{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OA6GHGYN5CMOOECLENLHQ63X6U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ed6eef892e020a4a52e80b9d6e73af4158460ee2d670184e913cd64356baeea0","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T02:44:08Z","title_canon_sha256":"0de5ac85e36dac5d64ec6e56b39d0642b40bebc2fbbb142b019d6351ef236264"},"schema_version":"1.0","source":{"id":"2508.04028","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04028","created_at":"2026-07-05T11:49:19Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04028v1","created_at":"2026-07-05T11:49:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04028","created_at":"2026-07-05T11:49:19Z"},{"alias_kind":"pith_short_12","alias_value":"OA6GHGYN5CMO","created_at":"2026-07-05T11:49:19Z"},{"alias_kind":"pith_short_16","alias_value":"OA6GHGYN5CMOOECL","created_at":"2026-07-05T11:49:19Z"},{"alias_kind":"pith_short_8","alias_value":"OA6GHGYN","created_at":"2026-07-05T11:49:19Z"}],"graph_snapshots":[{"event_id":"sha256:a8df68b064ccbb4af7110d7e878d8503eebaef7dd05fd0273b329d46cfc4ab38","target":"graph","created_at":"2026-07-05T11:49:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.04028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval (ITR) task is more challenging. We find that the challenge lies in discriminating both fine-grained attributes and similar subcategories of the downstream data. To address this challenge, we propose Dual prompt Learning with Joint Category-Attribute Reweighting (DCAR), a novel dual-prompt learning framework to achieve precise image-text matching. The framework","authors_text":"Caiyang Yu, Chenwei Tang, Jiancheng Lv, Mengmi Zhang, Shudong Huang, Tao Wang, Yifan Wang, Zhengqing Zang","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T02:44:08Z","title":"Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04028","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:72d5ea639317617020a88680936a5aa13a5a1812d5287906af28b3ceba80f77f","target":"record","created_at":"2026-07-05T11:49:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ed6eef892e020a4a52e80b9d6e73af4158460ee2d670184e913cd64356baeea0","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-06T02:44:08Z","title_canon_sha256":"0de5ac85e36dac5d64ec6e56b39d0642b40bebc2fbbb142b019d6351ef236264"},"schema_version":"1.0","source":{"id":"2508.04028","kind":"arxiv","version":1}},"canonical_sha256":"703c639b0de898e7104b2356787b77f506e0e4036133659421641381163e4d26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"703c639b0de898e7104b2356787b77f506e0e4036133659421641381163e4d26","first_computed_at":"2026-07-05T11:49:19.373329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:19.373329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iNCL+jz5qn1jIeTyvedlToeOc6Ee9kurxS2X7OhDYNhJ1SZ6dsOnULVPHsneMU6cKGOH2JRm0yby12SbzBrLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:19.373796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04028","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72d5ea639317617020a88680936a5aa13a5a1812d5287906af28b3ceba80f77f","sha256:a8df68b064ccbb4af7110d7e878d8503eebaef7dd05fd0273b329d46cfc4ab38"],"state_sha256":"4144a0295fe4f10ed37a13b973526ad11745dcb5b7b68281f5691ce4bc727d08"}