{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CFCO5KAGTUYI32VLDLP32FRJMY","short_pith_number":"pith:CFCO5KAG","schema_version":"1.0","canonical_sha256":"1144eea8069d308deaab1adfbd162966144a19cadab4116dc58e7d5983282ee3","source":{"kind":"arxiv","id":"2410.09453","version":3},"attestation_state":"computed","paper":{"title":"MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Bin-Bin Gao, Chengjie Wang, Feng Zheng, Hanqiu Deng, Jialin Li, Jian Li, Xi Jiang, Yifeng Zhou, Yong Liu","submitted_at":"2024-10-12T09:16:09Z","abstract_excerpt":"In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities. However, despite their impressive problem-solving skills in many domains, MLLMs' ability in industrial anomaly detection has not been systematically studied. To bridge this gap, we present MMAD, the first-ever full-spectrum MLLMs benchmark in industrial Anomaly Detection. We defined seven key subtasks of MLLMs in industrial inspection and designed a novel pipeline to generat"},"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":"2410.09453","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-12T09:16:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f61c1f9e1212082fca039a8751ce74e8bade20c56575fb31f48e3703fbaf7df7","abstract_canon_sha256":"36c33b2d1b15ebf37bbddac49da0a099b4393d6e37559c082f8339fb415fb18e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:50.692891Z","signature_b64":"7wfnlrMQn3FfiBgN77YZYp/9mGGQ/0JmCKZfoB7KWqtTuJsCEPfnHvvnkAnwg23ukE9M7zhdKJCr3SvCyjdUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1144eea8069d308deaab1adfbd162966144a19cadab4116dc58e7d5983282ee3","last_reissued_at":"2026-07-05T10:17:50.692389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:50.692389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Bin-Bin Gao, Chengjie Wang, Feng Zheng, Hanqiu Deng, Jialin Li, Jian Li, Xi Jiang, Yifeng Zhou, Yong Liu","submitted_at":"2024-10-12T09:16:09Z","abstract_excerpt":"In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language capabilities and generalization abilities. However, despite their impressive problem-solving skills in many domains, MLLMs' ability in industrial anomaly detection has not been systematically studied. To bridge this gap, we present MMAD, the first-ever full-spectrum MLLMs benchmark in industrial Anomaly Detection. We defined seven key subtasks of MLLMs in industrial inspection and designed a novel pipeline to generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09453","kind":"arxiv","version":3},"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/2410.09453/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":"2410.09453","created_at":"2026-07-05T10:17:50.692450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09453v3","created_at":"2026-07-05T10:17:50.692450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09453","created_at":"2026-07-05T10:17:50.692450+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFCO5KAGTUYI","created_at":"2026-07-05T10:17:50.692450+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFCO5KAGTUYI32VL","created_at":"2026-07-05T10:17:50.692450+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFCO5KAG","created_at":"2026-07-05T10:17:50.692450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07953","citing_title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28401","citing_title":"Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18169","citing_title":"PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13671","citing_title":"AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09850","citing_title":"Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03066","citing_title":"Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12440","citing_title":"IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08615","citing_title":"MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07413","citing_title":"FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY","json":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY.json","graph_json":"https://pith.science/api/pith-number/CFCO5KAGTUYI32VLDLP32FRJMY/graph.json","events_json":"https://pith.science/api/pith-number/CFCO5KAGTUYI32VLDLP32FRJMY/events.json","paper":"https://pith.science/paper/CFCO5KAG"},"agent_actions":{"view_html":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY","download_json":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY.json","view_paper":"https://pith.science/paper/CFCO5KAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09453&json=true","fetch_graph":"https://pith.science/api/pith-number/CFCO5KAGTUYI32VLDLP32FRJMY/graph.json","fetch_events":"https://pith.science/api/pith-number/CFCO5KAGTUYI32VLDLP32FRJMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY/action/storage_attestation","attest_author":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY/action/author_attestation","sign_citation":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY/action/citation_signature","submit_replication":"https://pith.science/pith/CFCO5KAGTUYI32VLDLP32FRJMY/action/replication_record"}},"created_at":"2026-07-05T10:17:50.692450+00:00","updated_at":"2026-07-05T10:17:50.692450+00:00"}