{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7JZJEC4YGOKJ4BCVLJV43YZPQZ","short_pith_number":"pith:7JZJEC4Y","schema_version":"1.0","canonical_sha256":"fa72920b9833949e04555a6bcde32f86416468bff330dbdd91a13f47b08e880f","source":{"kind":"arxiv","id":"2302.00487","version":3},"attestation_state":"computed","paper":{"title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hang Su, Jun Zhu, Liyuan Wang, Xingxing Zhang","submitted_at":"2023-01-31T11:34:56Z","abstract_excerpt":"To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance degradation of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual lear"},"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":"2302.00487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T11:34:56Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ab4a8811b6c852955dbae57471dd1e7ceddfbc84435f06b6cb8acb1ad6b52199","abstract_canon_sha256":"20a215f0946e60c76c135871c18575dfb87906a93476675d003ce917d74ac6e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:38.389122Z","signature_b64":"JYeIBYEUQUdPZr951CJ9kuF1H9azz8xomcgu+b2tP9Ts6P8lRxvLOkS3pGjHOdBc3UCzf420Oz4GJPSrsQwrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa72920b9833949e04555a6bcde32f86416468bff330dbdd91a13f47b08e880f","last_reissued_at":"2026-07-05T07:41:38.388658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:38.388658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hang Su, Jun Zhu, Liyuan Wang, Xingxing Zhang","submitted_at":"2023-01-31T11:34:56Z","abstract_excerpt":"To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance degradation of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00487","kind":"arxiv","version":3},"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/2302.00487/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":"2302.00487","created_at":"2026-07-05T07:41:38.388716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00487v3","created_at":"2026-07-05T07:41:38.388716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00487","created_at":"2026-07-05T07:41:38.388716+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JZJEC4YGOKJ","created_at":"2026-07-05T07:41:38.388716+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JZJEC4YGOKJ4BCV","created_at":"2026-07-05T07:41:38.388716+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JZJEC4Y","created_at":"2026-07-05T07:41:38.388716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22952","citing_title":"Domain-incremental audio classification using domain-specific experts and prototype classifier","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07474","citing_title":"Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00047","citing_title":"Comprehensive AI governance requires addressing non-model gains","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29498","citing_title":"Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20532","citing_title":"Hybrid Edge-HPC Systems for Low-Latency Data-Driven Inference","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23061","citing_title":"Anytime Training with Schedule-Free Spectral Optimization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16079","citing_title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20532","citing_title":"Hybrid Edge-HPC Systems for Low-Latency Data-Driven Inference","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15053","citing_title":"TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16079","citing_title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10973","citing_title":"Rotation-Preserving Supervised Fine-Tuning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05776","citing_title":"HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21598","citing_title":"You Don't Need Public Tests to Generate Correct Code","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18270","citing_title":"Incremental learning for audio classification with Hebbian Deep Neural Networks","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":198,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12874","citing_title":"LIFE -- an energy efficient advanced continual learning agentic AI framework for frontier systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16291","citing_title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ","json":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ.json","graph_json":"https://pith.science/api/pith-number/7JZJEC4YGOKJ4BCVLJV43YZPQZ/graph.json","events_json":"https://pith.science/api/pith-number/7JZJEC4YGOKJ4BCVLJV43YZPQZ/events.json","paper":"https://pith.science/paper/7JZJEC4Y"},"agent_actions":{"view_html":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ","download_json":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ.json","view_paper":"https://pith.science/paper/7JZJEC4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00487&json=true","fetch_graph":"https://pith.science/api/pith-number/7JZJEC4YGOKJ4BCVLJV43YZPQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7JZJEC4YGOKJ4BCVLJV43YZPQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ/action/storage_attestation","attest_author":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ/action/author_attestation","sign_citation":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ/action/citation_signature","submit_replication":"https://pith.science/pith/7JZJEC4YGOKJ4BCVLJV43YZPQZ/action/replication_record"}},"created_at":"2026-07-05T07:41:38.388716+00:00","updated_at":"2026-07-05T07:41:38.388716+00:00"}