{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RZKHOAEL5L3744O3TV5DV3P2FD","short_pith_number":"pith:RZKHOAEL","schema_version":"1.0","canonical_sha256":"8e5477008beaf7fe71db9d7a3aedfa28cbb2ab347e790999a0454e09a7768d40","source":{"kind":"arxiv","id":"2502.06210","version":2},"attestation_state":"computed","paper":{"title":"Achieving Deep Continual Learning via Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aojun Lu, Chunhui Ding, Jiahao Fan, Jiancheng Lv, Junchao Ke, Yanan Sun","submitted_at":"2025-02-10T07:21:44Z","abstract_excerpt":"Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the collective learning mechanisms of human populations, we introduce Evolving Continual Learning (ECL), a framework that maintains and evolves a diverse population of neural network models. ECL continually searches for an optimal architecture for each introduced incremental task. This tailored model is trained on the corresponding task and archived as a specialized exp"},"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":"2502.06210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T07:21:44Z","cross_cats_sorted":[],"title_canon_sha256":"f5c5ee8ef79533e07857ea8813f26327cadd99c4e3669b7a17a60554fc1e2ab9","abstract_canon_sha256":"d3eed2a6e02d4e5f3c84b4c1dd5fb4275b920892cbe2486a5ddaab07f70b7682"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:55.829756Z","signature_b64":"hPqzLP6M5ic4QanS/ceoSykGV0qzsQUyn8UUWT6zdCdiSWKhl7nyKOrOBxOSnEzsB5e3dTWyqptcIqvQgbHbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e5477008beaf7fe71db9d7a3aedfa28cbb2ab347e790999a0454e09a7768d40","last_reissued_at":"2026-07-05T11:45:55.829132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:55.829132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Deep Continual Learning via Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aojun Lu, Chunhui Ding, Jiahao Fan, Jiancheng Lv, Junchao Ke, Yanan Sun","submitted_at":"2025-02-10T07:21:44Z","abstract_excerpt":"Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the collective learning mechanisms of human populations, we introduce Evolving Continual Learning (ECL), a framework that maintains and evolves a diverse population of neural network models. ECL continually searches for an optimal architecture for each introduced incremental task. This tailored model is trained on the corresponding task and archived as a specialized exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06210","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/2502.06210/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":"2502.06210","created_at":"2026-07-05T11:45:55.829203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06210v2","created_at":"2026-07-05T11:45:55.829203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06210","created_at":"2026-07-05T11:45:55.829203+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZKHOAEL5L37","created_at":"2026-07-05T11:45:55.829203+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZKHOAEL5L3744O3","created_at":"2026-07-05T11:45:55.829203+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZKHOAEL","created_at":"2026-07-05T11:45:55.829203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10457","citing_title":"SEAL: Searching Expandable Architectures for Incremental Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD","json":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD.json","graph_json":"https://pith.science/api/pith-number/RZKHOAEL5L3744O3TV5DV3P2FD/graph.json","events_json":"https://pith.science/api/pith-number/RZKHOAEL5L3744O3TV5DV3P2FD/events.json","paper":"https://pith.science/paper/RZKHOAEL"},"agent_actions":{"view_html":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD","download_json":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD.json","view_paper":"https://pith.science/paper/RZKHOAEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06210&json=true","fetch_graph":"https://pith.science/api/pith-number/RZKHOAEL5L3744O3TV5DV3P2FD/graph.json","fetch_events":"https://pith.science/api/pith-number/RZKHOAEL5L3744O3TV5DV3P2FD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD/action/storage_attestation","attest_author":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD/action/author_attestation","sign_citation":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD/action/citation_signature","submit_replication":"https://pith.science/pith/RZKHOAEL5L3744O3TV5DV3P2FD/action/replication_record"}},"created_at":"2026-07-05T11:45:55.829203+00:00","updated_at":"2026-07-05T11:45:55.829203+00:00"}