{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4DPUQ34UCLMU53H2JIMIWQPFI","short_pith_number":"pith:T4DPUQ34","schema_version":"1.0","canonical_sha256":"9f06fa437ca096ca7767d250c45a0f2a036e19b55ab35c9b82ce5c32d8ab311f","source":{"kind":"arxiv","id":"2409.18860","version":2},"attestation_state":"computed","paper":{"title":"LW2G: Learning Whether to Grow for Prompt-based Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Da-Wei Zhou, Dengxin Dai, Hanbin Zhao, Hui Qian, Jiahua Dong, Qian Feng","submitted_at":"2024-09-27T15:55:13Z","abstract_excerpt":"Recent Prompt-based Continual learning (PCL) has achieved remarkable performance with pre-trained models. These approaches expand a prompt pool by adding a new set of prompts while learning and select the correct set during inference. Previous studies have revealed that learning task-wised prompt sets individually and low selection accuracy pose challenges to the performance of PCL. In this paper, we propose a plug-in method, $\\textbf{L}$earning $\\textbf{W}$hether $\\textbf{t}$o $\\textbf{G}$row $\\textbf{(LW2G)}$, which leverages the disparities between tasks to form an effective and efficient p"},"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":"2409.18860","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-27T15:55:13Z","cross_cats_sorted":[],"title_canon_sha256":"21397d7268a2a07a1d41efc39f936832a4adf923595b1d0d92657118a0469cd6","abstract_canon_sha256":"f6ddded1734f300457f3b3e2841efc80909e91f98231bc186ef0a288bdabbfaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:02.082328Z","signature_b64":"4pp0v47C4sOdzKU2AEIgllj9x94qd1XRjLbyPhUZuBycKIBA+xhRGb/oi0YZEjTV0OWhvUXpzmmFYrC3ASaaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f06fa437ca096ca7767d250c45a0f2a036e19b55ab35c9b82ce5c32d8ab311f","last_reissued_at":"2026-07-05T11:29:02.081779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:02.081779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LW2G: Learning Whether to Grow for Prompt-based Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Da-Wei Zhou, Dengxin Dai, Hanbin Zhao, Hui Qian, Jiahua Dong, Qian Feng","submitted_at":"2024-09-27T15:55:13Z","abstract_excerpt":"Recent Prompt-based Continual learning (PCL) has achieved remarkable performance with pre-trained models. These approaches expand a prompt pool by adding a new set of prompts while learning and select the correct set during inference. Previous studies have revealed that learning task-wised prompt sets individually and low selection accuracy pose challenges to the performance of PCL. In this paper, we propose a plug-in method, $\\textbf{L}$earning $\\textbf{W}$hether $\\textbf{t}$o $\\textbf{G}$row $\\textbf{(LW2G)}$, which leverages the disparities between tasks to form an effective and efficient p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18860","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/2409.18860/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":"2409.18860","created_at":"2026-07-05T11:29:02.081847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18860v2","created_at":"2026-07-05T11:29:02.081847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18860","created_at":"2026-07-05T11:29:02.081847+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4DPUQ34UCLM","created_at":"2026-07-05T11:29:02.081847+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4DPUQ34UCLMU53H","created_at":"2026-07-05T11:29:02.081847+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4DPUQ34","created_at":"2026-07-05T11:29:02.081847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04227","citing_title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI","json":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI.json","graph_json":"https://pith.science/api/pith-number/T4DPUQ34UCLMU53H2JIMIWQPFI/graph.json","events_json":"https://pith.science/api/pith-number/T4DPUQ34UCLMU53H2JIMIWQPFI/events.json","paper":"https://pith.science/paper/T4DPUQ34"},"agent_actions":{"view_html":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI","download_json":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI.json","view_paper":"https://pith.science/paper/T4DPUQ34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18860&json=true","fetch_graph":"https://pith.science/api/pith-number/T4DPUQ34UCLMU53H2JIMIWQPFI/graph.json","fetch_events":"https://pith.science/api/pith-number/T4DPUQ34UCLMU53H2JIMIWQPFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI/action/storage_attestation","attest_author":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI/action/author_attestation","sign_citation":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI/action/citation_signature","submit_replication":"https://pith.science/pith/T4DPUQ34UCLMU53H2JIMIWQPFI/action/replication_record"}},"created_at":"2026-07-05T11:29:02.081847+00:00","updated_at":"2026-07-05T11:29:02.081847+00:00"}