{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5WTKH6XNQKBAGN22KHP7LUR3EY","short_pith_number":"pith:5WTKH6XN","schema_version":"1.0","canonical_sha256":"eda6a3faed828203375a51dff5d23b263549c4990f55e4e8f1252743aee65f9b","source":{"kind":"arxiv","id":"2403.18266","version":1},"attestation_state":"computed","paper":{"title":"Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng-Lin Liu, Fei Zhu, Wenzhuo Liu","submitted_at":"2024-03-27T05:38:48Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as an effective paradigm for deriving general representations from vast amounts of unlabeled data. However, as real-world applications continually integrate new content, the high computational and resource demands of SSL necessitate continual learning rather than complete retraining. This poses a challenge in striking a balance between stability and plasticity when adapting to new information. In this paper, we employ Centered Kernel Alignment for quantitatively analyzing model stability and plasticity, revealing the critical roles of batch normalizat"},"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":"2403.18266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T05:38:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ca24bf95c6221cb992a58c59c4fad445e9e1664ebee7cdc6a710655a8d235251","abstract_canon_sha256":"3bbf9ab1e2780575be36b94e1e8cd4ded27a7f3c1d2e45a759bdfbfb23fcf44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:07.003847Z","signature_b64":"bAxB3M95Qtvf35e+tyT/yyRcl5w6soFHD9b/OzSavivf9BiicoCQf/45ByDBIqa/wmvg2FXPJy0loKdXX5fNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eda6a3faed828203375a51dff5d23b263549c4990f55e4e8f1252743aee65f9b","last_reissued_at":"2026-07-05T08:01:07.003400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:07.003400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng-Lin Liu, Fei Zhu, Wenzhuo Liu","submitted_at":"2024-03-27T05:38:48Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as an effective paradigm for deriving general representations from vast amounts of unlabeled data. However, as real-world applications continually integrate new content, the high computational and resource demands of SSL necessitate continual learning rather than complete retraining. This poses a challenge in striking a balance between stability and plasticity when adapting to new information. In this paper, we employ Centered Kernel Alignment for quantitatively analyzing model stability and plasticity, revealing the critical roles of batch normalizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18266","kind":"arxiv","version":1},"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/2403.18266/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":"2403.18266","created_at":"2026-07-05T08:01:07.003469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18266v1","created_at":"2026-07-05T08:01:07.003469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18266","created_at":"2026-07-05T08:01:07.003469+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WTKH6XNQKBA","created_at":"2026-07-05T08:01:07.003469+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WTKH6XNQKBAGN22","created_at":"2026-07-05T08:01:07.003469+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WTKH6XN","created_at":"2026-07-05T08:01:07.003469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13941","citing_title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY","json":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY.json","graph_json":"https://pith.science/api/pith-number/5WTKH6XNQKBAGN22KHP7LUR3EY/graph.json","events_json":"https://pith.science/api/pith-number/5WTKH6XNQKBAGN22KHP7LUR3EY/events.json","paper":"https://pith.science/paper/5WTKH6XN"},"agent_actions":{"view_html":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY","download_json":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY.json","view_paper":"https://pith.science/paper/5WTKH6XN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18266&json=true","fetch_graph":"https://pith.science/api/pith-number/5WTKH6XNQKBAGN22KHP7LUR3EY/graph.json","fetch_events":"https://pith.science/api/pith-number/5WTKH6XNQKBAGN22KHP7LUR3EY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY/action/storage_attestation","attest_author":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY/action/author_attestation","sign_citation":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY/action/citation_signature","submit_replication":"https://pith.science/pith/5WTKH6XNQKBAGN22KHP7LUR3EY/action/replication_record"}},"created_at":"2026-07-05T08:01:07.003469+00:00","updated_at":"2026-07-05T08:01:07.003469+00:00"}