{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GTC4GNDWI7ITITKDXREMJ3Y665","short_pith_number":"pith:GTC4GNDW","schema_version":"1.0","canonical_sha256":"34c5c3347647d1344d43bc48c4ef1ef74c4ddcfbb3f036170d0420306b60fb99","source":{"kind":"arxiv","id":"2602.19320","version":2},"attestation_state":"computed","paper":{"title":"Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alysa Zhao, Ayushi Kishore, Bingzhe Li, Dingyi Kang, Dongming Jiang, Feng Chen, Jinxin Yang, Qiannan Li, Songtao Wei, Xu Hu, Yi Li","submitted_at":"2026-02-22T19:50:01Z","abstract_excerpt":"Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain fragile: existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models, and system-level costs are frequently overlooked. This survey presents a structured analysis of agentic memory from both architectural and system persp"},"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":"2602.19320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-22T19:50:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35fe0407f3a88d10a731e0e88eddb2c437949a48b0791a13e15f884b1888a9b5","abstract_canon_sha256":"e9b07fe74816a101f579b5feb01dbd187aa4dce4e9f90b80f0c1969ac7865a64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:23.601350Z","signature_b64":"eXMu6donWe1sfIIZjqmp+4Oolo1uJnxr2VHxxQA1UD25f/fDV8EVdZP7o35AuGlYi1GnRBMKcgUVWbn+/fDZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c5c3347647d1344d43bc48c4ef1ef74c4ddcfbb3f036170d0420306b60fb99","last_reissued_at":"2026-05-21T01:04:23.600449Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:23.600449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alysa Zhao, Ayushi Kishore, Bingzhe Li, Dingyi Kang, Dongming Jiang, Feng Chen, Jinxin Yang, Qiannan Li, Songtao Wei, Xu Hu, Yi Li","submitted_at":"2026-02-22T19:50:01Z","abstract_excerpt":"Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain fragile: existing benchmarks are often underscaled, evaluation metrics are misaligned with semantic utility, performance varies significantly across backbone models, and system-level costs are frequently overlooked. This survey presents a structured analysis of agentic memory from both architectural and system persp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19320","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/2602.19320/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":"2602.19320","created_at":"2026-05-21T01:04:23.600579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.19320v2","created_at":"2026-05-21T01:04:23.600579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19320","created_at":"2026-05-21T01:04:23.600579+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTC4GNDWI7IT","created_at":"2026-05-21T01:04:23.600579+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTC4GNDWI7ITITKD","created_at":"2026-05-21T01:04:23.600579+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTC4GNDW","created_at":"2026-05-21T01:04:23.600579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.23071","citing_title":"The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09942","citing_title":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11364","citing_title":"The Missing Knowledge Layer in Cognitive Architectures for AI Agents","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07313","citing_title":"When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13453","citing_title":"FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15065","citing_title":"Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665","json":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665.json","graph_json":"https://pith.science/api/pith-number/GTC4GNDWI7ITITKDXREMJ3Y665/graph.json","events_json":"https://pith.science/api/pith-number/GTC4GNDWI7ITITKDXREMJ3Y665/events.json","paper":"https://pith.science/paper/GTC4GNDW"},"agent_actions":{"view_html":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665","download_json":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665.json","view_paper":"https://pith.science/paper/GTC4GNDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.19320&json=true","fetch_graph":"https://pith.science/api/pith-number/GTC4GNDWI7ITITKDXREMJ3Y665/graph.json","fetch_events":"https://pith.science/api/pith-number/GTC4GNDWI7ITITKDXREMJ3Y665/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665/action/storage_attestation","attest_author":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665/action/author_attestation","sign_citation":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665/action/citation_signature","submit_replication":"https://pith.science/pith/GTC4GNDWI7ITITKDXREMJ3Y665/action/replication_record"}},"created_at":"2026-05-21T01:04:23.600579+00:00","updated_at":"2026-05-21T01:04:23.600579+00:00"}