{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LPHBMSJES3SMO6UG3HXXMX4SIF","short_pith_number":"pith:LPHBMSJE","schema_version":"1.0","canonical_sha256":"5bce16492496e4c77a86d9ef765f924177e08aa2a2203d6b519ea24fe47c6145","source":{"kind":"arxiv","id":"2507.05677","version":2},"attestation_state":"computed","paper":{"title":"Integrated Structural Prompt Learning for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Bo Jiang, Jiahui Wang, Qin Xu","submitted_at":"2025-07-08T04:59:58Z","abstract_excerpt":"Prompt learning methods have significantly extended the transferability of pre-trained Vision-Language Models (VLMs) like CLIP for various downstream tasks. These methods adopt handcraft templates or learnable vectors to provide text or image instructions in fine-tuning VLMs. However, most existing works ignore the structural relationships between learnable prompts and tokens within and between modalities. Moreover, balancing the performance of base and new classes remains a significant challenge. In this paper, we propose an Integrated Structural Prompt (ISP) for VLMs to enhance the interacti"},"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":"2507.05677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T04:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"72bb4d8cc4b2810bc0164fc6c0f9e56a79eb7fdd56792c4e2abe09a18a1c13f7","abstract_canon_sha256":"137e696cfb1cbc5e27cd098e8b145e42248995ffdb51955fa36aa85a23146ea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:11.981233Z","signature_b64":"n0jzP9+tshFRxyezLyQESH+QmxwewBhDBVR1Rz+Ih9RL81s2K1QOr1pmLWIuV9wXg9gTF4saQA/ytMHDk1ndDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bce16492496e4c77a86d9ef765f924177e08aa2a2203d6b519ea24fe47c6145","last_reissued_at":"2026-07-05T11:34:11.980753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:11.980753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrated Structural Prompt Learning for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Bo Jiang, Jiahui Wang, Qin Xu","submitted_at":"2025-07-08T04:59:58Z","abstract_excerpt":"Prompt learning methods have significantly extended the transferability of pre-trained Vision-Language Models (VLMs) like CLIP for various downstream tasks. These methods adopt handcraft templates or learnable vectors to provide text or image instructions in fine-tuning VLMs. However, most existing works ignore the structural relationships between learnable prompts and tokens within and between modalities. Moreover, balancing the performance of base and new classes remains a significant challenge. In this paper, we propose an Integrated Structural Prompt (ISP) for VLMs to enhance the interacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05677","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/2507.05677/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":"2507.05677","created_at":"2026-07-05T11:34:11.980812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05677v2","created_at":"2026-07-05T11:34:11.980812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05677","created_at":"2026-07-05T11:34:11.980812+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPHBMSJES3SM","created_at":"2026-07-05T11:34:11.980812+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPHBMSJES3SMO6UG","created_at":"2026-07-05T11:34:11.980812+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPHBMSJE","created_at":"2026-07-05T11:34:11.980812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF","json":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF.json","graph_json":"https://pith.science/api/pith-number/LPHBMSJES3SMO6UG3HXXMX4SIF/graph.json","events_json":"https://pith.science/api/pith-number/LPHBMSJES3SMO6UG3HXXMX4SIF/events.json","paper":"https://pith.science/paper/LPHBMSJE"},"agent_actions":{"view_html":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF","download_json":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF.json","view_paper":"https://pith.science/paper/LPHBMSJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05677&json=true","fetch_graph":"https://pith.science/api/pith-number/LPHBMSJES3SMO6UG3HXXMX4SIF/graph.json","fetch_events":"https://pith.science/api/pith-number/LPHBMSJES3SMO6UG3HXXMX4SIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF/action/storage_attestation","attest_author":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF/action/author_attestation","sign_citation":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF/action/citation_signature","submit_replication":"https://pith.science/pith/LPHBMSJES3SMO6UG3HXXMX4SIF/action/replication_record"}},"created_at":"2026-07-05T11:34:11.980812+00:00","updated_at":"2026-07-05T11:34:11.980812+00:00"}