{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GOGTPS6FAD564HOTRCSMSSCDQV","short_pith_number":"pith:GOGTPS6F","schema_version":"1.0","canonical_sha256":"338d37cbc500fbee1dd388a4c94843857ca4af801526fba72c7347f04f5351a7","source":{"kind":"arxiv","id":"2307.02738","version":3},"attestation_state":"computed","paper":{"title":"RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SC"],"primary_cat":"cs.AI","authors_text":"Brandon Kynoch, Dwane van der Sluis, Hugo Latapie","submitted_at":"2023-07-06T02:51:54Z","abstract_excerpt":"Large Language Models (LLMs) have made extraordinary progress in the field of Artificial Intelligence and have demonstrated remarkable capabilities across a large variety of tasks and domains. However, as we venture closer to creating Artificial General Intelligence (AGI) systems, we recognize the need to supplement LLMs with long-term memory to overcome the context window limitation and more importantly, to create a foundation for sustained reasoning, cumulative learning and long-term user interaction. In this paper we propose RecallM, a novel architecture for providing LLMs with an adaptable"},"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":"2307.02738","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-06T02:51:54Z","cross_cats_sorted":["cs.CL","cs.SC"],"title_canon_sha256":"42f0d90fb19ecb72b6980dd511706c909b728b42adf3a70894bc06d26a5829c5","abstract_canon_sha256":"6fdff3be2656d958bc1df692e12d0ff268d2019dbcf9c5320516bb2c683fc055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:35.827801Z","signature_b64":"sFRAs6bgDuQ4Gbiq4Zgj5yN5tHuPm0G7Q7cPaeKbVyIcpoGM+ajFi1pkaclU2y3jEz6fqlPB9fjnLoXWycYUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"338d37cbc500fbee1dd388a4c94843857ca4af801526fba72c7347f04f5351a7","last_reissued_at":"2026-07-05T06:56:35.827435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:35.827435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SC"],"primary_cat":"cs.AI","authors_text":"Brandon Kynoch, Dwane van der Sluis, Hugo Latapie","submitted_at":"2023-07-06T02:51:54Z","abstract_excerpt":"Large Language Models (LLMs) have made extraordinary progress in the field of Artificial Intelligence and have demonstrated remarkable capabilities across a large variety of tasks and domains. However, as we venture closer to creating Artificial General Intelligence (AGI) systems, we recognize the need to supplement LLMs with long-term memory to overcome the context window limitation and more importantly, to create a foundation for sustained reasoning, cumulative learning and long-term user interaction. In this paper we propose RecallM, a novel architecture for providing LLMs with an adaptable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02738","kind":"arxiv","version":3},"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/2307.02738/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":"2307.02738","created_at":"2026-07-05T06:56:35.827492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02738v3","created_at":"2026-07-05T06:56:35.827492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02738","created_at":"2026-07-05T06:56:35.827492+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOGTPS6FAD56","created_at":"2026-07-05T06:56:35.827492+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOGTPS6FAD564HOT","created_at":"2026-07-05T06:56:35.827492+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOGTPS6F","created_at":"2026-07-05T06:56:35.827492+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/GOGTPS6FAD564HOTRCSMSSCDQV","json":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV.json","graph_json":"https://pith.science/api/pith-number/GOGTPS6FAD564HOTRCSMSSCDQV/graph.json","events_json":"https://pith.science/api/pith-number/GOGTPS6FAD564HOTRCSMSSCDQV/events.json","paper":"https://pith.science/paper/GOGTPS6F"},"agent_actions":{"view_html":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV","download_json":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV.json","view_paper":"https://pith.science/paper/GOGTPS6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02738&json=true","fetch_graph":"https://pith.science/api/pith-number/GOGTPS6FAD564HOTRCSMSSCDQV/graph.json","fetch_events":"https://pith.science/api/pith-number/GOGTPS6FAD564HOTRCSMSSCDQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV/action/storage_attestation","attest_author":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV/action/author_attestation","sign_citation":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV/action/citation_signature","submit_replication":"https://pith.science/pith/GOGTPS6FAD564HOTRCSMSSCDQV/action/replication_record"}},"created_at":"2026-07-05T06:56:35.827492+00:00","updated_at":"2026-07-05T06:56:35.827492+00:00"}