{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A2ZPCNJILDGES6R24CMAJ2HEMQ","short_pith_number":"pith:A2ZPCNJI","schema_version":"1.0","canonical_sha256":"06b2f1352858cc497a3ae09804e8e464165c01146e463448f70a1d3962bede4c","source":{"kind":"arxiv","id":"2508.17417","version":1},"attestation_state":"computed","paper":{"title":"Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qilong Wang, Qinghua Hu, Xiaojie Yin","submitted_at":"2025-08-24T15:45:22Z","abstract_excerpt":"Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment due to domain gaps between pre-training and downstream tasks. Existing approaches primarily focus on text prompting with class-specific descriptions and visual-text adaptation via aligning cropped image regions with textual descriptions. However, they still face the issues of incomplete textual prompts and noisy visual prompts. In this paper, we propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment by constr"},"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":"2508.17417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T15:45:22Z","cross_cats_sorted":[],"title_canon_sha256":"ddb1ec25a011f17578f93c339ea94a3fdc19e0b0e8fd8b3f8d4b29587842b7dc","abstract_canon_sha256":"81af58f560e7aa6b825b6658ce898f7d0072d240f096b74272dee5eaf456e2a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:41.204951Z","signature_b64":"rlAoElqigPPEFONv5Jy5WgjM69fBhqh6fnaVOlEsgpAUilOZzvKrCqckhLerBNp7CYqkS30BJjOHXUGtFyFaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06b2f1352858cc497a3ae09804e8e464165c01146e463448f70a1d3962bede4c","last_reissued_at":"2026-07-05T11:58:41.204516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:41.204516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qilong Wang, Qinghua Hu, Xiaojie Yin","submitted_at":"2025-08-24T15:45:22Z","abstract_excerpt":"Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment due to domain gaps between pre-training and downstream tasks. Existing approaches primarily focus on text prompting with class-specific descriptions and visual-text adaptation via aligning cropped image regions with textual descriptions. However, they still face the issues of incomplete textual prompts and noisy visual prompts. In this paper, we propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment by constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17417","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/2508.17417/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":"2508.17417","created_at":"2026-07-05T11:58:41.204575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17417v1","created_at":"2026-07-05T11:58:41.204575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17417","created_at":"2026-07-05T11:58:41.204575+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2ZPCNJILDGE","created_at":"2026-07-05T11:58:41.204575+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2ZPCNJILDGES6R2","created_at":"2026-07-05T11:58:41.204575+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2ZPCNJI","created_at":"2026-07-05T11:58:41.204575+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/A2ZPCNJILDGES6R24CMAJ2HEMQ","json":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ.json","graph_json":"https://pith.science/api/pith-number/A2ZPCNJILDGES6R24CMAJ2HEMQ/graph.json","events_json":"https://pith.science/api/pith-number/A2ZPCNJILDGES6R24CMAJ2HEMQ/events.json","paper":"https://pith.science/paper/A2ZPCNJI"},"agent_actions":{"view_html":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ","download_json":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ.json","view_paper":"https://pith.science/paper/A2ZPCNJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17417&json=true","fetch_graph":"https://pith.science/api/pith-number/A2ZPCNJILDGES6R24CMAJ2HEMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/A2ZPCNJILDGES6R24CMAJ2HEMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ/action/storage_attestation","attest_author":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ/action/author_attestation","sign_citation":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ/action/citation_signature","submit_replication":"https://pith.science/pith/A2ZPCNJILDGES6R24CMAJ2HEMQ/action/replication_record"}},"created_at":"2026-07-05T11:58:41.204575+00:00","updated_at":"2026-07-05T11:58:41.204575+00:00"}