{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PHATXWAXS4WL52TZVPPXRXACJ2","short_pith_number":"pith:PHATXWAX","schema_version":"1.0","canonical_sha256":"79c13bd817972cbeea79abdf78dc024ea94ee92a75c8d08f16355ca9e54ce362","source":{"kind":"arxiv","id":"2110.07298","version":3},"attestation_state":"computed","paper":{"title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengwei Qin, Shafiq Joty","submitted_at":"2021-10-14T12:06:29Z","abstract_excerpt":"Existing approaches to lifelong language learning rely on plenty of labeled data for learning a new task, which is hard to obtain in most real scenarios. Considering that humans can continually learn new tasks from a handful of examples, we expect the models also to be able to generalize well on new few-shot tasks without forgetting the previous ones. In this work, we define this more challenging yet practical problem as Lifelong Few-shot Language Learning (LFLL) and propose a unified framework for it based on prompt tuning of T5. Our framework called LFPT5 takes full advantage of PT's strong "},"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":"2110.07298","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T12:06:29Z","cross_cats_sorted":[],"title_canon_sha256":"a73efa08f6650621416654309a2843779b4219e1764757a7b4f1d4c2102778e9","abstract_canon_sha256":"dd3a4104f3c186d01c4899b4c948fb9b4957da756b0d06eeb1ab70563f0d285f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:12.295061Z","signature_b64":"ISCTg0aQIUQM53wxRgesChCC/3Q8xroahYBQtlDMljG5J5pR0dhed4iqi11cMMfvsoLbx4up1llh9JZTPd2BCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79c13bd817972cbeea79abdf78dc024ea94ee92a75c8d08f16355ca9e54ce362","last_reissued_at":"2026-07-05T04:10:12.294628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:12.294628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengwei Qin, Shafiq Joty","submitted_at":"2021-10-14T12:06:29Z","abstract_excerpt":"Existing approaches to lifelong language learning rely on plenty of labeled data for learning a new task, which is hard to obtain in most real scenarios. Considering that humans can continually learn new tasks from a handful of examples, we expect the models also to be able to generalize well on new few-shot tasks without forgetting the previous ones. In this work, we define this more challenging yet practical problem as Lifelong Few-shot Language Learning (LFLL) and propose a unified framework for it based on prompt tuning of T5. Our framework called LFPT5 takes full advantage of PT's strong "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07298","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/2110.07298/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":"2110.07298","created_at":"2026-07-05T04:10:12.294686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07298v3","created_at":"2026-07-05T04:10:12.294686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07298","created_at":"2026-07-05T04:10:12.294686+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHATXWAXS4WL","created_at":"2026-07-05T04:10:12.294686+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHATXWAXS4WL52TZ","created_at":"2026-07-05T04:10:12.294686+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHATXWAX","created_at":"2026-07-05T04:10:12.294686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.21035","citing_title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08949","citing_title":"Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08949","citing_title":"Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2","json":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2.json","graph_json":"https://pith.science/api/pith-number/PHATXWAXS4WL52TZVPPXRXACJ2/graph.json","events_json":"https://pith.science/api/pith-number/PHATXWAXS4WL52TZVPPXRXACJ2/events.json","paper":"https://pith.science/paper/PHATXWAX"},"agent_actions":{"view_html":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2","download_json":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2.json","view_paper":"https://pith.science/paper/PHATXWAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07298&json=true","fetch_graph":"https://pith.science/api/pith-number/PHATXWAXS4WL52TZVPPXRXACJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/PHATXWAXS4WL52TZVPPXRXACJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2/action/storage_attestation","attest_author":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2/action/author_attestation","sign_citation":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2/action/citation_signature","submit_replication":"https://pith.science/pith/PHATXWAXS4WL52TZVPPXRXACJ2/action/replication_record"}},"created_at":"2026-07-05T04:10:12.294686+00:00","updated_at":"2026-07-05T04:10:12.294686+00:00"}