{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5LXCAUHLMOGMFHPN4ULDPXSJ72","short_pith_number":"pith:5LXCAUHL","schema_version":"1.0","canonical_sha256":"eaee2050eb638cc29dede51637de49febb36db66c4fa29e1e5cf803c0f697bfa","source":{"kind":"arxiv","id":"2302.08741","version":1},"attestation_state":"computed","paper":{"title":"New Insights for the Stability-Plasticity Dilemma in Online Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dahuin Jung, Dongjin Lee, Ho Bae, Hyemi Jang, Sungroh Yoon, Sunwon Hong","submitted_at":"2023-02-17T07:43:59Z","abstract_excerpt":"The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adapt"},"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":"2302.08741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-17T07:43:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"97682bf35d0cf88cee65242344cbecf4c67106146bc26ed6678be29bc1abbfc8","abstract_canon_sha256":"328022eb6bb82abddead422780150499302fe83e41f5e1431e2d82e09d81bef2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:54.271198Z","signature_b64":"M6BXP8HZqz8Z1DqHuoQuScdBx7s8Al3Ra3MfBNkbQ7gEPu6CfIAjfwR4Toxy1zD0S4iXO9UVZ/CB/IqjZ2r+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaee2050eb638cc29dede51637de49febb36db66c4fa29e1e5cf803c0f697bfa","last_reissued_at":"2026-07-05T05:42:54.270673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:54.270673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"New Insights for the Stability-Plasticity Dilemma in Online Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dahuin Jung, Dongjin Lee, Ho Bae, Hyemi Jang, Sungroh Yoon, Sunwon Hong","submitted_at":"2023-02-17T07:43:59Z","abstract_excerpt":"The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08741","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/2302.08741/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":"2302.08741","created_at":"2026-07-05T05:42:54.270729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.08741v1","created_at":"2026-07-05T05:42:54.270729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08741","created_at":"2026-07-05T05:42:54.270729+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LXCAUHLMOGM","created_at":"2026-07-05T05:42:54.270729+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LXCAUHLMOGMFHPN","created_at":"2026-07-05T05:42:54.270729+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LXCAUHL","created_at":"2026-07-05T05:42:54.270729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10637","citing_title":"A Simple Baseline for Stable and Plastic Neural Networks","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72","json":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72.json","graph_json":"https://pith.science/api/pith-number/5LXCAUHLMOGMFHPN4ULDPXSJ72/graph.json","events_json":"https://pith.science/api/pith-number/5LXCAUHLMOGMFHPN4ULDPXSJ72/events.json","paper":"https://pith.science/paper/5LXCAUHL"},"agent_actions":{"view_html":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72","download_json":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72.json","view_paper":"https://pith.science/paper/5LXCAUHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.08741&json=true","fetch_graph":"https://pith.science/api/pith-number/5LXCAUHLMOGMFHPN4ULDPXSJ72/graph.json","fetch_events":"https://pith.science/api/pith-number/5LXCAUHLMOGMFHPN4ULDPXSJ72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72/action/storage_attestation","attest_author":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72/action/author_attestation","sign_citation":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72/action/citation_signature","submit_replication":"https://pith.science/pith/5LXCAUHLMOGMFHPN4ULDPXSJ72/action/replication_record"}},"created_at":"2026-07-05T05:42:54.270729+00:00","updated_at":"2026-07-05T05:42:54.270729+00:00"}