{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UKBRGDF3OE2BUTZL2DD7K3BULU","short_pith_number":"pith:UKBRGDF3","schema_version":"1.0","canonical_sha256":"a283130cbb71341a4f2bd0c7f56c345d24f8a755b41e4cadda505d0a7030eeac","source":{"kind":"arxiv","id":"2403.12362","version":1},"attestation_state":"computed","paper":{"title":"DMAD: Dual Memory Bank for Real-World Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Jiangning Zhang, Jianlong Hu, Jinlong Peng, Liujuan Cao, Rongrong Ji, Shengchuan Zhang, Xu Chen, Yabiao Wang, Zhenye Gan","submitted_at":"2024-03-19T02:16:32Z","abstract_excerpt":"Training a unified model is considered to be more suitable for practical industrial anomaly detection scenarios due to its generalization ability and storage efficiency. However, this multi-class setting, which exclusively uses normal data, overlooks the few but important accessible annotated anomalies in the real world. To address the challenge of real-world anomaly detection, we propose a new framework named Dual Memory bank enhanced representation learning for Anomaly Detection (DMAD). This framework handles both unsupervised and semi-supervised scenarios in a unified (multi-class) setting."},"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":"2403.12362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T02:16:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"39d43960076e77452a26bf6e4405cf92f939a5d6b86c16254e26a225a51f0210","abstract_canon_sha256":"e0ac932c39b0de4e20f647cb6dc55b23029102014abce9d0abb60fba453692de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:00.131393Z","signature_b64":"rb5zDFdCUzLxTuZuwqOw1exaTLXYcyTeZtAMJ1EGg4mAr7SUJqKeb5glinI2dYYziZhXXrjy9Q+P5iLxYZo/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a283130cbb71341a4f2bd0c7f56c345d24f8a755b41e4cadda505d0a7030eeac","last_reissued_at":"2026-07-05T07:58:00.129696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:00.129696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMAD: Dual Memory Bank for Real-World Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Jiangning Zhang, Jianlong Hu, Jinlong Peng, Liujuan Cao, Rongrong Ji, Shengchuan Zhang, Xu Chen, Yabiao Wang, Zhenye Gan","submitted_at":"2024-03-19T02:16:32Z","abstract_excerpt":"Training a unified model is considered to be more suitable for practical industrial anomaly detection scenarios due to its generalization ability and storage efficiency. However, this multi-class setting, which exclusively uses normal data, overlooks the few but important accessible annotated anomalies in the real world. To address the challenge of real-world anomaly detection, we propose a new framework named Dual Memory bank enhanced representation learning for Anomaly Detection (DMAD). This framework handles both unsupervised and semi-supervised scenarios in a unified (multi-class) setting."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12362","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/2403.12362/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":"2403.12362","created_at":"2026-07-05T07:58:00.130875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12362v1","created_at":"2026-07-05T07:58:00.130875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12362","created_at":"2026-07-05T07:58:00.130875+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKBRGDF3OE2B","created_at":"2026-07-05T07:58:00.130875+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKBRGDF3OE2BUTZL","created_at":"2026-07-05T07:58:00.130875+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKBRGDF3","created_at":"2026-07-05T07:58:00.130875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14808","citing_title":"SuperADD: Training-free Class-agnostic Anomaly Segmentation -- CVPR 2026 VAND 4.0 Workshop Challenge Industrial Track","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU","json":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU.json","graph_json":"https://pith.science/api/pith-number/UKBRGDF3OE2BUTZL2DD7K3BULU/graph.json","events_json":"https://pith.science/api/pith-number/UKBRGDF3OE2BUTZL2DD7K3BULU/events.json","paper":"https://pith.science/paper/UKBRGDF3"},"agent_actions":{"view_html":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU","download_json":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU.json","view_paper":"https://pith.science/paper/UKBRGDF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12362&json=true","fetch_graph":"https://pith.science/api/pith-number/UKBRGDF3OE2BUTZL2DD7K3BULU/graph.json","fetch_events":"https://pith.science/api/pith-number/UKBRGDF3OE2BUTZL2DD7K3BULU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU/action/storage_attestation","attest_author":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU/action/author_attestation","sign_citation":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU/action/citation_signature","submit_replication":"https://pith.science/pith/UKBRGDF3OE2BUTZL2DD7K3BULU/action/replication_record"}},"created_at":"2026-07-05T07:58:00.130875+00:00","updated_at":"2026-07-05T07:58:00.130875+00:00"}