{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VU26E7KJWLGWO4X6VUVHG4P2AM","short_pith_number":"pith:VU26E7KJ","schema_version":"1.0","canonical_sha256":"ad35e27d49b2cd6772fead2a7371fa0319519d91a713ca986b0bc136bd51adae","source":{"kind":"arxiv","id":"2605.26252","version":1},"attestation_state":"computed","paper":{"title":"Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Abdelghny Orogat, Essam Mansour","submitted_at":"2026-05-25T18:22:42Z","abstract_excerpt":"Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as storage. They localize correctness at records, embeddings, or edges. Each supplies only some of the capabilities that long-term memory requires. The result is four recurring failure modes: unregulated growth, missing semantic revision, capacity-driven forgetting, and read-only retrieval. In our vision, long-term agent memory is a new data-management workload. Its c"},"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":"2605.26252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-25T18:22:42Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"486200e297bf2310fe4abb6542c4d9fb8386ea12a8cd3dd4ccd04f5d5b16466b","abstract_canon_sha256":"9344e00735e84271a21e322095fd0c3236f3e1a0c59d10bf7071f00f85520854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:08.269504Z","signature_b64":"I7PEgPiQS6v1V8iNtpDb/86MsK+uyR8CB0b08H/NcLdvY7/l1qCZmLAfHvdOSaLYgeSV7I772JBpqtNF1Hu1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad35e27d49b2cd6772fead2a7371fa0319519d91a713ca986b0bc136bd51adae","last_reissued_at":"2026-05-27T01:05:08.268352Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:08.268352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Abdelghny Orogat, Essam Mansour","submitted_at":"2026-05-25T18:22:42Z","abstract_excerpt":"Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as storage. They localize correctness at records, embeddings, or edges. Each supplies only some of the capabilities that long-term memory requires. The result is four recurring failure modes: unregulated growth, missing semantic revision, capacity-driven forgetting, and read-only retrieval. In our vision, long-term agent memory is a new data-management workload. Its c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26252","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/2605.26252/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":"2605.26252","created_at":"2026-05-27T01:05:08.268520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26252v1","created_at":"2026-05-27T01:05:08.268520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26252","created_at":"2026-05-27T01:05:08.268520+00:00"},{"alias_kind":"pith_short_12","alias_value":"VU26E7KJWLGW","created_at":"2026-05-27T01:05:08.268520+00:00"},{"alias_kind":"pith_short_16","alias_value":"VU26E7KJWLGWO4X6","created_at":"2026-05-27T01:05:08.268520+00:00"},{"alias_kind":"pith_short_8","alias_value":"VU26E7KJ","created_at":"2026-05-27T01:05:08.268520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM","json":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM.json","graph_json":"https://pith.science/api/pith-number/VU26E7KJWLGWO4X6VUVHG4P2AM/graph.json","events_json":"https://pith.science/api/pith-number/VU26E7KJWLGWO4X6VUVHG4P2AM/events.json","paper":"https://pith.science/paper/VU26E7KJ"},"agent_actions":{"view_html":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM","download_json":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM.json","view_paper":"https://pith.science/paper/VU26E7KJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26252&json=true","fetch_graph":"https://pith.science/api/pith-number/VU26E7KJWLGWO4X6VUVHG4P2AM/graph.json","fetch_events":"https://pith.science/api/pith-number/VU26E7KJWLGWO4X6VUVHG4P2AM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM/action/storage_attestation","attest_author":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM/action/author_attestation","sign_citation":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM/action/citation_signature","submit_replication":"https://pith.science/pith/VU26E7KJWLGWO4X6VUVHG4P2AM/action/replication_record"}},"created_at":"2026-05-27T01:05:08.268520+00:00","updated_at":"2026-05-27T01:05:08.268520+00:00"}