{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VE3C24RWDWATPBOR3PCFLMSCG2","short_pith_number":"pith:VE3C24RW","schema_version":"1.0","canonical_sha256":"a9362d72361d813785d1dbc455b24236957b853dbb7666a4231efe597f785de2","source":{"kind":"arxiv","id":"2405.14325","version":5},"attestation_state":"computed","paper":{"title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fang Chen, Hongen Liao, Huiqi Li, Jia Guo, Shuai Lu, Weihang Zhang","submitted_at":"2024-05-23T08:55:20Z","abstract_excerpt":"Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images. Despite various advancements addressing this challenging task, the detection performance under the multi-class setting still lags far behind state-of-the-art class-separated models. Our research aims to bridge this substantial performance gap. In this paper, we introduce a minimalistic reconstruction-based anomaly detection framework, namely Dinomaly, which leverages pure Transformer architectures without relying on complex designs, additional modules, or s"},"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":"2405.14325","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T08:55:20Z","cross_cats_sorted":[],"title_canon_sha256":"f75d539fb9909c93ed0974f0372f4855d6873311516556becdfb2fbb45f87aea","abstract_canon_sha256":"1766704084460f9ad3f294a4bac0100643083c9015ee65a7bb5a756edd54ab0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:24.675933Z","signature_b64":"Xx/MD0YYGxNshGwT5l1TbgQ3qdjbotoQWJ/qrvGHkvnlMizy+tv+mf613SDbkg/JDRQyfLZVadpUNpbLcR4bBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9362d72361d813785d1dbc455b24236957b853dbb7666a4231efe597f785de2","last_reissued_at":"2026-07-05T10:43:24.675441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:24.675441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fang Chen, Hongen Liao, Huiqi Li, Jia Guo, Shuai Lu, Weihang Zhang","submitted_at":"2024-05-23T08:55:20Z","abstract_excerpt":"Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images. Despite various advancements addressing this challenging task, the detection performance under the multi-class setting still lags far behind state-of-the-art class-separated models. Our research aims to bridge this substantial performance gap. In this paper, we introduce a minimalistic reconstruction-based anomaly detection framework, namely Dinomaly, which leverages pure Transformer architectures without relying on complex designs, additional modules, or s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14325","kind":"arxiv","version":5},"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/2405.14325/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":"2405.14325","created_at":"2026-07-05T10:43:24.675501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14325v5","created_at":"2026-07-05T10:43:24.675501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14325","created_at":"2026-07-05T10:43:24.675501+00:00"},{"alias_kind":"pith_short_12","alias_value":"VE3C24RWDWAT","created_at":"2026-07-05T10:43:24.675501+00:00"},{"alias_kind":"pith_short_16","alias_value":"VE3C24RWDWATPBOR","created_at":"2026-07-05T10:43:24.675501+00:00"},{"alias_kind":"pith_short_8","alias_value":"VE3C24RW","created_at":"2026-07-05T10:43:24.675501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07149","citing_title":"Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2","json":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2.json","graph_json":"https://pith.science/api/pith-number/VE3C24RWDWATPBOR3PCFLMSCG2/graph.json","events_json":"https://pith.science/api/pith-number/VE3C24RWDWATPBOR3PCFLMSCG2/events.json","paper":"https://pith.science/paper/VE3C24RW"},"agent_actions":{"view_html":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2","download_json":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2.json","view_paper":"https://pith.science/paper/VE3C24RW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14325&json=true","fetch_graph":"https://pith.science/api/pith-number/VE3C24RWDWATPBOR3PCFLMSCG2/graph.json","fetch_events":"https://pith.science/api/pith-number/VE3C24RWDWATPBOR3PCFLMSCG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2/action/storage_attestation","attest_author":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2/action/author_attestation","sign_citation":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2/action/citation_signature","submit_replication":"https://pith.science/pith/VE3C24RWDWATPBOR3PCFLMSCG2/action/replication_record"}},"created_at":"2026-07-05T10:43:24.675501+00:00","updated_at":"2026-07-05T10:43:24.675501+00:00"}