{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AOYDZ67TNULUG42JXM3SOCA52Y","short_pith_number":"pith:AOYDZ67T","schema_version":"1.0","canonical_sha256":"03b03cfbf36d17437349bb3727081dd607a4836d2d088a3930b6cfa5f31d139a","source":{"kind":"arxiv","id":"2605.05097","version":3},"attestation_state":"computed","paper":{"title":"Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Coupling fast and slow variables on knowledge-graph edges lets external memory adapt on its own for continual LLM updates.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Andreas Pattichis, Constantine Dovrolis","submitted_at":"2026-05-06T16:33:42Z","abstract_excerpt":"LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and"},"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":true},"canonical_record":{"source":{"id":"2605.05097","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-06T16:33:42Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"846c777b9d8a220276bc738f2d20d371024f5b10647aa49c70ad0f79fca44a73","abstract_canon_sha256":"9ddf7a565f98cb5f197af68c46b3b1750e1a8237d0dc1ea983054ef06f2b7fc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:53.748391Z","signature_b64":"NiQbQ+E/Qo2YFe+ariTWFPsq5y5A0Jltwv4NK6cWlvZWe2y4mQo0wg19Df7oS5cML7+DPGBImn47UTsTlGwZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03b03cfbf36d17437349bb3727081dd607a4836d2d088a3930b6cfa5f31d139a","last_reissued_at":"2026-06-25T01:17:53.747837Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:53.747837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Coupling fast and slow variables on knowledge-graph edges lets external memory adapt on its own for continual LLM updates.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Andreas Pattichis, Constantine Dovrolis","submitted_at":"2026-05-06T16:33:42Z","abstract_excerpt":"LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Benna-Fusi multi-timescale coupling, when placed on the edges of an LLM knowledge graph, will produce stable continual learning without introducing interference, scalability bottlenecks, or loss of previously consolidated knowledge.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Memini organizes LLM knowledge as a directed graph whose edges follow coupled fast-slow dynamics so that episodic recall, consolidation, and selective forgetting arise automatically from a single mechanism.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Coupling fast and slow variables on knowledge-graph edges lets external memory adapt on its own for continual LLM updates.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"513fae4c959da520176731ef54035c938b8c17cc2d5e2a7b118cf41214ef6721"},"source":{"id":"2605.05097","kind":"arxiv","version":3},"verdict":{"id":"6fa7af5d-429b-4df2-98b8-e27a0fda45ef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T18:08:36.065136Z","strongest_claim":"From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics.","one_line_summary":"Memini organizes LLM knowledge as a directed graph whose edges follow coupled fast-slow dynamics so that episodic recall, consolidation, and selective forgetting arise automatically from a single mechanism.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Benna-Fusi multi-timescale coupling, when placed on the edges of an LLM knowledge graph, will produce stable continual learning without introducing interference, scalability bottlenecks, or loss of previously consolidated knowledge.","pith_extraction_headline":"Coupling fast and slow variables on knowledge-graph edges lets external memory adapt on its own for continual LLM updates."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05097/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T10:37:43.284813Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.601930Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:50:07.744547Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2128df2ec109b8f96b036d3228818ddf9f3f8b8f9961d8b32145dee004f9f22a"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"67c6fae30e57087f56563c9f3d2d10cdc3b61e0a4b08566c38a6aee471437c50"},"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":"2605.05097","created_at":"2026-06-25T01:17:53.747896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.05097v3","created_at":"2026-06-25T01:17:53.747896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05097","created_at":"2026-06-25T01:17:53.747896+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOYDZ67TNULU","created_at":"2026-06-25T01:17:53.747896+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOYDZ67TNULUG42J","created_at":"2026-06-25T01:17:53.747896+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOYDZ67T","created_at":"2026-06-25T01:17:53.747896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y","json":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y.json","graph_json":"https://pith.science/api/pith-number/AOYDZ67TNULUG42JXM3SOCA52Y/graph.json","events_json":"https://pith.science/api/pith-number/AOYDZ67TNULUG42JXM3SOCA52Y/events.json","paper":"https://pith.science/paper/AOYDZ67T"},"agent_actions":{"view_html":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y","download_json":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y.json","view_paper":"https://pith.science/paper/AOYDZ67T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.05097&json=true","fetch_graph":"https://pith.science/api/pith-number/AOYDZ67TNULUG42JXM3SOCA52Y/graph.json","fetch_events":"https://pith.science/api/pith-number/AOYDZ67TNULUG42JXM3SOCA52Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y/action/storage_attestation","attest_author":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y/action/author_attestation","sign_citation":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y/action/citation_signature","submit_replication":"https://pith.science/pith/AOYDZ67TNULUG42JXM3SOCA52Y/action/replication_record"}},"created_at":"2026-06-25T01:17:53.747896+00:00","updated_at":"2026-06-25T01:17:53.747896+00:00"}