{"as_of":"2026-08-10T15:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2e49f580aa281c8140ae558ed9e060ce8b6c3a2234b13169affdad696457d352","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T01:53:19.048439Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.14534/citation-record","integrity":"/paper/2607.14534/integrity","json":"/paper/2607.14534/citation-record.json","paper":"/paper/2607.14534"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:14.294871Z","title":"Efficientad: Accurate visual anomaly detection at millisecond-level latencies","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:14.294871Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:41bb2fe1454e27c2ad7b8f75255d03cc9aea08acaf717592c86a57d21d35b471","observation_id":"74ddcf8f-4e3c-4388-b212-b1f168300dc3","resolution":{"observed_at":"2026-08-02T01:53:14.294871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.02011","last_updated":"2019-02-01T16:16:28Z","snapshot_observed_at":"2026-07-06T06:48:34.386900Z","submitted_at":"2018-07-05T14:07:23Z","title":"Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.02011","snapshot_observed_at":"2026-08-02T01:53:14.349477Z","title":"Improving unsupervised defect segmentation by applying structural similarity to autoencoders.arXiv preprint arXiv:1807.02011, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:14.349477Z"},"links":{"cited_paper":"/paper/1807.02011","citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:8cd518529ce9991ba9d25a05a6da83bde9247b4f4a4c3bf72f5f8eaa81e633c1","observation_id":"a7eac0e7-310e-47ae-8d47-fd8d422703ff","resolution":{"observed_at":"2026-08-02T01:53:14.349477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:14.456312Z","title":"Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:14.456312Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:93bbb1a36e7b54fb52eee1ed80a188495b65c54d0171139dd77d79d2f05e4613","observation_id":"0dbf1a15-ee99-45ea-aafc-e6f7ef271aab","resolution":{"observed_at":"2026-08-02T01:53:14.456312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:14.626304Z","title":"Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:14.626304Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:2aaa511c3e07358a1b82137f7573d79e3f257471b9ce6a654ca70b49d06378a2","observation_id":"31a1ec43-ffda-401e-8239-65bd3dde297d","resolution":{"observed_at":"2026-08-02T01:53:14.626304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:14.793973Z","title":"InProceedingsoftheIEEE/CVF internationalconferenceoncomputervision,pages9650–9660,2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:14.793973Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:5afac3f62f35f902e50366f2d11c82e5cfc1b7ee0cbc5b7f33879d75260fa4c1","observation_id":"c7d7a8f2-db7b-444f-b51f-bb87419db016","resolution":{"observed_at":"2026-08-02T01:53:14.793973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:14.965680Z","title":"Detecting anomalous structures by convolutional sparse models","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:14.965680Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:126a7ae7768489b0dc5e59bd22b86d178baad5dae9f2875fc498cef08a51d557","observation_id":"fec128ac-6cf5-43fa-aeee-9feb72dbd346","resolution":{"observed_at":"2026-08-02T01:53:14.965680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.143964Z","title":"Padim: a patch distribution modeling framework for anomaly detection and localization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.143964Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:91ce9dbb7a242bec3ab0f3957560cb348be103b156c2964b83ae05dd77d1c9ec","observation_id":"f1234fad-e944-4563-a570-46ccccccca9b","resolution":{"observed_at":"2026-08-02T01:53:15.143964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.202026Z","title":"Anomaly detection via reverse distil- lation from one-class embedding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.202026Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:ea4fbc156105d6c7418c5b391fb735ac58fa73009cfb0647e8889a473c8dc693","observation_id":"9b8fc930-637b-48f4-998d-9388ee0759cb","resolution":{"observed_at":"2026-08-02T01:53:15.202026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-10T01:12:16.468283Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-02T01:53:15.252677Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.252677Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:96fb1283b1edd42bb2f5d68f541c719f7cfcf1c7caf18ebebdd302a13a85ca90","observation_id":"1d44cd73-a113-4543-ba75-3093edec7b10","resolution":{"observed_at":"2026-08-02T01:53:15.252677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.306560Z","title":"Few-shot defect image generation via defect-aware feature manipulation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.306560Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:f8eb4974ab277c392dfe7c153b0f1df54982a082dfe01fc099e6540ac7036ee1","observation_id":"7832f2a2-d7ba-4f36-921f-cf571d41dede","resolution":{"observed_at":"2026-08-02T01:53:15.306560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.437996Z","title":"Fastrecon: Few-shot industrial anomaly detection via fast feature reconstruction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.437996Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:4d260216ccdebc8042c13a376f1e20784bd20ec6e49697d29e395744026b993d","observation_id":"05c2c989-f0a5-4bc9-81b5-696d38b66de4","resolution":{"observed_at":"2026-08-02T01:53:15.437996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.478300Z","title":"Recon- trast: Domain-specific anomaly detection via contrastive reconstruc- tion.AdvancesinNeuralInformationProcessingSystems,36:10721– 10740, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.478300Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:901ed2c457d2147ba88843aa8dbc0d40b796b938eabfa3fbb31e41c79630667e","observation_id":"8e1a904c-e745-4600-814e-bffe8ab9fdd6","resolution":{"observed_at":"2026-08-02T01:53:15.478300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.533021Z","title":"Dinomaly: The less is more philosophy in multi-class unsuper- visedanomalydetection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.533021Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:64293f7374e6f544eceb7a2dff161e4c0c5a522665512a8a0bbed6451dfef3bf","observation_id":"3ba1d571-fc9b-44f9-ae3b-f7073feb7f8d","resolution":{"observed_at":"2026-08-02T01:53:15.533021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.585683Z","title":"Con- trolling neural collapse enhances out-of-distribution detection and transfer learning.arXiv preprint arXiv:2502.10691, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.585683Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:8f95cef0fe86a461b863b8b8b0253855e8f37ce2fc110411a255abb9932f0ca5","observation_id":"f4d7bed5-b5e5-491b-8bde-41f416cae6f4","resolution":{"observed_at":"2026-08-02T01:53:15.585683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.695824Z","title":"Mambaad: Exploring state space models for multi-class unsupervised anomaly detection.Advances in Neural Information Processing Systems, 37:71162–71187, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.695824Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:2f5e7fe4aeba6b8c69e613266c6ac9c9fbdb8effc48690c839b568b60309bff3","observation_id":"9cf0e6ff-efd8-4ca2-bfdd-a13b4def3a4d","resolution":{"observed_at":"2026-08-02T01:53:15.695824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.806721Z","title":"Adiffusion- based framework for multi-class anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.806721Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:8671034b362efc62bd8851f19dbd3fc059221d3db7ea1077a06340858dff717d","observation_id":"971dfe2d-28f7-442a-84bd-96cbfe573bf2","resolution":{"observed_at":"2026-08-02T01:53:15.806721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:15.913206Z","title":"Vlmdiff:Leveragingvision-languagemodelsformulti-classanomaly detection with diffusion, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:15.913206Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:24edbd623c329fbe5faa4f6115d03d95a155a50907cd1eea220b296dbb59263a","observation_id":"e4e76e0f-28d8-457f-a50b-1dcd67e07bc4","resolution":{"observed_at":"2026-08-02T01:53:15.913206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.020553Z","title":"Registrationbasedfew-shotanomaly detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.020553Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:603bd5aa7d11c34ff865d4d379057a8313f42d363e016b6a0fe4b0060f3cfc34","observation_id":"6e676992-714e-4239-8025-82bca22d2104","resolution":{"observed_at":"2026-08-02T01:53:16.020553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.129221Z","title":"Adversarial discriminative attention for robust anomaly detection","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.129221Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:33798d2ba3fe11961aa6e14f48e747b6121796d88848329556f0cdf2ad869371","observation_id":"a0ef5c18-f90a-4510-9896-b2108c7a6c6e","resolution":{"observed_at":"2026-08-02T01:53:16.129221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.247947Z","title":"Cutpaste: Self-supervised learning for anomaly detection and local- ization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.247947Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:d02d12b1f333f500e4816a363cbfc153371a4f6264be3c2c732c37c9e8c0af2f","observation_id":"c768bb08-3ca9-48b4-b4f7-ec66010c905a","resolution":{"observed_at":"2026-08-02T01:53:16.247947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.351655Z","title":"Ipg-frn: Intrinsic prototype-guided feature reconstruction network for industrial anomaly detection.Expert Systems with Ap- plications, page 132147, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.351655Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:caa3ca438d771531d1d7f0107b2c48f60f225ecaaa8142a665e4abe1442ce295","observation_id":"3545bbfa-10fd-41d9-8d1c-0a68f7723e0e","resolution":{"observed_at":"2026-08-02T01:53:16.351655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.467209Z","title":"Swintransformerv2: Scaling up capacity and resolution","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.467209Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:7961e3a6be7d1934a2acf67a1238fd68c30166f5ef2c05261a1cba8c490c4b0e","observation_id":"d1ef2d3d-ca4e-47ed-a4c0-db5eb5bd8983","resolution":{"observed_at":"2026-08-02T01:53:16.467209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.537234Z","title":"Sim- plenet: A simple network for image anomaly detection and localiza- tion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.537234Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:da5b31d83a19ec3daedec8bb59ef22b6c1de6c3ff2a6299e2f2422c55c7011ce","observation_id":"fe13082c-7bd1-4427-8dfc-952e48150112","resolution":{"observed_at":"2026-08-02T01:53:16.537234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-02T01:53:16.615238Z","title":"Decoupled weight decay regular- ization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.615238Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:efc1283389041571e9b05f0c5bd486261ec57d6020ecbd35cdac88c685360838","observation_id":"51052c37-29ca-4949-bd59-23cbfe84a08b","resolution":{"observed_at":"2026-08-02T01:53:16.615238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.699249Z","title":"Patch distance based auto-encoder for industrial anomaly detection.Expert Systems with Applications, 270:126537, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.699249Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:39e93851f2c05fed2e7e651fe3d82143a490abecb3449d32860ee3a5e28e7391","observation_id":"2e77ea49-a60a-4227-a2b6-dcf5f0cd928f","resolution":{"observed_at":"2026-08-02T01:53:16.699249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.754018Z","title":"Ocgan: One- classnoveltydetectionusingganswithconstrainedlatentrepresenta- tions.InProceedingsoftheIEEE/CVFconferenceoncomputervision and pattern recognition, pages 2898–2906, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.754018Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:9c96ab9c7659ebcc6e9bff8661e8abdab2521537f031091ea1209852cfc2146e","observation_id":"eac09cd2-344e-49e4-beef-e527bc24f019","resolution":{"observed_at":"2026-08-02T01:53:16.754018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.855353Z","title":"Towards total recall in industrial anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.855353Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:cd0cac64756f2541c5b709aacbea8a62001d0397eb3dee44c0fa2ce7dadaf83a","observation_id":"8100e311-b546-431c-b438-91999814d806","resolution":{"observed_at":"2026-08-02T01:53:16.855353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.918115Z","title":"Asymmetric student-teacher networks for industrial anomaly detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.918115Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:d9c8b7501732c0593d1b4ef17dc95ea5cdbbbb053165ef5b5f71162f199cdf0d","observation_id":"adbaa80d-6b9d-49ce-b820-6cd6ba4e1033","resolution":{"observed_at":"2026-08-02T01:53:16.918115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:16.969656Z","title":"Imagenet large scale visual recognition challenge.Internationaljournalofcomputervision,115(3):211–252, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:16.969656Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:715b0766e635dbf08e4181985916281858e3f35b866684a4b2831873f439e0ef","observation_id":"767f418f-f444-440e-bd0b-059d16c78dc4","resolution":{"observed_at":"2026-08-02T01:53:16.969656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.040662Z","title":"Multiresolutionknowledge distillation for anomaly detection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.040662Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:00602a3baefba5e8571a9186fbad22c093dadcae659e7c6f15c98d0a5fa50498","observation_id":"42504fba-8a94-4c3a-80a9-e668125ecaa9","resolution":{"observed_at":"2026-08-02T01:53:17.040662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.113865Z","title":"Natural synthetic anomalies for self-supervised anomaly detection andlocalization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.113865Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:ceb8854cb848421f0e77c1dfcb9d7307da4840cfe8ed77b88b0d4c8d79cb8ad6","observation_id":"0cacb31a-9495-483d-b7c8-cb4ee287cc36","resolution":{"observed_at":"2026-08-02T01:53:17.113865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.174598Z","title":"Real-iad:Areal-worldmulti-viewdatasetforbenchmarkingver- satile industrial anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.174598Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:77c7c1891d24cb8566fffbb78eb372758b5a3ccc281cb3f465d801d075fe8086","observation_id":"fb98a5be-14f4-4aaf-885f-dd6a82c59701","resolution":{"observed_at":"2026-08-02T01:53:17.174598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.244786Z","title":"Student- teacher feature pyramid matching for anomaly detection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.244786Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:08624454bb926a2ba6ffe5685851fcd84dc8a0203637399a75d9e1f5b038550e","observation_id":"88100a41-abd9-47c8-bac6-bb66b21cb1e8","resolution":{"observed_at":"2026-08-02T01:53:17.244786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.04257","last_updated":"2021-10-28T09:17:34Z","snapshot_observed_at":"2026-08-06T23:00:30.967037Z","submitted_at":"2021-03-07T04:25:04Z","title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.04257","snapshot_observed_at":"2026-08-02T01:53:17.306977Z","title":"Student- teacher feature pyramid matching for anomaly detection.arXiv preprint arXiv:2103.04257, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.306977Z"},"links":{"cited_paper":"/paper/2103.04257","citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:a17925927842d8fe6cd4c94c1718b85db806d19a901431fc11e6be3db6d297ee","observation_id":"bfbff450-ce7e-470e-8e1a-0d188f548944","resolution":{"observed_at":"2026-08-02T01:53:17.306977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.406356Z","title":"Uninet: A contrastive learning-guidedunifiedframeworkwithfeatureselectionforanomaly detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.406356Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:399fe4d59de848b474f7688efcc681d4034a8401f15ce3e9b150305efdca93b2","observation_id":"099a4abd-32e1-4e7c-8cf5-3a1f1626164b","resolution":{"observed_at":"2026-08-02T01:53:17.406356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.07122","last_updated":"2020-12-13T18:30:51Z","snapshot_observed_at":"2026-08-09T08:48:21.868623Z","submitted_at":"2020-12-13T18:30:51Z","title":"DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.07122","snapshot_observed_at":"2026-08-02T01:53:17.488532Z","title":"Dfr: Deep feature recon- struction for unsupervised anomaly segmentation.arXiv preprint arXiv:2012.07122, 2020","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.488532Z"},"links":{"cited_paper":"/paper/2012.07122","citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:5ae15e5eb092457db233a234ce996b52f1d6b84b832f713b71b77df6c97c2e8d","observation_id":"2bd6df22-10dc-42bc-94a0-787484993800","resolution":{"observed_at":"2026-08-02T01:53:17.488532Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08059","last_updated":"2023-07-16T14:41:22Z","snapshot_observed_at":"2026-08-09T12:08:07.374798Z","submitted_at":"2023-07-16T14:41:22Z","title":"LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08059","snapshot_observed_at":"2026-08-02T01:53:17.544448Z","title":"Lafite: Latent diffusion model with featureeditingforunsupervisedmulti-classanomalydetection.arXiv preprint arXiv:2307.08059, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.544448Z"},"links":{"cited_paper":"/paper/2307.08059","citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:788092fbd30ff31671b9be643261c0a4da0f1700abbc80c490dab44a65e578d2","observation_id":"7a4171ba-8603-48c1-a703-68f28dcc4921","resolution":{"observed_at":"2026-08-02T01:53:17.544448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.614342Z","title":"A unified model for multi-class anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.614342Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:937bd32daf6e1f74ee4c1a7c8b36e3e69727b89bee9a91a447bbf2785daa227d","observation_id":"09e69f07-ba31-4b61-81bd-8f3fdf9d8668","resolution":{"observed_at":"2026-08-02T01:53:17.614342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.668086Z","title":"Draem - a dis- criminatively trained reconstruction embedding for surface anomaly detection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.668086Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:088a09ecbe1aab647ccc3372c31dc3cffd859aa0e98d3b7c692aa3edace12083","observation_id":"0e0f07be-90d7-4fac-b9fc-bad54d618d6f","resolution":{"observed_at":"2026-08-02T01:53:17.668086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.672059Z","title":"Dsr–a dual subspace re-projection network for surface anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.672059Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:aa779f82022d9cb12bca4fad2eb0db8aa2ff93f1ae190ce73c8a87de4f10b577","observation_id":"dfe4b877-ec05-4f19-9f73-55f796a502bd","resolution":{"observed_at":"2026-08-02T01:53:17.672059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:17.742930Z","title":"A diverse embedding-based composite reconstruction encoder– decoder for color fabric defect detection.Expert Systems with Applications, 278:127261, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.742930Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:d9fb57432efae004c73f6deb8a640ffe19224331a5373cac088f86fa99978d76","observation_id":"57fa82e9-d63b-43cb-a2fe-77efbf09c258","resolution":{"observed_at":"2026-08-02T01:53:17.742930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.03262","last_updated":"2025-08-19T02:35:24Z","snapshot_observed_at":"2026-08-10T03:51:30.148257Z","submitted_at":"2024-06-05T13:40:07Z","title":"A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.03262","snapshot_observed_at":"2026-08-02T01:53:17.968869Z","title":"Ader: A comprehensive benchmark for multi-class visual anomaly detection.arXiv preprint arXiv:2406.03262, 1(4), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:17.968869Z"},"links":{"cited_paper":"/paper/2406.03262","citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:1bdac808c64cbe0ed748eaac4779bdff6d3463637d1f3c852b7a0976a8333003","observation_id":"7c89c6d2-3ad2-4a7b-bf7d-5b22723fadde","resolution":{"observed_at":"2026-08-02T01:53:17.968869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:18.221622Z","title":"Exploring plain vit features for multi-class unsupervised visual anomaly detec- tion.ComputerVisionandImageUnderstanding,253:104308,2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:18.221622Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:97be0e8c7ad0abdbe673bd92d0ed76b625b412648bb2ac24550f23c4d949fc1b","observation_id":"99545fb3-627e-4d42-b203-b51f57e25a9d","resolution":{"observed_at":"2026-08-02T01:53:18.221622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:18.395654Z","title":"Adaptive frequency modulated transformer for industrialsurfacedefectdetection.ExpertSystemswithApplications, page 132502, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:18.395654Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:1717cd9fc49824adbe5a7fe803892cfce07aa204ad5a617c764172aa582fc83e","observation_id":"10179101-dca3-4051-810c-c705fd712d14","resolution":{"observed_at":"2026-08-02T01:53:18.395654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:18.512875Z","title":"Destseg: Segmentation guided denoising student-teacher for anomaly detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:18.512875Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:e665e00686dc7532b5c221eb45aac61220c370ed7c5ae219fcbec7906f246791","observation_id":"ba961156-4514-4636-9690-b6eb8208d326","resolution":{"observed_at":"2026-08-02T01:53:18.512875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:18.598780Z","title":"Omnial: A unified cnn framework for unsupervised anomaly localization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:18.598780Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:8956a7dfa4e68c84c6f5135bfc46ac4c1bcba21061c7ed71f3b0af06d965c3d3","observation_id":"9a85d9d3-965a-4573-b0ff-1ef8e1d22e9d","resolution":{"observed_at":"2026-08-02T01:53:18.598780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:18.702869Z","title":"Fad:Featureaugmenteddistillationforanomaly detection and localization.Expert Systems with Applications, 288: 128249, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:18.702869Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:a5026bdce8896195958652eb40366179b6d2891a803b5fbe0687200359f914b9","observation_id":"f1db2ed3-dbaf-42f7-9870-797af453f787","resolution":{"observed_at":"2026-08-02T01:53:18.702869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:18.930722Z","title":"Class- incremental learning via dual augmentation.Advances in neural information processing systems, 34:14306–14318, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:18.930722Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:215f6c335aefb64b4479f9428451fd54b2891aadff136cdd0b1eeb587f46ae87","observation_id":"56b664ce-3faa-421e-b62e-db3b64ff8408","resolution":{"observed_at":"2026-08-02T01:53:18.930722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:53:19.048439Z","title":"Spot-the-difference self-supervised pre-training for anomaly detection and segmentation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T01:53:19.048439Z"},"links":{"citing_paper":"/paper/2607.14534"},"observation_digest":"sha256:2adc39dd4f4282b021abf6c90dcde26ba8d776387d9ab5abf2d7510846e51725","observation_id":"65bcf891-b8cc-4ccd-a8a6-e6dff9081337","resolution":{"observed_at":"2026-08-02T01:53:19.048439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.14534","last_updated":"2026-07-16T03:39:56Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T10:53:48.541610Z","submitted_at":"2026-07-16T03:39:56Z","title":"SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":49,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":49},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2607.14534."}