{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GJNEEYHGZLQAWT377CIE245IRJ","short_pith_number":"pith:GJNEEYHG","schema_version":"1.0","canonical_sha256":"325a4260e6cae00b4f7ff8904d73a88a75cef7d422d83e294125beb97b01bb02","source":{"kind":"arxiv","id":"2412.00890","version":1},"attestation_state":"computed","paper":{"title":"Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun Qian, Tianyu Sun, Wenhong Wang","submitted_at":"2024-12-01T17:00:43Z","abstract_excerpt":"Industrial anomaly detection (IAD) plays a crucial role in the maintenance and quality control of manufacturing processes. In this paper, we propose a novel approach, Vision-Language Anomaly Detection via Contrastive Cross-Modal Training (CLAD), which leverages large vision-language models (LVLMs) to improve both anomaly detection and localization in industrial settings. CLAD aligns visual and textual features into a shared embedding space using contrastive learning, ensuring that normal instances are grouped together while anomalies are pushed apart. Through extensive experiments on two bench"},"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":"2412.00890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-01T17:00:43Z","cross_cats_sorted":[],"title_canon_sha256":"6023c865e729d702e320b1443c15885b25b0a4d2af1a6009459bde8490ddd5f5","abstract_canon_sha256":"7bb7758a064583c9cb0443f13e31dfb275efa6102d45d86fd9d92a74728c826e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:49.996910Z","signature_b64":"Yb8sZxMcEM5O38HOPO/BeTE8/KQLp36YO0R0zgn/wPHdILfREOBRV1O6zXrbdINbM1i8kJHFMP1z0UIUo5BcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"325a4260e6cae00b4f7ff8904d73a88a75cef7d422d83e294125beb97b01bb02","last_reissued_at":"2026-07-05T09:42:49.996523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:49.996523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun Qian, Tianyu Sun, Wenhong Wang","submitted_at":"2024-12-01T17:00:43Z","abstract_excerpt":"Industrial anomaly detection (IAD) plays a crucial role in the maintenance and quality control of manufacturing processes. In this paper, we propose a novel approach, Vision-Language Anomaly Detection via Contrastive Cross-Modal Training (CLAD), which leverages large vision-language models (LVLMs) to improve both anomaly detection and localization in industrial settings. CLAD aligns visual and textual features into a shared embedding space using contrastive learning, ensuring that normal instances are grouped together while anomalies are pushed apart. Through extensive experiments on two bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00890","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/2412.00890/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":"2412.00890","created_at":"2026-07-05T09:42:49.996577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00890v1","created_at":"2026-07-05T09:42:49.996577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00890","created_at":"2026-07-05T09:42:49.996577+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJNEEYHGZLQA","created_at":"2026-07-05T09:42:49.996577+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJNEEYHGZLQAWT37","created_at":"2026-07-05T09:42:49.996577+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJNEEYHG","created_at":"2026-07-05T09:42:49.996577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ","json":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ.json","graph_json":"https://pith.science/api/pith-number/GJNEEYHGZLQAWT377CIE245IRJ/graph.json","events_json":"https://pith.science/api/pith-number/GJNEEYHGZLQAWT377CIE245IRJ/events.json","paper":"https://pith.science/paper/GJNEEYHG"},"agent_actions":{"view_html":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ","download_json":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ.json","view_paper":"https://pith.science/paper/GJNEEYHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00890&json=true","fetch_graph":"https://pith.science/api/pith-number/GJNEEYHGZLQAWT377CIE245IRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GJNEEYHGZLQAWT377CIE245IRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ/action/storage_attestation","attest_author":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ/action/author_attestation","sign_citation":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ/action/citation_signature","submit_replication":"https://pith.science/pith/GJNEEYHGZLQAWT377CIE245IRJ/action/replication_record"}},"created_at":"2026-07-05T09:42:49.996577+00:00","updated_at":"2026-07-05T09:42:49.996577+00:00"}