{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N44RVE352OFY46BAHN4KARBXZ2","short_pith_number":"pith:N44RVE35","schema_version":"1.0","canonical_sha256":"6f391a937dd38b8e78203b78a04437ceafd5b8808487d5160d691b06889973f2","source":{"kind":"arxiv","id":"2505.02626","version":1},"attestation_state":"computed","paper":{"title":"Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arian Mousakhan, Jawad Tayyub, Sassan Mokhtar, Silvio Galesso, Thomas Brox","submitted_at":"2025-05-05T13:08:25Z","abstract_excerpt":"Recent advances in visual industrial anomaly detection have demonstrated exceptional performance in identifying and segmenting anomalous regions while maintaining fast inference speeds. However, anomaly classification-distinguishing different types of anomalies-remains largely unexplored despite its critical importance in real-world inspection tasks. To address this gap, we propose VELM, a novel LLM-based pipeline for anomaly classification. Given the critical importance of inference speed, we first apply an unsupervised anomaly detection method as a vision expert to assess the normality of an"},"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":"2505.02626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T13:08:25Z","cross_cats_sorted":[],"title_canon_sha256":"ee9ad360ad6b132028019797c36050994c1109a65c60c43bec7cef59957237a0","abstract_canon_sha256":"2427d29499d9730848f05984106434dac30a9af3c9d31e398f52133e5b58bebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:40.549083Z","signature_b64":"KQSpkZI4JGuHQxKDtORlqMO+uDzn62238hTy8+VxeBS2Zc3P6ehqetJcbON1RnD3c0LgoUI/fNLamXYYl5msAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f391a937dd38b8e78203b78a04437ceafd5b8808487d5160d691b06889973f2","last_reissued_at":"2026-07-05T10:58:40.548642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:40.548642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arian Mousakhan, Jawad Tayyub, Sassan Mokhtar, Silvio Galesso, Thomas Brox","submitted_at":"2025-05-05T13:08:25Z","abstract_excerpt":"Recent advances in visual industrial anomaly detection have demonstrated exceptional performance in identifying and segmenting anomalous regions while maintaining fast inference speeds. However, anomaly classification-distinguishing different types of anomalies-remains largely unexplored despite its critical importance in real-world inspection tasks. To address this gap, we propose VELM, a novel LLM-based pipeline for anomaly classification. Given the critical importance of inference speed, we first apply an unsupervised anomaly detection method as a vision expert to assess the normality of an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02626","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/2505.02626/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":"2505.02626","created_at":"2026-07-05T10:58:40.548698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02626v1","created_at":"2026-07-05T10:58:40.548698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02626","created_at":"2026-07-05T10:58:40.548698+00:00"},{"alias_kind":"pith_short_12","alias_value":"N44RVE352OFY","created_at":"2026-07-05T10:58:40.548698+00:00"},{"alias_kind":"pith_short_16","alias_value":"N44RVE352OFY46BA","created_at":"2026-07-05T10:58:40.548698+00:00"},{"alias_kind":"pith_short_8","alias_value":"N44RVE35","created_at":"2026-07-05T10:58:40.548698+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/N44RVE352OFY46BAHN4KARBXZ2","json":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2.json","graph_json":"https://pith.science/api/pith-number/N44RVE352OFY46BAHN4KARBXZ2/graph.json","events_json":"https://pith.science/api/pith-number/N44RVE352OFY46BAHN4KARBXZ2/events.json","paper":"https://pith.science/paper/N44RVE35"},"agent_actions":{"view_html":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2","download_json":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2.json","view_paper":"https://pith.science/paper/N44RVE35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02626&json=true","fetch_graph":"https://pith.science/api/pith-number/N44RVE352OFY46BAHN4KARBXZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/N44RVE352OFY46BAHN4KARBXZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2/action/storage_attestation","attest_author":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2/action/author_attestation","sign_citation":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2/action/citation_signature","submit_replication":"https://pith.science/pith/N44RVE352OFY46BAHN4KARBXZ2/action/replication_record"}},"created_at":"2026-07-05T10:58:40.548698+00:00","updated_at":"2026-07-05T10:58:40.548698+00:00"}