{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDYXSRP6CCQD7HZF5FEBYACEU2","short_pith_number":"pith:NDYXSRP6","schema_version":"1.0","canonical_sha256":"68f17945fe10a03f9f25e9481c0044a69e17cb85954ee8ae1acbc680b257062c","source":{"kind":"arxiv","id":"2503.14162","version":2},"attestation_state":"computed","paper":{"title":"EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiacheng Ruan, Ting Liu, Xian Gao, Yuzhuo Fu, Zongyun Zhang","submitted_at":"2025-03-18T11:33:29Z","abstract_excerpt":"Industrial Anomaly Detection (IAD) is critical to ensure product quality during manufacturing. Although existing zero-shot defect segmentation and detection methods have shown effectiveness, they cannot provide detailed descriptions of the defects. Furthermore, the application of large multi-modal models in IAD remains in its infancy, facing challenges in balancing question-answering (QA) performance and mask-based grounding capabilities, often owing to overfitting during the fine-tuning process. To address these challenges, we propose a novel approach that introduces a dedicated multi-modal d"},"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":"2503.14162","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T11:33:29Z","cross_cats_sorted":[],"title_canon_sha256":"fef03feabfb50046c39b17e3699f5889dff06b1566709571292e10fc5a17a9ad","abstract_canon_sha256":"e0aa10b1153376b69747a5a526befcff49f91916f69a4e6784fb71314c9de3d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:58.210665Z","signature_b64":"AEBGpQ4yewihGJoEN37eRREpHBIXMA5l74HH2PQYc9ekh2kBuo6EXQT/ZtbYcCCsaHaCZR9hmqyVBRZHAsV5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f17945fe10a03f9f25e9481c0044a69e17cb85954ee8ae1acbc680b257062c","last_reissued_at":"2026-07-05T11:03:58.210202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:58.210202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiacheng Ruan, Ting Liu, Xian Gao, Yuzhuo Fu, Zongyun Zhang","submitted_at":"2025-03-18T11:33:29Z","abstract_excerpt":"Industrial Anomaly Detection (IAD) is critical to ensure product quality during manufacturing. Although existing zero-shot defect segmentation and detection methods have shown effectiveness, they cannot provide detailed descriptions of the defects. Furthermore, the application of large multi-modal models in IAD remains in its infancy, facing challenges in balancing question-answering (QA) performance and mask-based grounding capabilities, often owing to overfitting during the fine-tuning process. To address these challenges, we propose a novel approach that introduces a dedicated multi-modal d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14162","kind":"arxiv","version":2},"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/2503.14162/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":"2503.14162","created_at":"2026-07-05T11:03:58.210255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14162v2","created_at":"2026-07-05T11:03:58.210255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14162","created_at":"2026-07-05T11:03:58.210255+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDYXSRP6CCQD","created_at":"2026-07-05T11:03:58.210255+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDYXSRP6CCQD7HZF","created_at":"2026-07-05T11:03:58.210255+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDYXSRP6","created_at":"2026-07-05T11:03:58.210255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.13779","citing_title":"AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10397","citing_title":"AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2","json":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2.json","graph_json":"https://pith.science/api/pith-number/NDYXSRP6CCQD7HZF5FEBYACEU2/graph.json","events_json":"https://pith.science/api/pith-number/NDYXSRP6CCQD7HZF5FEBYACEU2/events.json","paper":"https://pith.science/paper/NDYXSRP6"},"agent_actions":{"view_html":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2","download_json":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2.json","view_paper":"https://pith.science/paper/NDYXSRP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14162&json=true","fetch_graph":"https://pith.science/api/pith-number/NDYXSRP6CCQD7HZF5FEBYACEU2/graph.json","fetch_events":"https://pith.science/api/pith-number/NDYXSRP6CCQD7HZF5FEBYACEU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2/action/storage_attestation","attest_author":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2/action/author_attestation","sign_citation":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2/action/citation_signature","submit_replication":"https://pith.science/pith/NDYXSRP6CCQD7HZF5FEBYACEU2/action/replication_record"}},"created_at":"2026-07-05T11:03:58.210255+00:00","updated_at":"2026-07-05T11:03:58.210255+00:00"}