{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CUYRNK47EHB47XZPSPIE3F5STG","short_pith_number":"pith:CUYRNK47","schema_version":"1.0","canonical_sha256":"153116ab9f21c3cfdf2f93d04d97b299874bccf1e66eae047b7e291ddd4f3cf4","source":{"kind":"arxiv","id":"2410.13166","version":4},"attestation_state":"computed","paper":{"title":"An Evolved Universal Transformer Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Edoardo Cetin, Qi Sun, Tianyu Zhao, Yujin Tang","submitted_at":"2024-10-17T02:47:10Z","abstract_excerpt":"Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with Neural Attention Memory Models (NAMMs), introducing a learned network for memory management that improves both the performance and efficiency of transformers. We evolve NAMMs atop pre-trained transformers to provide different latent contexts focusing on the most relevant information for individual layers and attention heads. NAMMs are universally applicable"},"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":"2410.13166","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T02:47:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d05e4a558ae11fd2afc928e11ed0c1d63dfcdfc4ba9ab038298f88449001dd34","abstract_canon_sha256":"db2ee8ee21123f3a2b859e95586417ab78d5b5e45e7ba185fb100faa906eaaed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:44.000619Z","signature_b64":"aCs2gRNgNvmxKXE4yJcHEmEsXhyV335cUr2ltm6CgnARtEH/ZUBYhv8O5tc4x5gyq57Fx45gSt72y/cJjVvNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"153116ab9f21c3cfdf2f93d04d97b299874bccf1e66eae047b7e291ddd4f3cf4","last_reissued_at":"2026-07-05T10:13:44.000118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:44.000118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Evolved Universal Transformer Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Edoardo Cetin, Qi Sun, Tianyu Zhao, Yujin Tang","submitted_at":"2024-10-17T02:47:10Z","abstract_excerpt":"Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with Neural Attention Memory Models (NAMMs), introducing a learned network for memory management that improves both the performance and efficiency of transformers. We evolve NAMMs atop pre-trained transformers to provide different latent contexts focusing on the most relevant information for individual layers and attention heads. NAMMs are universally applicable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13166","kind":"arxiv","version":4},"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/2410.13166/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":"2410.13166","created_at":"2026-07-05T10:13:44.000180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13166v4","created_at":"2026-07-05T10:13:44.000180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13166","created_at":"2026-07-05T10:13:44.000180+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUYRNK47EHB4","created_at":"2026-07-05T10:13:44.000180+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUYRNK47EHB47XZP","created_at":"2026-07-05T10:13:44.000180+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUYRNK47","created_at":"2026-07-05T10:13:44.000180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00663","citing_title":"Titans: Learning to Memorize at Test Time","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG","json":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG.json","graph_json":"https://pith.science/api/pith-number/CUYRNK47EHB47XZPSPIE3F5STG/graph.json","events_json":"https://pith.science/api/pith-number/CUYRNK47EHB47XZPSPIE3F5STG/events.json","paper":"https://pith.science/paper/CUYRNK47"},"agent_actions":{"view_html":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG","download_json":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG.json","view_paper":"https://pith.science/paper/CUYRNK47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13166&json=true","fetch_graph":"https://pith.science/api/pith-number/CUYRNK47EHB47XZPSPIE3F5STG/graph.json","fetch_events":"https://pith.science/api/pith-number/CUYRNK47EHB47XZPSPIE3F5STG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG/action/storage_attestation","attest_author":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG/action/author_attestation","sign_citation":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG/action/citation_signature","submit_replication":"https://pith.science/pith/CUYRNK47EHB47XZPSPIE3F5STG/action/replication_record"}},"created_at":"2026-07-05T10:13:44.000180+00:00","updated_at":"2026-07-05T10:13:44.000180+00:00"}