{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TFGOIYWXTIZKX2JH4WHO3DBVMR","short_pith_number":"pith:TFGOIYWX","schema_version":"1.0","canonical_sha256":"994ce462d79a32abe927e58eed8c35645ab8e30ed56e081cf913bad891125510","source":{"kind":"arxiv","id":"2312.07495","version":2},"attestation_state":"computed","paper":{"title":"Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Dacheng Tao, Jiangning Zhang, Ming-Hsuan Yang, Xiangtai Li, Xuhai Chen, Yabiao Wang, Yong Liu","submitted_at":"2023-12-12T18:28:59Z","abstract_excerpt":"This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultaneously testing both normal and anomaly images across multiple classes. Existing reconstruction-based methods typically adopt pyramidal networks as encoders and decoders to obtain multi-resolution features, often involving complex sub-modules with extensive handcraft engineering. In contrast, a plain Vision Transformer (ViT) showcasing a more straightforward architecture has proven effective in multiple domains, inclu"},"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":"2312.07495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T18:28:59Z","cross_cats_sorted":[],"title_canon_sha256":"79e05299bb663bad6532056eff681c18c90b0cf2b543963e163610dccad6e5cf","abstract_canon_sha256":"a2ef01ec0ab3d415eda33a0df84a66ca21474b66374dfb8bc93db9988cc22a60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:05.651430Z","signature_b64":"2AfSQaieZf47ZJY3CWKlo2abzU6+d/eoRXQEGoxa49TMOExm/emEzRHgmNF196+sVnTCqQDOqffklVnqCuYwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994ce462d79a32abe927e58eed8c35645ab8e30ed56e081cf913bad891125510","last_reissued_at":"2026-07-05T08:54:05.650889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:05.650889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Dacheng Tao, Jiangning Zhang, Ming-Hsuan Yang, Xiangtai Li, Xuhai Chen, Yabiao Wang, Yong Liu","submitted_at":"2023-12-12T18:28:59Z","abstract_excerpt":"This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultaneously testing both normal and anomaly images across multiple classes. Existing reconstruction-based methods typically adopt pyramidal networks as encoders and decoders to obtain multi-resolution features, often involving complex sub-modules with extensive handcraft engineering. In contrast, a plain Vision Transformer (ViT) showcasing a more straightforward architecture has proven effective in multiple domains, inclu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07495","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/2312.07495/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":"2312.07495","created_at":"2026-07-05T08:54:05.650955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07495v2","created_at":"2026-07-05T08:54:05.650955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07495","created_at":"2026-07-05T08:54:05.650955+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFGOIYWXTIZK","created_at":"2026-07-05T08:54:05.650955+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFGOIYWXTIZKX2JH","created_at":"2026-07-05T08:54:05.650955+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFGOIYWX","created_at":"2026-07-05T08:54:05.650955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24375","citing_title":"MATCH: Flow Matching for Multi-View Anomaly Detection","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23126","citing_title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02252","citing_title":"ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24402","citing_title":"Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08664","citing_title":"IPAD-CLIP: Teaching CLIP to Detect Image Local Perceptual Artifacts","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08301","citing_title":"GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR","json":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR.json","graph_json":"https://pith.science/api/pith-number/TFGOIYWXTIZKX2JH4WHO3DBVMR/graph.json","events_json":"https://pith.science/api/pith-number/TFGOIYWXTIZKX2JH4WHO3DBVMR/events.json","paper":"https://pith.science/paper/TFGOIYWX"},"agent_actions":{"view_html":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR","download_json":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR.json","view_paper":"https://pith.science/paper/TFGOIYWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07495&json=true","fetch_graph":"https://pith.science/api/pith-number/TFGOIYWXTIZKX2JH4WHO3DBVMR/graph.json","fetch_events":"https://pith.science/api/pith-number/TFGOIYWXTIZKX2JH4WHO3DBVMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR/action/storage_attestation","attest_author":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR/action/author_attestation","sign_citation":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR/action/citation_signature","submit_replication":"https://pith.science/pith/TFGOIYWXTIZKX2JH4WHO3DBVMR/action/replication_record"}},"created_at":"2026-07-05T08:54:05.650955+00:00","updated_at":"2026-07-05T08:54:05.650955+00:00"}