{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UK2RBB4NOGQ3HWQEJODWA3APGO","short_pith_number":"pith:UK2RBB4N","schema_version":"1.0","canonical_sha256":"a2b510878d71a1b3da044b87606c0f33afe85d2620b5f1c63fa6d113a702486f","source":{"kind":"arxiv","id":"2605.17596","version":1},"attestation_state":"computed","paper":{"title":"NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daya Rajaratnam, Mujahid Sultan, Sri Thuraisamy","submitted_at":"2026-05-17T18:48:19Z","abstract_excerpt":"We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions via a hybrid neuro-symbolic architecture. NeuSymMS couples neural fact extraction from unstructured dialogue with a CLIPS-based expert system that classifies, deduplicates, and reconciles facts under explicit lifecycle rules. The system represents knowledge as subject-relation-value triples stored in relational database management system, supports user/agents/agent-to-agents scoping, and implements a dual-horizon short-term/long-term memory mo"},"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":"2605.17596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T18:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"06bacc7320a71d812d9553b18579749682a09c7dc76f15b0fd0ba4553a6d4dfb","abstract_canon_sha256":"23407ffdd298bd2b4dfc3955b258788f172310577cf2f1dc04ebfbbbf401512d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:47.787415Z","signature_b64":"vBYCVxgesw9tgwtRTPeqXeSbaYrHQHd5J2y9f5/pDo4TTHgyhVt3SS8c7HVrhSbOrlFHM1+Cmb88a9MghGUnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2b510878d71a1b3da044b87606c0f33afe85d2620b5f1c63fa6d113a702486f","last_reissued_at":"2026-05-20T00:04:47.786573Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:47.786573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daya Rajaratnam, Mujahid Sultan, Sri Thuraisamy","submitted_at":"2026-05-17T18:48:19Z","abstract_excerpt":"We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions via a hybrid neuro-symbolic architecture. NeuSymMS couples neural fact extraction from unstructured dialogue with a CLIPS-based expert system that classifies, deduplicates, and reconciles facts under explicit lifecycle rules. The system represents knowledge as subject-relation-value triples stored in relational database management system, supports user/agents/agent-to-agents scoping, and implements a dual-horizon short-term/long-term memory mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17596","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/2605.17596/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.579917Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.508100Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d1493318917bc6a0d20a0d967f89747766709c18d18acdd9a5e0cc5514944acb"},"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":"2605.17596","created_at":"2026-05-20T00:04:47.786705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17596v1","created_at":"2026-05-20T00:04:47.786705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17596","created_at":"2026-05-20T00:04:47.786705+00:00"},{"alias_kind":"pith_short_12","alias_value":"UK2RBB4NOGQ3","created_at":"2026-05-20T00:04:47.786705+00:00"},{"alias_kind":"pith_short_16","alias_value":"UK2RBB4NOGQ3HWQE","created_at":"2026-05-20T00:04:47.786705+00:00"},{"alias_kind":"pith_short_8","alias_value":"UK2RBB4N","created_at":"2026-05-20T00:04:47.786705+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/UK2RBB4NOGQ3HWQEJODWA3APGO","json":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO.json","graph_json":"https://pith.science/api/pith-number/UK2RBB4NOGQ3HWQEJODWA3APGO/graph.json","events_json":"https://pith.science/api/pith-number/UK2RBB4NOGQ3HWQEJODWA3APGO/events.json","paper":"https://pith.science/paper/UK2RBB4N"},"agent_actions":{"view_html":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO","download_json":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO.json","view_paper":"https://pith.science/paper/UK2RBB4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17596&json=true","fetch_graph":"https://pith.science/api/pith-number/UK2RBB4NOGQ3HWQEJODWA3APGO/graph.json","fetch_events":"https://pith.science/api/pith-number/UK2RBB4NOGQ3HWQEJODWA3APGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO/action/storage_attestation","attest_author":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO/action/author_attestation","sign_citation":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO/action/citation_signature","submit_replication":"https://pith.science/pith/UK2RBB4NOGQ3HWQEJODWA3APGO/action/replication_record"}},"created_at":"2026-05-20T00:04:47.786705+00:00","updated_at":"2026-05-20T00:04:47.786705+00:00"}