{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X7B2RKPJIXZKI3R422YEYNFMFL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b7801a7d859cefe4f7ddf7093c1613dc67c4567b25e68d4c634d2c1667ecc4b","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T10:42:22Z","title_canon_sha256":"27969c7b9efbbac34dba12837ef6ebdf5600691297ed400ff47589f51cb1b36b"},"schema_version":"1.0","source":{"id":"2404.09654","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09654","created_at":"2026-07-05T10:45:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09654v3","created_at":"2026-07-05T10:45:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09654","created_at":"2026-07-05T10:45:07Z"},{"alias_kind":"pith_short_12","alias_value":"X7B2RKPJIXZK","created_at":"2026-07-05T10:45:07Z"},{"alias_kind":"pith_short_16","alias_value":"X7B2RKPJIXZKI3R4","created_at":"2026-07-05T10:45:07Z"},{"alias_kind":"pith_short_8","alias_value":"X7B2RKPJ","created_at":"2026-07-05T10:45:07Z"}],"graph_snapshots":[{"event_id":"sha256:df27656edff8bc2267e0e1025067c4c6351365776156e468f163a802c937d242","target":"graph","created_at":"2026-07-05T10:45:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.09654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing images with textual descriptions indicative of normal and abnormal conditions, referred to as anomaly prompts. However, existing approaches depend on static anomaly prompts that are prone to cross-semantic ambiguity, and prioritize global image-level representations over crucial local pixel-level image-to-text alignment that is necessary for accurate anomaly lo","authors_text":"Beng Chin Ooi, Fang Deng, Jiaqi Zhu, Junran Wu, Shaofeng Cai","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T10:42:22Z","title":"Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09654","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:97f74fe97f55b9fc5d4ce110841cec4e5195b8c7df33bfa09e4140a010177042","target":"record","created_at":"2026-07-05T10:45:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b7801a7d859cefe4f7ddf7093c1613dc67c4567b25e68d4c634d2c1667ecc4b","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T10:42:22Z","title_canon_sha256":"27969c7b9efbbac34dba12837ef6ebdf5600691297ed400ff47589f51cb1b36b"},"schema_version":"1.0","source":{"id":"2404.09654","kind":"arxiv","version":3}},"canonical_sha256":"bfc3a8a9e945f2a46e3cd6b04c34ac2ae1c3edbcf9f1a0398967128c1eb8f7cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfc3a8a9e945f2a46e3cd6b04c34ac2ae1c3edbcf9f1a0398967128c1eb8f7cc","first_computed_at":"2026-07-05T10:45:07.338912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:07.338912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G990byXOzqCbv6KzxG62KavdLr9P6w07n7FcdY0MI6BzILhboEAP/w9NqoNsyR/UDyfrWD40dpSXmYcKqDdKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:07.339445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09654","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97f74fe97f55b9fc5d4ce110841cec4e5195b8c7df33bfa09e4140a010177042","sha256:df27656edff8bc2267e0e1025067c4c6351365776156e468f163a802c937d242"],"state_sha256":"6615c8bb1a084abb494c07ec931cba2272c135fb3d82c32105b61fb7cfb943ba"}