{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G7NA2K3HAYWRRF4MYXCXZZGCOI","short_pith_number":"pith:G7NA2K3H","schema_version":"1.0","canonical_sha256":"37da0d2b67062d18978cc5c57ce4c2723b75e06a30d54dca2feac5373f627b8c","source":{"kind":"arxiv","id":"2411.00489","version":2},"attestation_state":"computed","paper":{"title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fan Zhang, Hao Zheng, Junxiao Shen, Laurence Aitchison, Matt W. Jones, Miao Liu, Per Ola Kristensson, Weizhe Lin, Xuhai Xu, Zihong He","submitted_at":"2024-11-01T10:04:01Z","abstract_excerpt":"With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by introducing the mechanisms of human long-term"},"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":"2411.00489","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-01T10:04:01Z","cross_cats_sorted":[],"title_canon_sha256":"a101ef3851b909741356a0e952206c42902823f1628b0ae32a7dde642d2678c7","abstract_canon_sha256":"f047ba625393bf7a1be695665367e42fb601be974e10843daac0429e1e3033fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:54.917950Z","signature_b64":"yIz6T86k7Z9rYfYN5jHH4tUh5/WXhBik3mBA3prqgREOxo1YRpjyinIHNamd7EiYCPRbS8SRf9TQUKBSoy7ECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37da0d2b67062d18978cc5c57ce4c2723b75e06a30d54dca2feac5373f627b8c","last_reissued_at":"2026-07-05T09:59:54.917517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:54.917517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fan Zhang, Hao Zheng, Junxiao Shen, Laurence Aitchison, Matt W. Jones, Miao Liu, Per Ola Kristensson, Weizhe Lin, Xuhai Xu, Zihong He","submitted_at":"2024-11-01T10:04:01Z","abstract_excerpt":"With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by introducing the mechanisms of human long-term"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00489","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/2411.00489/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":"2411.00489","created_at":"2026-07-05T09:59:54.917575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00489v2","created_at":"2026-07-05T09:59:54.917575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00489","created_at":"2026-07-05T09:59:54.917575+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7NA2K3HAYWR","created_at":"2026-07-05T09:59:54.917575+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7NA2K3HAYWRRF4M","created_at":"2026-07-05T09:59:54.917575+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7NA2K3H","created_at":"2026-07-05T09:59:54.917575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01072","citing_title":"Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29141","citing_title":"Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30260","citing_title":"How LoRA Remembers? A Parametric Memory Law for LLM Finetuning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2508.03341","citing_title":"What Deserves Memory: Adaptive Memory Distillation for LLM Agents","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI","json":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI.json","graph_json":"https://pith.science/api/pith-number/G7NA2K3HAYWRRF4MYXCXZZGCOI/graph.json","events_json":"https://pith.science/api/pith-number/G7NA2K3HAYWRRF4MYXCXZZGCOI/events.json","paper":"https://pith.science/paper/G7NA2K3H"},"agent_actions":{"view_html":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI","download_json":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI.json","view_paper":"https://pith.science/paper/G7NA2K3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00489&json=true","fetch_graph":"https://pith.science/api/pith-number/G7NA2K3HAYWRRF4MYXCXZZGCOI/graph.json","fetch_events":"https://pith.science/api/pith-number/G7NA2K3HAYWRRF4MYXCXZZGCOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI/action/storage_attestation","attest_author":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI/action/author_attestation","sign_citation":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI/action/citation_signature","submit_replication":"https://pith.science/pith/G7NA2K3HAYWRRF4MYXCXZZGCOI/action/replication_record"}},"created_at":"2026-07-05T09:59:54.917575+00:00","updated_at":"2026-07-05T09:59:54.917575+00:00"}