{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MR5YV73MWR2LDRGWZQBLP3F2X6","short_pith_number":"pith:MR5YV73M","schema_version":"1.0","canonical_sha256":"647b8aff6cb474b1c4d6cc02b7ecbabfabadafc76fc0414d251e10d42566d407","source":{"kind":"arxiv","id":"2503.13443","version":1},"attestation_state":"computed","paper":{"title":"DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chao Wang, Guodong Long, Haoyang Li, Jing Jiang, Liang Wang, Yan Peng","submitted_at":"2025-03-17T17:59:27Z","abstract_excerpt":"The Base-New Trade-off (BNT) problem universally exists during the optimization of CLIP-based prompt tuning, where continuous fine-tuning on base (target) classes leads to a simultaneous decrease of generalization ability on new (unseen) classes. Existing approaches attempt to regulate the prompt tuning process to balance BNT by appending constraints. However, imposed on the same target prompt, these constraints fail to fully avert the mutual exclusivity between the optimization directions for base and new. As a novel solution to this challenge, we propose the plug-and-play Dual-Prompt Collabo"},"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":"2503.13443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T17:59:27Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"63b092c200c638b67fb4f0e7627cfc81af12469404c5ccbb15e1329ee2aa3fe0","abstract_canon_sha256":"b8eb38bcde9216e5dab866c10819357731ac682af067a1c3966742f9fd91ce2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:47.663377Z","signature_b64":"WzEXs+oVVn0cCcPOazRPaGL2nElfrv6tcl3iEI+z1cBlmZ1GkGKkCZGqJhq4pYXInOZ3qTGAYupSUb3EGZx3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"647b8aff6cb474b1c4d6cc02b7ecbabfabadafc76fc0414d251e10d42566d407","last_reissued_at":"2026-07-05T10:37:47.662851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:47.662851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chao Wang, Guodong Long, Haoyang Li, Jing Jiang, Liang Wang, Yan Peng","submitted_at":"2025-03-17T17:59:27Z","abstract_excerpt":"The Base-New Trade-off (BNT) problem universally exists during the optimization of CLIP-based prompt tuning, where continuous fine-tuning on base (target) classes leads to a simultaneous decrease of generalization ability on new (unseen) classes. Existing approaches attempt to regulate the prompt tuning process to balance BNT by appending constraints. However, imposed on the same target prompt, these constraints fail to fully avert the mutual exclusivity between the optimization directions for base and new. As a novel solution to this challenge, we propose the plug-and-play Dual-Prompt Collabo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13443","kind":"arxiv","version":1},"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/2503.13443/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":"2503.13443","created_at":"2026-07-05T10:37:47.662911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13443v1","created_at":"2026-07-05T10:37:47.662911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13443","created_at":"2026-07-05T10:37:47.662911+00:00"},{"alias_kind":"pith_short_12","alias_value":"MR5YV73MWR2L","created_at":"2026-07-05T10:37:47.662911+00:00"},{"alias_kind":"pith_short_16","alias_value":"MR5YV73MWR2LDRGW","created_at":"2026-07-05T10:37:47.662911+00:00"},{"alias_kind":"pith_short_8","alias_value":"MR5YV73M","created_at":"2026-07-05T10:37:47.662911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18504","citing_title":"Generalizing vision-language models to novel domains: A comprehensive survey","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6","json":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6.json","graph_json":"https://pith.science/api/pith-number/MR5YV73MWR2LDRGWZQBLP3F2X6/graph.json","events_json":"https://pith.science/api/pith-number/MR5YV73MWR2LDRGWZQBLP3F2X6/events.json","paper":"https://pith.science/paper/MR5YV73M"},"agent_actions":{"view_html":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6","download_json":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6.json","view_paper":"https://pith.science/paper/MR5YV73M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13443&json=true","fetch_graph":"https://pith.science/api/pith-number/MR5YV73MWR2LDRGWZQBLP3F2X6/graph.json","fetch_events":"https://pith.science/api/pith-number/MR5YV73MWR2LDRGWZQBLP3F2X6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6/action/storage_attestation","attest_author":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6/action/author_attestation","sign_citation":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6/action/citation_signature","submit_replication":"https://pith.science/pith/MR5YV73MWR2LDRGWZQBLP3F2X6/action/replication_record"}},"created_at":"2026-07-05T10:37:47.662911+00:00","updated_at":"2026-07-05T10:37:47.662911+00:00"}