{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7YW4X3S2BDTPVB7BMA6NHL27MH","short_pith_number":"pith:7YW4X3S2","schema_version":"1.0","canonical_sha256":"fe2dcbee5a08e6fa87e1603cd3af5f61c9f578c41e3d170d67b414da2a81acdf","source":{"kind":"arxiv","id":"2404.07518","version":3},"attestation_state":"computed","paper":{"title":"Remembering Transformer for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Arthur Juliani, Ippei Fujisawa, Jun Sakuma, Ryota Kanai, Yuwei Sun","submitted_at":"2024-04-11T07:22:14Z","abstract_excerpt":"Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task identity information during inference and cannot eliminate interference among different tasks, while soft parameter sharing approaches encounter the problem of an increasing model parameter size. To tackle these challenges, we propose the Remembering Transformer, inspired by the brain's Complementary Learning Systems (CLS). Remembering Transformer employs a mixtu"},"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":"2404.07518","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-11T07:22:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9b918e2a32a289f0fa9c82740b51fa120b585b2a6c7ac3824163570ca0be7866","abstract_canon_sha256":"07ee8152ad55e3514b1be4d58eb082067d6a8fa8e7487166dbddab8071d54036"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:43.880214Z","signature_b64":"EQ/GAQeHJTb5U10T9AnC02Xom/BwtUyqu8jmVK+T//StuX0t05/iUB8YaxE864XzXEPb2DIzV9r32RQHTxIxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe2dcbee5a08e6fa87e1603cd3af5f61c9f578c41e3d170d67b414da2a81acdf","last_reissued_at":"2026-07-05T08:19:43.879654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:43.879654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Remembering Transformer for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Arthur Juliani, Ippei Fujisawa, Jun Sakuma, Ryota Kanai, Yuwei Sun","submitted_at":"2024-04-11T07:22:14Z","abstract_excerpt":"Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task identity information during inference and cannot eliminate interference among different tasks, while soft parameter sharing approaches encounter the problem of an increasing model parameter size. To tackle these challenges, we propose the Remembering Transformer, inspired by the brain's Complementary Learning Systems (CLS). Remembering Transformer employs a mixtu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07518","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/2404.07518/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":"2404.07518","created_at":"2026-07-05T08:19:43.879716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07518v3","created_at":"2026-07-05T08:19:43.879716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07518","created_at":"2026-07-05T08:19:43.879716+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YW4X3S2BDTP","created_at":"2026-07-05T08:19:43.879716+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YW4X3S2BDTPVB7B","created_at":"2026-07-05T08:19:43.879716+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YW4X3S2","created_at":"2026-07-05T08:19:43.879716+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/7YW4X3S2BDTPVB7BMA6NHL27MH","json":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH.json","graph_json":"https://pith.science/api/pith-number/7YW4X3S2BDTPVB7BMA6NHL27MH/graph.json","events_json":"https://pith.science/api/pith-number/7YW4X3S2BDTPVB7BMA6NHL27MH/events.json","paper":"https://pith.science/paper/7YW4X3S2"},"agent_actions":{"view_html":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH","download_json":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH.json","view_paper":"https://pith.science/paper/7YW4X3S2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07518&json=true","fetch_graph":"https://pith.science/api/pith-number/7YW4X3S2BDTPVB7BMA6NHL27MH/graph.json","fetch_events":"https://pith.science/api/pith-number/7YW4X3S2BDTPVB7BMA6NHL27MH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH/action/storage_attestation","attest_author":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH/action/author_attestation","sign_citation":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH/action/citation_signature","submit_replication":"https://pith.science/pith/7YW4X3S2BDTPVB7BMA6NHL27MH/action/replication_record"}},"created_at":"2026-07-05T08:19:43.879716+00:00","updated_at":"2026-07-05T08:19:43.879716+00:00"}