{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MV6E5VRAGAB5VPZVJYUDMVAW4A","short_pith_number":"pith:MV6E5VRA","schema_version":"1.0","canonical_sha256":"657c4ed6203003dabf354e28365416e013bcf09e4532f284b8240f96f2b12f8e","source":{"kind":"arxiv","id":"2405.15549","version":3},"attestation_state":"computed","paper":{"title":"SEP: Self-Enhanced Prompt Tuning for Visual-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Hantao Yao, Lu Yu, Rui Zhang, Yongdong Zhang","submitted_at":"2024-05-24T13:35:56Z","abstract_excerpt":"Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as they are independent of the pre-trained tokens and fail to capture input-specific knowledge, such as class-aware textual or instance-aware visual knowledge. Leveraging the discriminative and generalization capabilities inherent in pre-trained tokens, we introduce a novel approach named Self-Enhanced Prompt Tuning (SEP). The core principle of SEP involves adapting the learnable pr"},"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":"2405.15549","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-24T13:35:56Z","cross_cats_sorted":[],"title_canon_sha256":"d5669c77b4ea1cc804109f61d966fcda6a9a0f155396b5e05bc7b4f2042c2d1c","abstract_canon_sha256":"f558a29bcf7ebf22dfa687c18ecc854e1365b8e1e55aaf32a23417cad61dc27d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:06.620521Z","signature_b64":"FuJCrW3Flm1faYBzxkB1OBViVO6tGiHr/zI0ecrc7A/VuyhyTL9Ks0a9ZQ62lszUIj7h1kedEWyjnL8hpUP0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"657c4ed6203003dabf354e28365416e013bcf09e4532f284b8240f96f2b12f8e","last_reissued_at":"2026-07-05T09:39:06.620042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:06.620042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEP: Self-Enhanced Prompt Tuning for Visual-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Hantao Yao, Lu Yu, Rui Zhang, Yongdong Zhang","submitted_at":"2024-05-24T13:35:56Z","abstract_excerpt":"Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as they are independent of the pre-trained tokens and fail to capture input-specific knowledge, such as class-aware textual or instance-aware visual knowledge. Leveraging the discriminative and generalization capabilities inherent in pre-trained tokens, we introduce a novel approach named Self-Enhanced Prompt Tuning (SEP). The core principle of SEP involves adapting the learnable pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15549","kind":"arxiv","version":3},"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/2405.15549/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":"2405.15549","created_at":"2026-07-05T09:39:06.620099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15549v3","created_at":"2026-07-05T09:39:06.620099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15549","created_at":"2026-07-05T09:39:06.620099+00:00"},{"alias_kind":"pith_short_12","alias_value":"MV6E5VRAGAB5","created_at":"2026-07-05T09:39:06.620099+00:00"},{"alias_kind":"pith_short_16","alias_value":"MV6E5VRAGAB5VPZV","created_at":"2026-07-05T09:39:06.620099+00:00"},{"alias_kind":"pith_short_8","alias_value":"MV6E5VRA","created_at":"2026-07-05T09:39:06.620099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05677","citing_title":"Integrated Structural Prompt Learning for Vision-Language Models","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A","json":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A.json","graph_json":"https://pith.science/api/pith-number/MV6E5VRAGAB5VPZVJYUDMVAW4A/graph.json","events_json":"https://pith.science/api/pith-number/MV6E5VRAGAB5VPZVJYUDMVAW4A/events.json","paper":"https://pith.science/paper/MV6E5VRA"},"agent_actions":{"view_html":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A","download_json":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A.json","view_paper":"https://pith.science/paper/MV6E5VRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15549&json=true","fetch_graph":"https://pith.science/api/pith-number/MV6E5VRAGAB5VPZVJYUDMVAW4A/graph.json","fetch_events":"https://pith.science/api/pith-number/MV6E5VRAGAB5VPZVJYUDMVAW4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A/action/storage_attestation","attest_author":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A/action/author_attestation","sign_citation":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A/action/citation_signature","submit_replication":"https://pith.science/pith/MV6E5VRAGAB5VPZVJYUDMVAW4A/action/replication_record"}},"created_at":"2026-07-05T09:39:06.620099+00:00","updated_at":"2026-07-05T09:39:06.620099+00:00"}