{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K3HJZOWD3NKLQAP7KQOBGKBYLP","short_pith_number":"pith:K3HJZOWD","schema_version":"1.0","canonical_sha256":"56ce9cbac3db54b801ff541c1328385bcdd2f2a881e1847828d81a49b738fba5","source":{"kind":"arxiv","id":"2506.03951","version":2},"attestation_state":"computed","paper":{"title":"Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aojun Lu, Hangjie Yuan, Tao Feng, Yanan Sun","submitted_at":"2025-06-04T13:40:41Z","abstract_excerpt":"The quest for Continual Learning (CL) seeks to empower neural networks with the ability to learn and adapt incrementally. Central to this pursuit is addressing the stability-plasticity dilemma, which involves striking a balance between two conflicting objectives: preserving previously learned knowledge and acquiring new knowledge. While numerous CL methods aim to achieve this trade-off, they often overlook the impact of network architecture on stability and plasticity, restricting the trade-off to the parameter level. In this paper, we delve into the conflict between stability and plasticity a"},"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":"2506.03951","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T13:40:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"eb65357f93b7a519157f44fefd341d61226471c8755c364c5b72982a1c62f26f","abstract_canon_sha256":"dd05431f58957a66d9b2c246bd074eec32905b1ccf831f762e201cacf0c780b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:10.178340Z","signature_b64":"Pc+P+VGUHj3PUfGhTHlKdcYviIBm4gA2fx5OjH5sSAKwjp8MgZZqoBX644RAUYm+41jzAmlVBGMtH/4ZydGoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ce9cbac3db54b801ff541c1328385bcdd2f2a881e1847828d81a49b738fba5","last_reissued_at":"2026-07-05T11:16:10.177647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:10.177647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aojun Lu, Hangjie Yuan, Tao Feng, Yanan Sun","submitted_at":"2025-06-04T13:40:41Z","abstract_excerpt":"The quest for Continual Learning (CL) seeks to empower neural networks with the ability to learn and adapt incrementally. Central to this pursuit is addressing the stability-plasticity dilemma, which involves striking a balance between two conflicting objectives: preserving previously learned knowledge and acquiring new knowledge. While numerous CL methods aim to achieve this trade-off, they often overlook the impact of network architecture on stability and plasticity, restricting the trade-off to the parameter level. In this paper, we delve into the conflict between stability and plasticity a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03951","kind":"arxiv","version":2},"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/2506.03951/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":"2506.03951","created_at":"2026-07-05T11:16:10.177737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03951v2","created_at":"2026-07-05T11:16:10.177737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03951","created_at":"2026-07-05T11:16:10.177737+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3HJZOWD3NKL","created_at":"2026-07-05T11:16:10.177737+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3HJZOWD3NKLQAP7","created_at":"2026-07-05T11:16:10.177737+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3HJZOWD","created_at":"2026-07-05T11:16:10.177737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17889","citing_title":"Dimensionality Controls When Modularity Helps in Continual Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15775","citing_title":"Continual Learning of Domain-Invariant Representations","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03938","citing_title":"FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10973","citing_title":"Rotation-Preserving Supervised Fine-Tuning","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP","json":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP.json","graph_json":"https://pith.science/api/pith-number/K3HJZOWD3NKLQAP7KQOBGKBYLP/graph.json","events_json":"https://pith.science/api/pith-number/K3HJZOWD3NKLQAP7KQOBGKBYLP/events.json","paper":"https://pith.science/paper/K3HJZOWD"},"agent_actions":{"view_html":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP","download_json":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP.json","view_paper":"https://pith.science/paper/K3HJZOWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03951&json=true","fetch_graph":"https://pith.science/api/pith-number/K3HJZOWD3NKLQAP7KQOBGKBYLP/graph.json","fetch_events":"https://pith.science/api/pith-number/K3HJZOWD3NKLQAP7KQOBGKBYLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP/action/storage_attestation","attest_author":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP/action/author_attestation","sign_citation":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP/action/citation_signature","submit_replication":"https://pith.science/pith/K3HJZOWD3NKLQAP7KQOBGKBYLP/action/replication_record"}},"created_at":"2026-07-05T11:16:10.177737+00:00","updated_at":"2026-07-05T11:16:10.177737+00:00"}