{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JWUIBFZPLGYU3L44M2WJM6UOVT","short_pith_number":"pith:JWUIBFZP","schema_version":"1.0","canonical_sha256":"4da880972f59b14daf9c66ac967a8eaccce457010ba7cfa228199153ad7c65b8","source":{"kind":"arxiv","id":"2211.12701","version":2},"attestation_state":"computed","paper":{"title":"Continual Learning of Natural Language Processing Tasks: A Survey","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bing Liu, Zixuan Ke","submitted_at":"2022-11-23T04:46:28Z","abstract_excerpt":"Continual learning (CL) is a learning paradigm that emulates the human capability of learning and accumulating knowledge continually without forgetting the previously learned knowledge and also transferring the learned knowledge to help learn new tasks better. This survey presents a comprehensive review and analysis of the recent progress of CL in NLP, which has significant differences from CL in computer vision and machine learning. It covers (1) all CL settings with a taxonomy of existing techniques; (2) catastrophic forgetting (CF) prevention, (3) knowledge transfer (KT), which is particula"},"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":"2211.12701","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T04:46:28Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"33c3329687729a11e89e2b7695d5ed1a82677ba8d16c2c16476ae6325b176181","abstract_canon_sha256":"f8d07918afe92f7e9d2e46357115f152c515d3670c453be2e3a8924c1db5baef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:07.101581Z","signature_b64":"7SIJF9zfzJXM40wTKUCbxrATxBrHBXxtNrH3lepPkNMSp6juBGEcSpJxCLVLKJ8goWkgjw2EySGrh15NGOmYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4da880972f59b14daf9c66ac967a8eaccce457010ba7cfa228199153ad7c65b8","last_reissued_at":"2026-07-05T06:09:07.101110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:07.101110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning of Natural Language Processing Tasks: A Survey","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bing Liu, Zixuan Ke","submitted_at":"2022-11-23T04:46:28Z","abstract_excerpt":"Continual learning (CL) is a learning paradigm that emulates the human capability of learning and accumulating knowledge continually without forgetting the previously learned knowledge and also transferring the learned knowledge to help learn new tasks better. This survey presents a comprehensive review and analysis of the recent progress of CL in NLP, which has significant differences from CL in computer vision and machine learning. It covers (1) all CL settings with a taxonomy of existing techniques; (2) catastrophic forgetting (CF) prevention, (3) knowledge transfer (KT), which is particula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12701","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/2211.12701/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":"2211.12701","created_at":"2026-07-05T06:09:07.101168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12701v2","created_at":"2026-07-05T06:09:07.101168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12701","created_at":"2026-07-05T06:09:07.101168+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWUIBFZPLGYU","created_at":"2026-07-05T06:09:07.101168+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWUIBFZPLGYU3L44","created_at":"2026-07-05T06:09:07.101168+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWUIBFZP","created_at":"2026-07-05T06:09:07.101168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.06624","citing_title":"A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08747","citing_title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","ref_index":6,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10590","citing_title":"Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance","ref_index":19,"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":197,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT","json":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT.json","graph_json":"https://pith.science/api/pith-number/JWUIBFZPLGYU3L44M2WJM6UOVT/graph.json","events_json":"https://pith.science/api/pith-number/JWUIBFZPLGYU3L44M2WJM6UOVT/events.json","paper":"https://pith.science/paper/JWUIBFZP"},"agent_actions":{"view_html":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT","download_json":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT.json","view_paper":"https://pith.science/paper/JWUIBFZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12701&json=true","fetch_graph":"https://pith.science/api/pith-number/JWUIBFZPLGYU3L44M2WJM6UOVT/graph.json","fetch_events":"https://pith.science/api/pith-number/JWUIBFZPLGYU3L44M2WJM6UOVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT/action/storage_attestation","attest_author":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT/action/author_attestation","sign_citation":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT/action/citation_signature","submit_replication":"https://pith.science/pith/JWUIBFZPLGYU3L44M2WJM6UOVT/action/replication_record"}},"created_at":"2026-07-05T06:09:07.101168+00:00","updated_at":"2026-07-05T06:09:07.101168+00:00"}