{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PQAOKDJV2D2MONRTOFYIXH4MMY","short_pith_number":"pith:PQAOKDJV","schema_version":"1.0","canonical_sha256":"7c00e50d35d0f4c7363371708b9f8c66318bf09b11d80dd1e6531db771a4033c","source":{"kind":"arxiv","id":"2406.18197","version":4},"attestation_state":"computed","paper":{"title":"Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao-Chun Chen, Feng-Hao Yeh, Jerry Chun-Wei Lin, Jia Ji, Pi-Wei Chen, Zih-Ching Chen","submitted_at":"2024-06-26T09:29:05Z","abstract_excerpt":"Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning, making prompt-based anomaly detection a promising approach. Traditional methods depend on human-crafted prompts that require prior knowledge of specific anomaly types. Our goal is to develop a human-free prompt-based anomaly detection framework that optimally learns prompts through data-driven methods, eliminating the need for human intervention. The primary challenge in this approach is the lack of anomalous samples during the training phase. Additionally, the Vision Transform"},"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":"2406.18197","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-26T09:29:05Z","cross_cats_sorted":[],"title_canon_sha256":"f399676ecb49d0a8b0b68a3e332c0150d78e0978fb7252c581d3c8f6be3b58ef","abstract_canon_sha256":"bc72345ee0bd0d2571b6a690d2ef18881e867ff9017ec75c1d39dc3645928e6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:37.004042Z","signature_b64":"jeh5rDaWyLmBfFs6y5D3ppu0P7j85tW+m6EdgOnbkZrZar36VhCstSFeyMQSFeZdz4mRuVQ2aq8e+JFhNgBMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c00e50d35d0f4c7363371708b9f8c66318bf09b11d80dd1e6531db771a4033c","last_reissued_at":"2026-07-05T09:05:37.003478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:37.003478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao-Chun Chen, Feng-Hao Yeh, Jerry Chun-Wei Lin, Jia Ji, Pi-Wei Chen, Zih-Ching Chen","submitted_at":"2024-06-26T09:29:05Z","abstract_excerpt":"Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning, making prompt-based anomaly detection a promising approach. Traditional methods depend on human-crafted prompts that require prior knowledge of specific anomaly types. Our goal is to develop a human-free prompt-based anomaly detection framework that optimally learns prompts through data-driven methods, eliminating the need for human intervention. The primary challenge in this approach is the lack of anomalous samples during the training phase. Additionally, the Vision Transform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18197","kind":"arxiv","version":4},"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/2406.18197/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":"2406.18197","created_at":"2026-07-05T09:05:37.003542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18197v4","created_at":"2026-07-05T09:05:37.003542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18197","created_at":"2026-07-05T09:05:37.003542+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQAOKDJV2D2M","created_at":"2026-07-05T09:05:37.003542+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQAOKDJV2D2MONRT","created_at":"2026-07-05T09:05:37.003542+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQAOKDJV","created_at":"2026-07-05T09:05:37.003542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16946","citing_title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY","json":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY.json","graph_json":"https://pith.science/api/pith-number/PQAOKDJV2D2MONRTOFYIXH4MMY/graph.json","events_json":"https://pith.science/api/pith-number/PQAOKDJV2D2MONRTOFYIXH4MMY/events.json","paper":"https://pith.science/paper/PQAOKDJV"},"agent_actions":{"view_html":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY","download_json":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY.json","view_paper":"https://pith.science/paper/PQAOKDJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18197&json=true","fetch_graph":"https://pith.science/api/pith-number/PQAOKDJV2D2MONRTOFYIXH4MMY/graph.json","fetch_events":"https://pith.science/api/pith-number/PQAOKDJV2D2MONRTOFYIXH4MMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY/action/storage_attestation","attest_author":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY/action/author_attestation","sign_citation":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY/action/citation_signature","submit_replication":"https://pith.science/pith/PQAOKDJV2D2MONRTOFYIXH4MMY/action/replication_record"}},"created_at":"2026-07-05T09:05:37.003542+00:00","updated_at":"2026-07-05T09:05:37.003542+00:00"}