{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CBOSOJFX4VGNIQXH5CVECWWWN4","short_pith_number":"pith:CBOSOJFX","schema_version":"1.0","canonical_sha256":"105d2724b7e54cd442e7e8aa415ad66f30b227071ac5eb5ed73f53cdc8a49174","source":{"kind":"arxiv","id":"2505.22039","version":1},"attestation_state":"computed","paper":{"title":"OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lu Han, Shifang Zhao, Yao Zhao, Yiheng Lin, Yunchao Wei","submitted_at":"2025-05-28T07:02:15Z","abstract_excerpt":"While anomaly detection has made significant progress, generating detailed analyses that incorporate industrial knowledge remains a challenge. To address this gap, we introduce OmniAD, a novel framework that unifies anomaly detection and understanding for fine-grained analysis. OmniAD is a multimodal reasoner that combines visual and textual reasoning processes. The visual reasoning provides detailed inspection by leveraging Text-as-Mask Encoding to perform anomaly detection through text generation without manually selected thresholds. Following this, Visual Guided Textual Reasoning conducts c"},"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":"2505.22039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T07:02:15Z","cross_cats_sorted":[],"title_canon_sha256":"f49d16c4001ac79d2741edd48b2ec7e1794743203a27abfc80a1990bcc64fb1a","abstract_canon_sha256":"1acede7f036fd0e5f84a172ccf16093d501df3a0bd63450dccd596788076d064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:08.617036Z","signature_b64":"ghIcPTsrJlRh1O3M5OBTa7MWLvTdN/tX3NwG6/Ec+CgKJEwY0cmYZgHIRPrRQsrM3hCPI36dMAfB7u7xr1B+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105d2724b7e54cd442e7e8aa415ad66f30b227071ac5eb5ed73f53cdc8a49174","last_reissued_at":"2026-07-05T11:11:08.616551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:08.616551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lu Han, Shifang Zhao, Yao Zhao, Yiheng Lin, Yunchao Wei","submitted_at":"2025-05-28T07:02:15Z","abstract_excerpt":"While anomaly detection has made significant progress, generating detailed analyses that incorporate industrial knowledge remains a challenge. To address this gap, we introduce OmniAD, a novel framework that unifies anomaly detection and understanding for fine-grained analysis. OmniAD is a multimodal reasoner that combines visual and textual reasoning processes. The visual reasoning provides detailed inspection by leveraging Text-as-Mask Encoding to perform anomaly detection through text generation without manually selected thresholds. Following this, Visual Guided Textual Reasoning conducts c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22039","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/2505.22039/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":"2505.22039","created_at":"2026-07-05T11:11:08.616616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22039v1","created_at":"2026-07-05T11:11:08.616616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22039","created_at":"2026-07-05T11:11:08.616616+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBOSOJFX4VGN","created_at":"2026-07-05T11:11:08.616616+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBOSOJFX4VGNIQXH","created_at":"2026-07-05T11:11:08.616616+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBOSOJFX","created_at":"2026-07-05T11:11:08.616616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":189,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13671","citing_title":"AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2602.17419","citing_title":"EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2603.13779","citing_title":"AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12440","citing_title":"IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4","json":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4.json","graph_json":"https://pith.science/api/pith-number/CBOSOJFX4VGNIQXH5CVECWWWN4/graph.json","events_json":"https://pith.science/api/pith-number/CBOSOJFX4VGNIQXH5CVECWWWN4/events.json","paper":"https://pith.science/paper/CBOSOJFX"},"agent_actions":{"view_html":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4","download_json":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4.json","view_paper":"https://pith.science/paper/CBOSOJFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22039&json=true","fetch_graph":"https://pith.science/api/pith-number/CBOSOJFX4VGNIQXH5CVECWWWN4/graph.json","fetch_events":"https://pith.science/api/pith-number/CBOSOJFX4VGNIQXH5CVECWWWN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4/action/storage_attestation","attest_author":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4/action/author_attestation","sign_citation":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4/action/citation_signature","submit_replication":"https://pith.science/pith/CBOSOJFX4VGNIQXH5CVECWWWN4/action/replication_record"}},"created_at":"2026-07-05T11:11:08.616616+00:00","updated_at":"2026-07-05T11:11:08.616616+00:00"}