{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VVRMG6YTYIPIOHIM5GWF2IB5NP","short_pith_number":"pith:VVRMG6YT","schema_version":"1.0","canonical_sha256":"ad62c37b13c21e871d0ce9ac5d203d6be5f98503423bcfa78e5c2a3592ea8a6e","source":{"kind":"arxiv","id":"2404.16789","version":3},"attestation_state":"computed","paper":{"title":"Continual Learning of Large Language Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Haizhou Shi, Hao Wang, Hengyi Wang, Sayna Ebrahimi, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Zihao Xu","submitted_at":"2024-04-25T17:38:57Z","abstract_excerpt":"The recent success of large language models (LLMs) trained on static, pre-collected, general datasets has sparked numerous research directions and applications. One such direction addresses the non-trivial challenge of integrating pre-trained LLMs into dynamic data distributions, task structures, and user preferences. Pre-trained LLMs, when tailored for specific needs, often experience significant performance degradation in previous knowledge domains -- a phenomenon known as \"catastrophic forgetting\". While extensively studied in the continual learning (CL) community, it presents new manifesta"},"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":"2404.16789","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-25T17:38:57Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7fbde48446e8de3a3296c1a32e8c40b8b8748917b47b3ae0b2ded7b3176f0f51","abstract_canon_sha256":"ae65de234773595f914614440121361d734a0079b9d01feaa02f429acec7d68a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:54.451850Z","signature_b64":"BrUq1oAGpchtpvQXDMY+d2wwv+/hg1ARAVntTHLomExvc08I1af+UvbLmAIYLK2V+1zYeQPdwc+osJFRsiczDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad62c37b13c21e871d0ce9ac5d203d6be5f98503423bcfa78e5c2a3592ea8a6e","last_reissued_at":"2026-07-05T09:39:54.451425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:54.451425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning of Large Language Models: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Haizhou Shi, Hao Wang, Hengyi Wang, Sayna Ebrahimi, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Zihao Xu","submitted_at":"2024-04-25T17:38:57Z","abstract_excerpt":"The recent success of large language models (LLMs) trained on static, pre-collected, general datasets has sparked numerous research directions and applications. One such direction addresses the non-trivial challenge of integrating pre-trained LLMs into dynamic data distributions, task structures, and user preferences. Pre-trained LLMs, when tailored for specific needs, often experience significant performance degradation in previous knowledge domains -- a phenomenon known as \"catastrophic forgetting\". While extensively studied in the continual learning (CL) community, it presents new manifesta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16789","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/2404.16789/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":"2404.16789","created_at":"2026-07-05T09:39:54.451476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16789v3","created_at":"2026-07-05T09:39:54.451476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16789","created_at":"2026-07-05T09:39:54.451476+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVRMG6YTYIPI","created_at":"2026-07-05T09:39:54.451476+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVRMG6YTYIPIOHIM","created_at":"2026-07-05T09:39:54.451476+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVRMG6YT","created_at":"2026-07-05T09:39:54.451476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19172","citing_title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21089","citing_title":"Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18024","citing_title":"Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02398","citing_title":"A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30857","citing_title":"MADS: Model-Aware Diverse Core Set Selection for Instruction Tuning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26104","citing_title":"Assert, don't describe: Linguistic features that shift LLM reasoning about animal welfare","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14387","citing_title":"SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2502.14802","citing_title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19089","citing_title":"Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP","json":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP.json","graph_json":"https://pith.science/api/pith-number/VVRMG6YTYIPIOHIM5GWF2IB5NP/graph.json","events_json":"https://pith.science/api/pith-number/VVRMG6YTYIPIOHIM5GWF2IB5NP/events.json","paper":"https://pith.science/paper/VVRMG6YT"},"agent_actions":{"view_html":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP","download_json":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP.json","view_paper":"https://pith.science/paper/VVRMG6YT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16789&json=true","fetch_graph":"https://pith.science/api/pith-number/VVRMG6YTYIPIOHIM5GWF2IB5NP/graph.json","fetch_events":"https://pith.science/api/pith-number/VVRMG6YTYIPIOHIM5GWF2IB5NP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP/action/storage_attestation","attest_author":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP/action/author_attestation","sign_citation":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP/action/citation_signature","submit_replication":"https://pith.science/pith/VVRMG6YTYIPIOHIM5GWF2IB5NP/action/replication_record"}},"created_at":"2026-07-05T09:39:54.451476+00:00","updated_at":"2026-07-05T09:39:54.451476+00:00"}