{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JWHB7FQPAPR2RS6F63M6SCZJKR","short_pith_number":"pith:JWHB7FQP","schema_version":"1.0","canonical_sha256":"4d8e1f960f03e3a8cbc5f6d9e90b29544d2bcc50606ecbeef4ad119109e14690","source":{"kind":"arxiv","id":"2112.08654","version":2},"attestation_state":"computed","paper":{"title":"Learning to Prompt for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Lee, Guolong Su, Han Zhang, Jennifer Dy, Ruoxi Sun, Tomas Pfister, Vincent Perot, Xiaoqi Ren, Zifeng Wang, Zizhao Zhang","submitted_at":"2021-12-16T06:17:07Z","abstract_excerpt":"The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task identity at test time to retrieve learned knowledge and address forgetting, while this work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time. Our method learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequentially under different task transitions"},"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":"2112.08654","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T06:17:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7c97675fe5c38cfd7f6b59ffb8afe7dba395372a5463805030d43ca87a7051bc","abstract_canon_sha256":"ad1697020f202bbdf2e454972b4e71bd26697a791dcc4c23547427c20d44d546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:06.992290Z","signature_b64":"idVqVWo6xzm2/DeDqHIAZIqbgUPgauW9ynqrB4lJLo07j5tNQw9srEqEVu87PcAm2DEf+s36uJBisWx/toFoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d8e1f960f03e3a8cbc5f6d9e90b29544d2bcc50606ecbeef4ad119109e14690","last_reissued_at":"2026-07-05T04:07:06.991844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:06.991844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Prompt for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chen-Yu Lee, Guolong Su, Han Zhang, Jennifer Dy, Ruoxi Sun, Tomas Pfister, Vincent Perot, Xiaoqi Ren, Zifeng Wang, Zizhao Zhang","submitted_at":"2021-12-16T06:17:07Z","abstract_excerpt":"The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge. Typical methods rely on a rehearsal buffer or known task identity at test time to retrieve learned knowledge and address forgetting, while this work presents a new paradigm for continual learning that aims to train a more succinct memory system without accessing task identity at test time. Our method learns to dynamically prompt (L2P) a pre-trained model to learn tasks sequentially under different task transitions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08654","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/2112.08654/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":"2112.08654","created_at":"2026-07-05T04:07:06.991898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08654v2","created_at":"2026-07-05T04:07:06.991898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08654","created_at":"2026-07-05T04:07:06.991898+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWHB7FQPAPR2","created_at":"2026-07-05T04:07:06.991898+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWHB7FQPAPR2RS6F","created_at":"2026-07-05T04:07:06.991898+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWHB7FQP","created_at":"2026-07-05T04:07:06.991898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.18187","citing_title":"BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR","json":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR.json","graph_json":"https://pith.science/api/pith-number/JWHB7FQPAPR2RS6F63M6SCZJKR/graph.json","events_json":"https://pith.science/api/pith-number/JWHB7FQPAPR2RS6F63M6SCZJKR/events.json","paper":"https://pith.science/paper/JWHB7FQP"},"agent_actions":{"view_html":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR","download_json":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR.json","view_paper":"https://pith.science/paper/JWHB7FQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08654&json=true","fetch_graph":"https://pith.science/api/pith-number/JWHB7FQPAPR2RS6F63M6SCZJKR/graph.json","fetch_events":"https://pith.science/api/pith-number/JWHB7FQPAPR2RS6F63M6SCZJKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR/action/storage_attestation","attest_author":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR/action/author_attestation","sign_citation":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR/action/citation_signature","submit_replication":"https://pith.science/pith/JWHB7FQPAPR2RS6F63M6SCZJKR/action/replication_record"}},"created_at":"2026-07-05T04:07:06.991898+00:00","updated_at":"2026-07-05T04:07:06.991898+00:00"}