{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RCDWLNWJWYGM5YYODB6BNFTN76","short_pith_number":"pith:RCDWLNWJ","schema_version":"1.0","canonical_sha256":"888765b6c9b60ccee30e187c16966dffadf4d89d7bedfdafeb13c8b7cb3fc517","source":{"kind":"arxiv","id":"2508.10645","version":1},"attestation_state":"computed","paper":{"title":"SemPT: Semantic Prompt Tuning for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiao Shi, Yangjun Ou, Zhenzhong Chen","submitted_at":"2025-08-14T13:41:59Z","abstract_excerpt":"Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language Models (VLMs) pre-trained on large amounts of image-text pairs offer a promising solution. However, existing prompt tuning methods rely on sparse category labels or disparate LLM-generated descriptions, which fragment knowledge representation and hinder transferability. To address this limitation, we introduce Semantic Prompt Tuning (SemPT), a novel framewo"},"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":"2508.10645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T13:41:59Z","cross_cats_sorted":[],"title_canon_sha256":"7c865bdadfac65513e10819b8a7d530512e286a04f36139d42c0d330ee06b39a","abstract_canon_sha256":"4169493894808ab2a0c4791945aaf05ae258b7d81882a270675878675ea44fa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:00.151535Z","signature_b64":"kSAqwmXCPN9YaXprdxQlyRbvNj6282czC7ojjtIsLCdjb68az9tzPwJtSFdMJTHmmun2pAJLZUl01QLReaavDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"888765b6c9b60ccee30e187c16966dffadf4d89d7bedfdafeb13c8b7cb3fc517","last_reissued_at":"2026-07-05T11:54:00.151097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:00.151097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemPT: Semantic Prompt Tuning for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiao Shi, Yangjun Ou, Zhenzhong Chen","submitted_at":"2025-08-14T13:41:59Z","abstract_excerpt":"Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language Models (VLMs) pre-trained on large amounts of image-text pairs offer a promising solution. However, existing prompt tuning methods rely on sparse category labels or disparate LLM-generated descriptions, which fragment knowledge representation and hinder transferability. To address this limitation, we introduce Semantic Prompt Tuning (SemPT), a novel framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10645","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/2508.10645/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":"2508.10645","created_at":"2026-07-05T11:54:00.151155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10645v1","created_at":"2026-07-05T11:54:00.151155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10645","created_at":"2026-07-05T11:54:00.151155+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCDWLNWJWYGM","created_at":"2026-07-05T11:54:00.151155+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCDWLNWJWYGM5YYO","created_at":"2026-07-05T11:54:00.151155+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCDWLNWJ","created_at":"2026-07-05T11:54:00.151155+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/RCDWLNWJWYGM5YYODB6BNFTN76","json":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76.json","graph_json":"https://pith.science/api/pith-number/RCDWLNWJWYGM5YYODB6BNFTN76/graph.json","events_json":"https://pith.science/api/pith-number/RCDWLNWJWYGM5YYODB6BNFTN76/events.json","paper":"https://pith.science/paper/RCDWLNWJ"},"agent_actions":{"view_html":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76","download_json":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76.json","view_paper":"https://pith.science/paper/RCDWLNWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10645&json=true","fetch_graph":"https://pith.science/api/pith-number/RCDWLNWJWYGM5YYODB6BNFTN76/graph.json","fetch_events":"https://pith.science/api/pith-number/RCDWLNWJWYGM5YYODB6BNFTN76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76/action/storage_attestation","attest_author":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76/action/author_attestation","sign_citation":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76/action/citation_signature","submit_replication":"https://pith.science/pith/RCDWLNWJWYGM5YYODB6BNFTN76/action/replication_record"}},"created_at":"2026-07-05T11:54:00.151155+00:00","updated_at":"2026-07-05T11:54:00.151155+00:00"}