{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MK3FVVDHUA57KQKISHUXHUQUCX","short_pith_number":"pith:MK3FVVDH","schema_version":"1.0","canonical_sha256":"62b65ad467a03bf5414891e973d21415c7621ff107b6657644f106d6c6adb86b","source":{"kind":"arxiv","id":"2303.07223","version":2},"attestation_state":"computed","paper":{"title":"PromptFusion: Decoupling Stability and Plasticity for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Chen, Menglin Jia, Xintong Han, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2023-03-13T15:58:00Z","abstract_excerpt":"Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming tasks. Such a trade-off is referred to as the stability-plasticity dilemma and is a more general and challenging problem for continual learning. However, the inherent conflict between these two concepts makes it seemingly impossible to devise a satisfactory solution to both of them simultaneously. Therefore, we ask, \"is it possible to divide them into two separate problems to conquer them independently?\". To this end,"},"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":"2303.07223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T15:58:00Z","cross_cats_sorted":[],"title_canon_sha256":"3678389563afe9e204a880c393b1ebf99c3cb42c6ed1ce57915d20ead7eabce0","abstract_canon_sha256":"d7438afc13b0ccf68d23c6ab056346610c9cfffc6133e0554aae6e1acb107ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:58.493897Z","signature_b64":"kNJRLyLfPXXnk+C29GMwog0pjV0+RpIsezj2h0pJvbKjle6Xw5Zr/PzVqtCh4cthX86+qoS9ZjUEMmkid8U7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62b65ad467a03bf5414891e973d21415c7621ff107b6657644f106d6c6adb86b","last_reissued_at":"2026-07-05T08:41:58.493566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:58.493566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptFusion: Decoupling Stability and Plasticity for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Chen, Menglin Jia, Xintong Han, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2023-03-13T15:58:00Z","abstract_excerpt":"Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming tasks. Such a trade-off is referred to as the stability-plasticity dilemma and is a more general and challenging problem for continual learning. However, the inherent conflict between these two concepts makes it seemingly impossible to devise a satisfactory solution to both of them simultaneously. Therefore, we ask, \"is it possible to divide them into two separate problems to conquer them independently?\". To this end,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07223","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/2303.07223/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":"2303.07223","created_at":"2026-07-05T08:41:58.493618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07223v2","created_at":"2026-07-05T08:41:58.493618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07223","created_at":"2026-07-05T08:41:58.493618+00:00"},{"alias_kind":"pith_short_12","alias_value":"MK3FVVDHUA57","created_at":"2026-07-05T08:41:58.493618+00:00"},{"alias_kind":"pith_short_16","alias_value":"MK3FVVDHUA57KQKI","created_at":"2026-07-05T08:41:58.493618+00:00"},{"alias_kind":"pith_short_8","alias_value":"MK3FVVDH","created_at":"2026-07-05T08:41:58.493618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21588","citing_title":"Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX","json":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX.json","graph_json":"https://pith.science/api/pith-number/MK3FVVDHUA57KQKISHUXHUQUCX/graph.json","events_json":"https://pith.science/api/pith-number/MK3FVVDHUA57KQKISHUXHUQUCX/events.json","paper":"https://pith.science/paper/MK3FVVDH"},"agent_actions":{"view_html":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX","download_json":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX.json","view_paper":"https://pith.science/paper/MK3FVVDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07223&json=true","fetch_graph":"https://pith.science/api/pith-number/MK3FVVDHUA57KQKISHUXHUQUCX/graph.json","fetch_events":"https://pith.science/api/pith-number/MK3FVVDHUA57KQKISHUXHUQUCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX/action/storage_attestation","attest_author":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX/action/author_attestation","sign_citation":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX/action/citation_signature","submit_replication":"https://pith.science/pith/MK3FVVDHUA57KQKISHUXHUQUCX/action/replication_record"}},"created_at":"2026-07-05T08:41:58.493618+00:00","updated_at":"2026-07-05T08:41:58.493618+00:00"}