{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OQHBPEW3WJMA2CP4LSDPI26PL7","short_pith_number":"pith:OQHBPEW3","schema_version":"1.0","canonical_sha256":"740e1792dbb2580d09fc5c86f46bcf5fd190939823f75f6931ed2a12a85d51a8","source":{"kind":"arxiv","id":"2211.15215","version":1},"attestation_state":"computed","paper":{"title":"Progressive Learning without Forgetting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ang Bian, Hangjie Yuan, Jianzhou Zhang, Mang Wang, Tao Feng, Ziyuan Huang","submitted_at":"2022-11-28T10:53:14Z","abstract_excerpt":"Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on two challenging problems in the paradigm of Continual Learning (CL) without involving any old data: (i) the accumulation of catastrophic forgetting caused by the gradually fading knowledge space from which the model learns the previous knowledge; (ii) the uncontrolled tug-of-war dynamics to balance the stability and plasticity during the learning of new tasks. In order to tackle these problems, we present Progressive"},"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":"2211.15215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T10:53:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"369de13ee2e3ac1ce6d59863291355e409024c1a116196bf28071d22d5c94dec","abstract_canon_sha256":"82520f0b26acb63ae2d0eebc352972a572685ff27ee82aac018903c8c3e239b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:00.865530Z","signature_b64":"tc/DBZEYJK5GkdwmgaYnb7a64WQ9CEUQBxlVKWke0d6Ywq0bUbaOfZhYY16pSqAcMwya6Z2KrzODXkRdPPSZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"740e1792dbb2580d09fc5c86f46bcf5fd190939823f75f6931ed2a12a85d51a8","last_reissued_at":"2026-07-05T05:20:00.865082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:00.865082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Learning without Forgetting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ang Bian, Hangjie Yuan, Jianzhou Zhang, Mang Wang, Tao Feng, Ziyuan Huang","submitted_at":"2022-11-28T10:53:14Z","abstract_excerpt":"Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on two challenging problems in the paradigm of Continual Learning (CL) without involving any old data: (i) the accumulation of catastrophic forgetting caused by the gradually fading knowledge space from which the model learns the previous knowledge; (ii) the uncontrolled tug-of-war dynamics to balance the stability and plasticity during the learning of new tasks. In order to tackle these problems, we present Progressive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15215","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/2211.15215/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":"2211.15215","created_at":"2026-07-05T05:20:00.865139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15215v1","created_at":"2026-07-05T05:20:00.865139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15215","created_at":"2026-07-05T05:20:00.865139+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQHBPEW3WJMA","created_at":"2026-07-05T05:20:00.865139+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQHBPEW3WJMA2CP4","created_at":"2026-07-05T05:20:00.865139+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQHBPEW3","created_at":"2026-07-05T05:20:00.865139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.06571","citing_title":"ModelScope Text-to-Video Technical Report","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18857","citing_title":"Task Switching Without Forgetting via Proximal Decoupling","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7","json":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7.json","graph_json":"https://pith.science/api/pith-number/OQHBPEW3WJMA2CP4LSDPI26PL7/graph.json","events_json":"https://pith.science/api/pith-number/OQHBPEW3WJMA2CP4LSDPI26PL7/events.json","paper":"https://pith.science/paper/OQHBPEW3"},"agent_actions":{"view_html":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7","download_json":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7.json","view_paper":"https://pith.science/paper/OQHBPEW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15215&json=true","fetch_graph":"https://pith.science/api/pith-number/OQHBPEW3WJMA2CP4LSDPI26PL7/graph.json","fetch_events":"https://pith.science/api/pith-number/OQHBPEW3WJMA2CP4LSDPI26PL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7/action/storage_attestation","attest_author":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7/action/author_attestation","sign_citation":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7/action/citation_signature","submit_replication":"https://pith.science/pith/OQHBPEW3WJMA2CP4LSDPI26PL7/action/replication_record"}},"created_at":"2026-07-05T05:20:00.865139+00:00","updated_at":"2026-07-05T05:20:00.865139+00:00"}