{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3LZ5557NN7KCT4ZTRXZPSTSBX6","short_pith_number":"pith:3LZ5557N","schema_version":"1.0","canonical_sha256":"daf3def7ed6fd429f3338df2f94e41bf85351198a5481b6dd857e2eb491ab030","source":{"kind":"arxiv","id":"2409.04796","version":3},"attestation_state":"computed","paper":{"title":"Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanhu Zeng, Fei Zhu, Hongxin Wei, Xu-Yao Zhang, Zhen Cheng","submitted_at":"2024-09-07T11:24:52Z","abstract_excerpt":"Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories, has gained prominence in practical scenarios. Recently, the advent of vision-language models (VLM) has heightened interest in enhancing OOD detection for VLM through few-shot tuning. However, existing methods mainly focus on optimizing global prompts, ignoring refined utilization of local information with regard to outliers. Motivated by this, we freeze global prompts and introduce Local-Prompt, a novel coarse-to-fine tuning paradigm to emphasize regional enhancement with local prompts. Our method compri"},"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":"2409.04796","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T11:24:52Z","cross_cats_sorted":[],"title_canon_sha256":"c320c5468c712f503e87419a9f20e7f21217b4b0368259b8dd216ff15eaaf3e8","abstract_canon_sha256":"d6264db6eb6cf55fd37b52f4981c354ba17456bbd59495b6067cc158ec1a0a43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:14.987134Z","signature_b64":"28lX59psjI1icybgBdqx7l0Qo1TShUe2pVKjHFTPlCX3B/o7/hH8/PXy1HpsvVspjPt5VO0dnFgXGgBoOxdFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daf3def7ed6fd429f3338df2f94e41bf85351198a5481b6dd857e2eb491ab030","last_reissued_at":"2026-07-05T10:20:14.986617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:14.986617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanhu Zeng, Fei Zhu, Hongxin Wei, Xu-Yao Zhang, Zhen Cheng","submitted_at":"2024-09-07T11:24:52Z","abstract_excerpt":"Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories, has gained prominence in practical scenarios. Recently, the advent of vision-language models (VLM) has heightened interest in enhancing OOD detection for VLM through few-shot tuning. However, existing methods mainly focus on optimizing global prompts, ignoring refined utilization of local information with regard to outliers. Motivated by this, we freeze global prompts and introduce Local-Prompt, a novel coarse-to-fine tuning paradigm to emphasize regional enhancement with local prompts. Our method compri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04796","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/2409.04796/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":"2409.04796","created_at":"2026-07-05T10:20:14.986678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04796v3","created_at":"2026-07-05T10:20:14.986678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04796","created_at":"2026-07-05T10:20:14.986678+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LZ5557NN7KC","created_at":"2026-07-05T10:20:14.986678+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LZ5557NN7KCT4ZT","created_at":"2026-07-05T10:20:14.986678+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LZ5557N","created_at":"2026-07-05T10:20:14.986678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17667","citing_title":"Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6","json":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6.json","graph_json":"https://pith.science/api/pith-number/3LZ5557NN7KCT4ZTRXZPSTSBX6/graph.json","events_json":"https://pith.science/api/pith-number/3LZ5557NN7KCT4ZTRXZPSTSBX6/events.json","paper":"https://pith.science/paper/3LZ5557N"},"agent_actions":{"view_html":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6","download_json":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6.json","view_paper":"https://pith.science/paper/3LZ5557N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04796&json=true","fetch_graph":"https://pith.science/api/pith-number/3LZ5557NN7KCT4ZTRXZPSTSBX6/graph.json","fetch_events":"https://pith.science/api/pith-number/3LZ5557NN7KCT4ZTRXZPSTSBX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6/action/storage_attestation","attest_author":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6/action/author_attestation","sign_citation":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6/action/citation_signature","submit_replication":"https://pith.science/pith/3LZ5557NN7KCT4ZTRXZPSTSBX6/action/replication_record"}},"created_at":"2026-07-05T10:20:14.986678+00:00","updated_at":"2026-07-05T10:20:14.986678+00:00"}