term dialogue. ARPM separates static knowledge memory from dynamic dialogue experience memory and combines vector retrieval, BM25, RRF fusion, dual-temporal reranking, chronological evidence reading, and a controlled analysis protocol for evidence verification and answe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14802","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":""},"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":"2605.14802","created_at":"2026-05-17T23:38:58.344922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14802v1","created_at":"2026-05-17T23:38:58.344922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14802","created_at":"2026-05-17T23:38:58.344922+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOHG4JED2ORC","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOHG4JED2ORCC5QA","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOHG4JED","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.01248","citing_title":"A Practice Auditing Framework for Large Language Model Use: Collective Empiricism, Pseudo-Rational Cognition, and Governance of AI-Generated Content","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI","json":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI.json","graph_json":"https://pith.science/api/pith-number/ZOHG4JED2ORCC5QALWE7RNFZUI/graph.json","events_json":"https://pith.science/api/pith-number/ZOHG4JED2ORCC5QALWE7RNFZUI/events.json","paper":"https://pith.science/paper/ZOHG4JED"},"agent_actions":{"view_html":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI","download_json":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI.json","view_paper":"https://pith.science/paper/ZOHG4JED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14802&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOHG4JED2ORCC5QALWE7RNFZUI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOHG4JED2ORCC5QALWE7RNFZUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI/action/storage_attestation","attest_author":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI/action/author_attestation","sign_citation":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI/action/citation_signature","submit_replication":"https://pith.science/pith/ZOHG4JED2ORCC5QALWE7RNFZUI/action/replication_record"}},"created_at":"2026-05-17T23:38:58.344922+00:00","updated_at":"2026-05-17T23:38:58.344922+00:00"}