{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TICGH6UYGX32QIOZOIWSFJ4OPQ","short_pith_number":"pith:TICGH6UY","schema_version":"1.0","canonical_sha256":"9a0463fa9835f7a821d9722d22a78e7c26e654431645b0e09fc74ae191f0d7f0","source":{"kind":"arxiv","id":"2502.14880","version":1},"attestation_state":"computed","paper":{"title":"KKA: Improving Vision Anomaly Detection through Anomaly-related Knowledge from Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Chen, Mingliang Xu, Peiguang Fan, Qidong Liu, Xiaoheng Jiang, Yafei Li, Yueting Zhuang, Zhengqing Hu","submitted_at":"2025-02-14T07:46:49Z","abstract_excerpt":"Vision anomaly detection, particularly in unsupervised settings, often struggles to distinguish between normal samples and anomalies due to the wide variability in anomalies. Recently, an increasing number of studies have focused on generating anomalies to help detectors learn more effective boundaries between normal samples and anomalies. However, as the generated anomalies are often derived from random factors, they frequently lack realism. Additionally, randomly generated anomalies typically offer limited support in constructing effective boundaries, as most differ substantially from normal"},"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":"2502.14880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T07:46:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"edbf0107e1d279561e54361ccf7465d3ecf5457288be789ba97cf9658860088c","abstract_canon_sha256":"3008567c6826c1343d14babd1afe7f3c9193b98a5d9eb3addfda431122c865a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:35.771508Z","signature_b64":"3x/NED+yTa80ZDZNPM3d4hO/58caYN7OGdf95P9YCWhmmwKcWI/Q/JYK5G5unZobmx+euCDs+osKLDNEmyTqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a0463fa9835f7a821d9722d22a78e7c26e654431645b0e09fc74ae191f0d7f0","last_reissued_at":"2026-07-05T10:17:35.771016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:35.771016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KKA: Improving Vision Anomaly Detection through Anomaly-related Knowledge from Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dong Chen, Mingliang Xu, Peiguang Fan, Qidong Liu, Xiaoheng Jiang, Yafei Li, Yueting Zhuang, Zhengqing Hu","submitted_at":"2025-02-14T07:46:49Z","abstract_excerpt":"Vision anomaly detection, particularly in unsupervised settings, often struggles to distinguish between normal samples and anomalies due to the wide variability in anomalies. Recently, an increasing number of studies have focused on generating anomalies to help detectors learn more effective boundaries between normal samples and anomalies. However, as the generated anomalies are often derived from random factors, they frequently lack realism. Additionally, randomly generated anomalies typically offer limited support in constructing effective boundaries, as most differ substantially from normal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14880","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/2502.14880/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":"2502.14880","created_at":"2026-07-05T10:17:35.771074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14880v1","created_at":"2026-07-05T10:17:35.771074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14880","created_at":"2026-07-05T10:17:35.771074+00:00"},{"alias_kind":"pith_short_12","alias_value":"TICGH6UYGX32","created_at":"2026-07-05T10:17:35.771074+00:00"},{"alias_kind":"pith_short_16","alias_value":"TICGH6UYGX32QIOZ","created_at":"2026-07-05T10:17:35.771074+00:00"},{"alias_kind":"pith_short_8","alias_value":"TICGH6UY","created_at":"2026-07-05T10:17:35.771074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14851","citing_title":"IFPV: An Integrated Multi-Agent Framework for Generative Operational Planning and High-Fidelity Plan Verification","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08599","citing_title":"What Will Happen Next: Large Models-Driven Deduction for Emergency Instances","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10989","citing_title":"MAFIG: Multi-agent Driven Formal Instruction Generation Framework","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ","json":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ.json","graph_json":"https://pith.science/api/pith-number/TICGH6UYGX32QIOZOIWSFJ4OPQ/graph.json","events_json":"https://pith.science/api/pith-number/TICGH6UYGX32QIOZOIWSFJ4OPQ/events.json","paper":"https://pith.science/paper/TICGH6UY"},"agent_actions":{"view_html":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ","download_json":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ.json","view_paper":"https://pith.science/paper/TICGH6UY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14880&json=true","fetch_graph":"https://pith.science/api/pith-number/TICGH6UYGX32QIOZOIWSFJ4OPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TICGH6UYGX32QIOZOIWSFJ4OPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ/action/storage_attestation","attest_author":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ/action/author_attestation","sign_citation":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ/action/citation_signature","submit_replication":"https://pith.science/pith/TICGH6UYGX32QIOZOIWSFJ4OPQ/action/replication_record"}},"created_at":"2026-07-05T10:17:35.771074+00:00","updated_at":"2026-07-05T10:17:35.771074+00:00"}