{"as_of":"2026-08-10T12:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5bd057cd14c37593251362ce9861cc849495f38a4acde66468b7a2a28eec9e46","coverage":[{"denominator":149,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:06:24.744696Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"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/2507.16946/citation-record","integrity":"/paper/2507.16946/integrity","json":"/paper/2507.16946/citation-record.json","paper":"/paper/2507.16946"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:24.361848Z","title":"CableInspect-AD: An expert- annotated anomaly detection dataset","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.361848Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:0031973e9dcf9aebc69d4599448f20f428ad33b28a3958e4c29d3fab8873be06","observation_id":"89ed104e-0305-4cdf-96d0-660613f13f83","resolution":{"observed_at":"2026-08-06T15:06:24.361848Z","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":"2026-08-06T15:06:24.366515Z","title":"Dual-path frequency discriminators for few-shot anomaly detection.Knowledge- Based Systems, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.366515Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:ad63a64abe8af8bb9f85dae21e0112a41b2bdc1c0c30b33c588ada5d5b55bf77","observation_id":"d43d208f-cacb-4048-8c9e-aa5ccd256e81","resolution":{"observed_at":"2026-08-06T15:06:24.366515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.02314","last_updated":"2021-09-12T20:26:52Z","snapshot_observed_at":"2026-08-06T01:56:28.054412Z","submitted_at":"2021-07-05T23:12:06Z","title":"The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.02314","snapshot_observed_at":"2026-08-06T15:06:24.370603Z","title":"The rsna-asnr-miccai brats 2021 benchmark on brain tumor segmentation and radiogenomic classification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.370603Z"},"links":{"cited_paper":"/paper/2107.02314","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:e7e9967eae613d612b40f9dbcec4b2bda304b403ba9c8bfa1357b99f08f0286e","observation_id":"4a1c38fd-9cf4-4c45-894f-e7ce1a350dc5","resolution":{"observed_at":"2026-08-06T15:06:24.370603Z","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":"2026-08-06T15:06:24.374948Z","title":"BMAD: Benchmarks for med- ical anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.374948Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:6402aac0f50563ddb6ee8305644cd8397b1fdcfa94e11070329d666c338819b8","observation_id":"bf241d17-0584-4289-ade4-a94ab95d21e3","resolution":{"observed_at":"2026-08-06T15:06:24.374948Z","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":"2026-08-06T15:06:24.378802Z","title":"MVTec AD–a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.378802Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:195b4d55a7f2864ec5624b932c2d287b4f100be9e925cb594a747a6f196e5985","observation_id":"c242c33d-caa3-4bcb-9a92-34cd841bb6eb","resolution":{"observed_at":"2026-08-06T15:06:24.378802Z","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":"2026-08-06T15:06:24.382686Z","title":"The liver tumor segmentation benchmark (lits)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.382686Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:3947064ebdd103857de5c497c4efe0f444bf20d518754bcfd582edaa50a7c26a","observation_id":"aceefc85-d53f-4117-98ba-9b37b46e4a81","resolution":{"observed_at":"2026-08-06T15:06:24.382686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10724","last_updated":"2023-05-18T05:52:06Z","snapshot_observed_at":"2026-07-06T15:29:05.031168Z","submitted_at":"2023-05-18T05:52:06Z","title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10724","snapshot_observed_at":"2026-08-06T15:06:24.386401Z","title":"Segment any anomaly without training via hybrid prompt regularization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.386401Z"},"links":{"cited_paper":"/paper/2305.10724","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:93510f208716e66a099c38a38e81b7aab6ecf6bcab1ff0ff54bcf6388aa16017","observation_id":"afd10c94-7f5b-4916-9bbf-1cebbcd3b111","resolution":{"observed_at":"2026-08-06T15:06:24.386401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16402","last_updated":"2024-01-29T18:41:21Z","snapshot_observed_at":"2026-08-09T08:20:16.324902Z","submitted_at":"2024-01-29T18:41:21Z","title":"A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16402","snapshot_observed_at":"2026-08-06T15:06:24.391064Z","title":"A survey on visual anomaly detection: Challenge, approach, and prospect","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.391064Z"},"links":{"cited_paper":"/paper/2401.16402","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:c79202d7a39703732f2bea1314634966f1fb072b2efaaf4198c4adfa69e941e7","observation_id":"451ac339-7fed-44e0-b369-95bb97edd32f","resolution":{"observed_at":"2026-08-06T15:06:24.391064Z","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":"2026-08-06T15:06:24.395760Z","title":"AdaCLIP: Adapt- ing CLIP with hybrid learnable prompts for zero-shot anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.395760Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:fae19fb0aada4f1522f6059b489eab5cdb7d5b43fe89fed4b5b50a628491a8d7","observation_id":"32793536-dfba-45ad-ad8c-8b19c2869a8c","resolution":{"observed_at":"2026-08-06T15:06:24.395760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18197","last_updated":"2024-09-11T01:26:34Z","snapshot_observed_at":"2026-07-06T18:37:13.064013Z","submitted_at":"2024-06-26T09:29:05Z","title":"Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme","version":4},"cited_work":{"arxiv_id":"2406.18197","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.18197","snapshot_observed_at":"2026-08-06T15:06:25.701534Z","title":"Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme","venue":"cs.CV","work_id":"12fcc718-0747-4fc8-a685-4aae627df3b3","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.399458Z"},"links":{"cited_paper":"/paper/2406.18197","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:398fcd17ca6bdf639721b3ac5b7627d0dfa2d4f5ac36d7c80a0523f6a253c504","observation_id":"2cdc66dd-64b9-44d4-9763-0194751a339a","resolution":{"observed_at":"2026-08-06T15:06:25.705759Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:24.403632Z","title":"A unified anomaly synthesis strategy with gradient ascent for industrial anomaly detection and localization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.403632Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:342eda4a2871fd4ea6354f793b9951cc81b695392ecc1243d01f818afc84ce6a","observation_id":"4d108bb2-d6a7-42c8-83a7-6a1aa245c268","resolution":{"observed_at":"2026-08-06T15:06:24.403632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.02357","last_updated":"2021-02-03T16:28:51Z","snapshot_observed_at":"2026-08-09T14:17:32.431497Z","submitted_at":"2020-05-05T17:43:35Z","title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.02357","snapshot_observed_at":"2026-08-06T15:06:24.407310Z","title":"Sub-image anomaly detec- tion with deep pyramid correspondences","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.407310Z"},"links":{"cited_paper":"/paper/2005.02357","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:b792d5f1cb821b7b1b04b57f046fde5c2755b1b96b6a385f23705abfe8ede1d6","observation_id":"503cec6b-8f00-42fb-a66e-2e2239624cee","resolution":{"observed_at":"2026-08-06T15:06:24.407310Z","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":"2026-08-06T15:06:24.411669Z","title":"Microsoft Copilot, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.411669Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:c5febaf301d951f9c21319edf7850271377f1c7019af8b08c4d91fc3a87cd425","observation_id":"8a4daed3-a86e-4337-88b6-e14cf1808bb1","resolution":{"observed_at":"2026-08-06T15:06:24.411669Z","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":"2026-08-06T15:06:24.415451Z","title":"PaDiM: a patch distribution modeling framework for anomaly detection and localization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.415451Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:6e747129fe48ec3b275ff6fdb1ff91b5b8ddefd3e1af306a604b8810d581ec88","observation_id":"85145034-1843-41f0-9919-d95f3de7fa8a","resolution":{"observed_at":"2026-08-06T15:06:24.415451Z","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":"2026-08-06T15:06:24.419969Z","title":"Anomaly detection via reverse distillation from one-class embedding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.419969Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:b5ab801e7f797a935615d9cc490d2d170408820629b96ab806cdf3082c101dfa","observation_id":"3b14db45-d729-4dc0-a132-8e7ddbdb161b","resolution":{"observed_at":"2026-08-06T15:06:24.419969Z","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":"2026-08-06T15:06:24.423783Z","title":"Continual learning for anomaly detection in surveillance videos","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.423783Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:269027ce11e19cab4a5a005012837d1830a0acf819ee6f2aaed14b380321cbe5","observation_id":"b7a70748-717a-42d9-9e3e-cf8014e2213a","resolution":{"observed_at":"2026-08-06T15:06:24.423783Z","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":"2026-08-06T15:06:24.427450Z","title":"Transformers: Align model docu- mentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.427450Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:45ce7fa3353a6b4e34c743804e3d366e05ea18a23b1ba33a2c34976de8535fd0","observation_id":"5bb3771f-d3ed-4873-b3a3-f45585defd37","resolution":{"observed_at":"2026-08-06T15:06:24.427450Z","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":"2026-08-06T15:06:24.431447Z","title":"ChangeChip: A reference-based unsupervised change de- tection for PCB defect detection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.431447Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:c7843a36ccfe3d303676911f0e0f5f4b4eecc2456e13dc33c4f1e74f371101ea","observation_id":"6e24a02c-66af-4c75-a961-f89d8e8568f3","resolution":{"observed_at":"2026-08-06T15:06:24.431447Z","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":"2026-08-06T15:06:24.435062Z","title":"TransFusion–a transparency-based diffusion model for anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.435062Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:4b5b2de1c0c2bdc98729f214fa0df0bef03d0267abdb8ca76b3c8dd989c9f1a0","observation_id":"3050249a-4db8-459e-b35e-0c7786763d72","resolution":{"observed_at":"2026-08-06T15:06:24.435062Z","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":"2026-08-06T15:06:24.438879Z","title":"Leveraging vector-quantized variational autoencoder inner metrics for anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.438879Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:a39c59215f2944fcca817bc6c6262d67744bc99519d3fa4c906e1a878148a549","observation_id":"47a3b7fa-49f4-4940-a097-f2a9811b3c0f","resolution":{"observed_at":"2026-08-06T15:06:24.438879Z","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":"2026-08-06T15:06:24.443132Z","title":"Learning to detect multi-class anomalies with just one normal image prompt","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.443132Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:7942114e1eebcf4a4b36d3bf8cc08dd17dbea350b1dd01665feca5d13733fbca","observation_id":"e9a18568-99bd-4b21-aa27-09c62c38a58d","resolution":{"observed_at":"2026-08-06T15:06:24.443132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15652","last_updated":"2023-05-25T01:58:42Z","snapshot_observed_at":"2026-07-06T15:33:02.985929Z","submitted_at":"2023-05-25T01:58:42Z","title":"Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial Vision","version":1},"cited_work":{"arxiv_id":"2305.15652","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.15652","snapshot_observed_at":"2026-08-06T15:06:25.668800Z","title":"Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial Vision","venue":"cs.CV","work_id":"cc0c8830-366d-49f7-96f3-58cc97d758e8","year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.446883Z"},"links":{"cited_paper":"/paper/2305.15652","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:cd07e4b4d5bb0b88306a7939c4cdbf0dab723452463f4cb32eca23ddd8b81415","observation_id":"555185e9-f467-40c2-b9e0-feb38847393d","resolution":{"observed_at":"2026-08-06T15:06:25.673128Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:24.451030Z","title":"Real-time evaluation in online continual learning: A new hope","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.451030Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:65a131f787cd1ecad560b38534c78b66ad8fcfa8b6a603fd6390cf65454373d7","observation_id":"b8245ceb-9518-435e-ae7f-e9f7be8dde1f","resolution":{"observed_at":"2026-08-06T15:06:24.451030Z","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":"2026-08-06T15:06:24.455733Z","title":"Filo: Zero-shot anomaly detection by fine-grained description and high- quality localization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.455733Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:8b19ec2ce2420919ed81f82fb59ef3f23687d547f7b27b8e27ca3e43fbf4959b","observation_id":"de0432bd-4cab-4ffb-8e9b-06580ccc4a83","resolution":{"observed_at":"2026-08-06T15:06:24.455733Z","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":"2026-08-06T15:06:24.459671Z","title":"AnomalyGPT: Detecting in- dustrial anomalies using large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.459671Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:99d917e99e1b48b18631759e6e152b63a116d133dc2d2c5c86755dfb6bbaf727","observation_id":"d14a1a43-1116-4539-bd66-a58b9980b8ca","resolution":{"observed_at":"2026-08-06T15:06:24.459671Z","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":"2026-08-06T15:06:24.463769Z","title":"Few-shot anomaly-driven generation for anomaly classification and segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.463769Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:ed6ac0fe642c5cc9719f85cec828100c118dbf65165dcb6c0bdc76e98a16209e","observation_id":"6342e330-054b-4d99-b355-abcb219fa22b","resolution":{"observed_at":"2026-08-06T15:06:24.463769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00724","last_updated":"2024-04-16T13:28:22Z","snapshot_observed_at":"2026-08-10T11:08:40.136882Z","submitted_at":"2024-03-31T15:50:52Z","title":"Absolute-Unified Multi-Class Anomaly Detection via Class-Agnostic Distribution Alignment","version":2},"cited_work":{"arxiv_id":"2404.00724","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.00724","snapshot_observed_at":"2026-08-06T15:06:25.650682Z","title":"Absolute-Unified Multi-Class Anomaly Detection via Class-Agnostic Distribution Alignment","venue":"cs.CV","work_id":"a513389c-9bee-4bb6-9dff-c2b5be2c7fcf","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.467770Z"},"links":{"cited_paper":"/paper/2404.00724","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:2c8deba26e1cbdb62df42c2e90d56247a55362b036af832262610c135c827adf","observation_id":"8fb96994-77bb-4e2e-ab98-3b326cabc2e2","resolution":{"observed_at":"2026-08-06T15:06:25.655152Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:24.471690Z","title":"Br35H: Brain tumor detection 2020,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.471690Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:c01f890da849ddbdd402bee9cf78adbe6c9482f314325e8f4be637b3c8af1515","observation_id":"2c1dcd65-2da6-4b91-aa9c-7bb2d0c41ef9","resolution":{"observed_at":"2026-08-06T15:06:24.471690Z","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":"2026-08-06T15:06:24.475848Z","title":"OneLLM: One framework to align all modali- ties with language","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.475848Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:97548bd5fa0966d9e5acf885082627a1a0c71bbe8ef0c772b86a2e1db8486577","observation_id":"b7c29ef9-8995-4a89-b60b-1a7509978757","resolution":{"observed_at":"2026-08-06T15:06:24.475848Z","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":"2026-08-06T15:06:24.479562Z","title":"MambaAD: Exploring state space models for multi-class unsupervised anomaly detec- tion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.479562Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:32cc3917bc79163295bd5d35d5a56046d61006da7b9e6aea1bf0b31b6ebd898d","observation_id":"97945ddd-cb55-4a0f-99fa-c96cc6f28a39","resolution":{"observed_at":"2026-08-06T15:06:24.479562Z","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":"2026-08-06T15:06:24.483587Z","title":"A diffusion-based framework for multi-class anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.483587Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:4f11a9f96fb7f512050c24b0965261087f749535803c26000746ca9147aae197","observation_id":"cbc2afdd-eac9-44fa-a476-a46fad0b36a4","resolution":{"observed_at":"2026-08-06T15:06:24.483587Z","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":"2026-08-06T15:06:24.487874Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.487874Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:73ad1d3c0cac2112fed6ac0855abcef44782202dbd17809279f4337a537953dd","observation_id":"2b05d1f6-21ef-4896-9098-80618a619c91","resolution":{"observed_at":"2026-08-06T15:06:24.487874Z","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":"2026-08-06T15:06:24.491854Z","title":"Learning unified reference rep- resentation for unsupervised multi-class anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.491854Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:f94ea4c959c0eba0555b07efb13bc44bc89a9107d69a8c13eb521c1c1893eb43","observation_id":"9f88ccc1-935b-41b8-be92-8a29791cfa55","resolution":{"observed_at":"2026-08-06T15:06:24.491854Z","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":"2026-08-06T15:06:24.496025Z","title":"Long-tailed anomaly detection with learnable class names","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.496025Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:70f1508fa4a71352b2bd21e45aacdc98bbf3f3a583f519dcf4341844d4a67d8b","observation_id":"b07a383f-ef73-4fa5-ae50-90eade01e1a3","resolution":{"observed_at":"2026-08-06T15:06:24.496025Z","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":"2026-08-06T15:06:24.499484Z","title":"Automated seg- mentation of macular edema in oct using deep neural net- works","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.499484Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:52b62d2743b0081ff465098ad611a2fd3f01e197ab96abef25f276fcb7be93e9","observation_id":"aa015249-eb91-4121-8a05-2fc6fddf56d2","resolution":{"observed_at":"2026-08-06T15:06:24.499484Z","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":"2026-08-06T15:06:24.502923Z","title":"Registration based few-shot anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.502923Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:60e9d21c436391c418344ee5e2717d093f24048fc1a8a959f222ff05e4fb4572","observation_id":"dbb625ac-6bc9-4800-b5b7-236d66281da6","resolution":{"observed_at":"2026-08-06T15:06:24.502923Z","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":"2026-08-06T15:06:24.506519Z","title":"Adapting visual- language models for generalizable anomaly detection in medical images","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.506519Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:ed841da79506c7d27a9e86a7381bdccc5beba6cabd47205f7f0e595f3efa957a","observation_id":"6e69525d-a94d-4937-9815-da80bb436461","resolution":{"observed_at":"2026-08-06T15:06:24.506519Z","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":"2026-08-06T15:06:24.510195Z","title":"ReCon- Patch: Contrastive patch representation learning for indus- trial anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.510195Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:80357c2c0cc222f26b3f29cc030ac651942e83492bcc20849818357acf17cbfa","observation_id":"7f8665c5-327c-4cd9-ac96-b556529b95cb","resolution":{"observed_at":"2026-08-06T15:06:24.510195Z","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":"2026-08-06T15:06:24.513734Z","title":"Towards open-world object-based anomaly detection via self-supervised outlier synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.513734Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:fae9affa7568be938699e2cf97244325181c52521162a4272e8405c711485eed","observation_id":"ee3b911d-cefb-427c-b6ad-f7bb84690d3a","resolution":{"observed_at":"2026-08-06T15:06:24.513734Z","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":"2026-08-06T15:06:24.517398Z","title":"WinCLIP: Zero- /few-shot anomaly classification and segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.517398Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:3b2f329d3352ac9972b67202c424da8a90a2f8cf6bfe1360435672e7dace08e5","observation_id":"6d240a20-fbb6-4bec-8ee7-9e33bf18ccc7","resolution":{"observed_at":"2026-08-06T15:06:24.517398Z","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":"2026-08-06T15:06:24.520860Z","title":"Scaling up visual and vision-language representation learning with noisy text supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.520860Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:71edd80ed5266390dd3c8c8190a7ff4f8e3390c3b4aca651c5b4b99a8ca796a3","observation_id":"4ac40283-b55e-404d-bc32-8387862c7dce","resolution":{"observed_at":"2026-08-06T15:06:24.520860Z","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":"2026-08-06T15:06:24.524760Z","title":"Brain tumor detec- tion using MRI images","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.524760Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:0a4ddbeaa80615102a8cdd0f969aa60c2efd0df20981eebb6bcfd77c1d67d76e","observation_id":"e35a8911-e4eb-4641-aea2-b3bdd47ab346","resolution":{"observed_at":"2026-08-06T15:06:24.524760Z","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":"2026-08-06T15:06:24.528493Z","title":"Head CT - hemorrhage, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.528493Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:3c4cf2de7fe720d876741157382b17b7f2c51732ba325a4dabe30ef5a3f49145","observation_id":"f2175444-14c0-4e86-966b-93ec3ecf6e9a","resolution":{"observed_at":"2026-08-06T15:06:24.528493Z","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":"2026-08-06T15:06:24.532150Z","title":"Online continual learning on class incremental blurry task configuration with anytime inference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.532150Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:aa0de077fba9aa7072a56afc077b3d468484ae726377070d314aae6d478cd424","observation_id":"bf5c8173-1a31-4dcd-8707-b2d6e6d9030b","resolution":{"observed_at":"2026-08-06T15:06:24.532150Z","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":"2026-08-06T15:06:24.536061Z","title":"Miccai multi-atlas la- beling beyond the cranial vault–workshop and challenge","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.536061Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:aa22122e2f4d687ccfd494aa10459f00df8213e88d39d27f5d7217931b4508af","observation_id":"4b0040c4-0510-41e1-a1ac-817a90d11ac7","resolution":{"observed_at":"2026-08-06T15:06:24.536061Z","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":"2026-08-06T15:06:24.539755Z","title":"Continuous memory representation for anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.539755Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:ec633a6e72cb96af9c6cd5fea0ac21cb2255eab50de42625ddd2fd4f714324b3","observation_id":"190094b2-d114-41a2-800e-288ea761bf3f","resolution":{"observed_at":"2026-08-06T15:06:24.539755Z","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":"2026-08-06T15:06:24.543503Z","title":"AD3: Introducing a score for anomaly detec- tion dataset difficulty assessment using VIADUCT dataset","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.543503Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:9cf086fb1bd9e3ba5a88be1176021cdf93867f438c516a20e428590b8cd04d16","observation_id":"70898475-a245-4b49-b58e-bdc4cf289caf","resolution":{"observed_at":"2026-08-06T15:06:24.543503Z","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":"2026-08-06T15:06:24.547200Z","title":"CutPaste: Self-supervised learning for anomaly de- tection and localization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.547200Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:465a052767ebf79c0df9a3f2471c6b27eddfce9bb77574dd59de467ec58382ea","observation_id":"9fcab1f9-b02b-4de5-b1eb-a95979a8a64e","resolution":{"observed_at":"2026-08-06T15:06:24.547200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12665","last_updated":"2024-01-29T10:57:38Z","snapshot_observed_at":"2026-08-09T10:45:27.478125Z","submitted_at":"2024-01-23T11:20:03Z","title":"ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation","version":2},"cited_work":{"arxiv_id":"2401.12665","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.12665","snapshot_observed_at":"2026-08-06T15:06:25.631440Z","title":"ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation","venue":"cs.CV","work_id":"cf3c4e34-ecd5-4c6c-8bca-429bc84479c0","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.550689Z"},"links":{"cited_paper":"/paper/2401.12665","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:06b8e23c313539956f566cb433a793c1b69dd5dfce556fe408309e26ba2823a4","observation_id":"4cd212ae-a602-4c7a-a7c1-022a765caddc","resolution":{"observed_at":"2026-08-06T15:06:25.635748Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:24.554839Z","title":"MuSc: Zero-shot industrial anomaly classification and segmenta- tion with mutual scoring of the unlabeled images","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.554839Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:f4ace93307c4b39662782006f22250bbd4e09f3e48d15abd122c920615c71254","observation_id":"51dc7f09-5250-42cb-8269-a5fecfdd835e","resolution":{"observed_at":"2026-08-06T15:06:24.554839Z","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":"2026-08-06T15:06:24.558392Z","title":"PromptAD: Learning prompts with only normal samples for few-shot anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.558392Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:f66b213183efc8ff01bd06184370c35c9607f9fc7c8d4d9dc3f61c0af3c3c3c0","observation_id":"698df711-218b-48dd-92d6-7028b94e0ead","resolution":{"observed_at":"2026-08-06T15:06:24.558392Z","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":"2026-08-06T15:06:24.562223Z","title":"FADE: Few-shot/zero-shot anomaly detection engine using large vision-language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.562223Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:261eb1459048565964262b54ad7f9827542a5661b688ebe967dad9d1f3845abd","observation_id":"193aeb56-51c2-4abe-b8ce-0b34a102960e","resolution":{"observed_at":"2026-08-06T15:06:24.562223Z","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":"2026-08-06T15:06:24.565803Z","title":"COFT-AD: Contrastive fine-tuning for few-shot anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.565803Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:0e9dc9eae616075579644c1125f2514b06b6ddad8ccc4f192d75e671036c628b","observation_id":"60855bd5-2301-42e5-af0c-b471b8258311","resolution":{"observed_at":"2026-08-06T15:06:24.565803Z","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":"2026-08-06T15:06:24.569585Z","title":"Learning diffusion models for multi-view anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.569585Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:cfec64bc3454bca1676a18271bc93ac59da7e19cb624f7ef51f787a24f12e5b7","observation_id":"40450dee-7bb2-4dff-959c-192d088eca06","resolution":{"observed_at":"2026-08-06T15:06:24.569585Z","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":"2026-08-06T15:06:24.573196Z","title":"Unsupervised continual anomaly detection with contrastively-learned prompt","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.573196Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:65e832db9a8ed11cb215d508c7733993b52e7e5077812326a3bdad05916687b1","observation_id":"56850e83-34e9-49cb-8b86-2f93fb5e5faf","resolution":{"observed_at":"2026-08-06T15:06:24.573196Z","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":"2026-08-06T15:06:24.576650Z","title":"Heterogeneity-aware recurrent neu- ral network for hyperspectral and multispectral image fu- sion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.576650Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:2a88b980e70b13598409f758f191f126bfa3a4720c264864b70f47f627dd0d14","observation_id":"fe7049e8-4ae4-40cf-8e31-b5b510a601da","resolution":{"observed_at":"2026-08-06T15:06:24.576650Z","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":"2026-08-06T15:06:24.580781Z","title":"Hierarchical vector quantized transformer for multi-class unsupervised anomaly detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.580781Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:d17f809934fc82cc5bec68dae53d72903e1df37db924b37ae4ccf77aa9522503","observation_id":"88126336-5d9f-4af2-bd06-a5e2c73f36ef","resolution":{"observed_at":"2026-08-06T15:06:24.580781Z","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":"2026-08-06T15:06:24.585045Z","title":"Review of wafer surface defect detection methods","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.585045Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:fe6c66a0adcb0d860402f9585201cce8e131fb8053a338b6f307c4b4685742f9","observation_id":"638e5ed3-4e73-4cf2-ab0c-4bf618da64d6","resolution":{"observed_at":"2026-08-06T15:06:24.585045Z","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":"2026-08-06T15:06:24.588857Z","title":"Anomaly de- tection through latent space restoration using vector quan- tized variational autoencoders","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.588857Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:cd19ad782152ccbd6e9d09432d19ec63b3e2ed072bcaa05d7c8b5f3888284274","observation_id":"2bdf8618-188a-4768-8b48-a58766695824","resolution":{"observed_at":"2026-08-06T15:06:24.588857Z","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":"2026-08-06T15:06:24.592646Z","title":"Mixture of ex- perts: a literature survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.592646Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:366b986ed4f30a1f47e47710f1768365c7d1d2113726c188b478f0b0db078373","observation_id":"373891c2-88b9-476d-8a91-be5db03598c3","resolution":{"observed_at":"2026-08-06T15:06:24.592646Z","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":"2026-08-06T15:06:24.596489Z","title":"Unsu- pervised, online and on-the-fly anomaly detection for non- stationary image distributions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.596489Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:cb4496e89a0d9ba33e7dea122e8284aedcd132e801b9a70da6250a673ea4e3ee","observation_id":"4a2b1682-28fa-4b22-a64e-8169aff7e476","resolution":{"observed_at":"2026-08-06T15:06:24.596489Z","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":"2026-08-06T15:06:24.599962Z","title":"MoEAD: A parameter- efficient model for multi-class anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.599962Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:7b633d2c6601154d21a99f5bb63aae418e480f8eba6e91605ffb31c764066c84","observation_id":"d748cb8e-9d20-4514-99b6-844d3cab02b7","resolution":{"observed_at":"2026-08-06T15:06:24.599962Z","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":"2026-08-06T15:06:24.603470Z","title":"RGI: Robust GAN- inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.603470Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:a0fbf8b7b13b272aa2516227138d75863453a5114196fb292aafca3c0be4210c","observation_id":"6a5e2b89-15f5-477e-9c31-478c1dc2c601","resolution":{"observed_at":"2026-08-06T15:06:24.603470Z","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":"2026-08-06T15:06:24.607132Z","title":"ChatGPT, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.607132Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:39ba351ac8ab8f3dad5a36efc4c0f1557ccdc0000252a1d5f4ed9037e00e39af","observation_id":"a9737e6d-38bf-4bf7-873d-fb3f7926d7fc","resolution":{"observed_at":"2026-08-06T15:06:24.607132Z","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":"2026-08-06T15:06:24.610853Z","title":"Deep learning for anomaly detection: A review","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.610853Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:6dde091173b225b92f11b04c8f644f4d62019190a9919cc2e16f4f53cbf42871","observation_id":"464cd2ed-d535-4fda-b5b7-4002c7d16df0","resolution":{"observed_at":"2026-08-06T15:06:24.610853Z","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":"2026-08-06T15:06:24.614559Z","title":"Revisiting deep feature reconstruction for logical and structural industrial anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.614559Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:d9e73eb81ee9593975bb52abee13b132243a797b1b8fe061f24856c21ae9cc4a","observation_id":"5f735a8b-1922-4eb7-bd6f-fec1987d3dcd","resolution":{"observed_at":"2026-08-06T15:06:24.614559Z","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":"2026-08-06T15:06:24.618357Z","title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly seg- mentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.618357Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:cff8a24c120aca2f5ccaec08220789c361a1331b81339adca949f5287550fb7f","observation_id":"afde420c-4e41-409d-a5c0-0c7c9dc10093","resolution":{"observed_at":"2026-08-06T15:06:24.618357Z","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":"2026-08-06T15:06:24.621825Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.621825Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:866786614a56c277e8df4fbc90c8d2f3e1548a0162216e8bf6bae64bd6edc313","observation_id":"f6080dc1-9aea-4642-a309-461fa745f657","resolution":{"observed_at":"2026-08-06T15:06:24.621825Z","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":"2026-08-06T15:06:24.625581Z","title":"DELTA: Decoupling long-tailed online continual learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.625581Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:edb8d73b6e7b77a12eaf58f17d583a8e273750acfeb5869fd40c03b936b6799b","observation_id":"cfb28705-0a58-4b08-a2f5-1827708d6023","resolution":{"observed_at":"2026-08-06T15:06:24.625581Z","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":"2026-08-06T15:06:24.629473Z","title":"Variational infer- ence with normalizing flows","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.629473Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:11e4adb9a4357fbe99572e94546f598f5ad6faad6a52d578c051464917d71d0a","observation_id":"94c3faad-2152-4b83-82fa-d7445fd434cf","resolution":{"observed_at":"2026-08-06T15:06:24.629473Z","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":"2026-08-06T15:06:24.633385Z","title":"Scaling vision with sparse mix- ture of experts","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.633385Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:c7d43a9bfc2e0c48a56be7f892ff3bd9bad2acb8184c21900391e67095c85014","observation_id":"6089365d-f7e4-4ddd-8d60-20c601852cc5","resolution":{"observed_at":"2026-08-06T15:06:24.633385Z","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":"2026-08-06T15:06:24.636974Z","title":"Towards to- tal recall in industrial anomaly detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.636974Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:9f6b232c486cfe5a0daba3e06092a91ac7f52d69ac09b51e170070711c09f2e9","observation_id":"8904cecb-f9a9-48f0-b310-39c8e69cc7f9","resolution":{"observed_at":"2026-08-06T15:06:24.636974Z","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":"2026-08-06T15:06:24.641981Z","title":"Same same but differnet: Semi-supervised defect detection with normalizing flows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.641981Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:5c5828f70815e0399f73dd9d3b2aeba0e813452aaa11c4e876c5c3adc8df5cbf","observation_id":"eb5270cd-5d2a-4998-a3b4-0a4b9cd2fd9d","resolution":{"observed_at":"2026-08-06T15:06:24.641981Z","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":"2026-08-06T15:06:24.646009Z","title":"Tire defect detection model using ma- chine learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.646009Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:a3efcadaa5e17f7b4f24bf4884fb13e4c43ef9ad2bf0ba7f45fca54d7e111c0a","observation_id":"63c0a64f-c579-4130-b744-e51efc48dfd4","resolution":{"observed_at":"2026-08-06T15:06:24.646009Z","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":"2026-08-06T15:06:24.649967Z","title":"Multiresolution knowledge distillation for anomaly detection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.649967Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:b3b724d5a1806d8a21b2da6678e82a26625bf3694be7d6156e8ba1948cb2d8ad","observation_id":"12692ee8-cee4-48b2-bf9b-97f7bc7a8535","resolution":{"observed_at":"2026-08-06T15:06:24.649967Z","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":"2026-08-06T15:06:24.653565Z","title":"Dissolving is amplifying: Towards fine-grained anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.653565Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:7d9a979ba334b35fcfdcd1e94a210a91ad93c59dc7d9afb6a97d3f5d57763e71","observation_id":"6b0c17c8-9f19-49d3-9605-7fb9d2d53612","resolution":{"observed_at":"2026-08-06T15:06:24.653565Z","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":"2026-08-06T15:06:24.657036Z","title":"GeneralAD: Anomaly detection across domains by attending to distorted features","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.657036Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:1da8a905c2ebcab264ce90fbafd7b8b595acc19142a3e0fb587a7b2439b2c897","observation_id":"f2522519-ba90-4a90-9bbd-ac6671079c98","resolution":{"observed_at":"2026-08-06T15:06:24.657036Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.522706Z","title":"EfficientNet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":"b19ccfac-4a46-4d7f-b929-7009d1d378ec","year":2019},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.660464Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:ad7306a30845637beb9a078e67f6c5a2115a7019fb851712458d11c0cdc67ff5","observation_id":"189ce715-bd63-4e2a-b807-cd8164e1e6d9","resolution":{"observed_at":"2026-08-06T15:06:26.526721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.510184Z","title":"An incremental unified framework for small defect inspection","venue":null,"work_id":"38be8a3a-56b0-4278-a719-0388e1d8656a","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.664065Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:aeeffd58a04e0116a9d4d88d030e072bfe4c6af742f0bcdfbd91bc78878d8b36","observation_id":"e819af4c-df5a-4ca4-a775-f78c9b635757","resolution":{"observed_at":"2026-08-06T15:06:26.513965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.497508Z","title":"Revisiting reverse distillation for anomaly detection","venue":null,"work_id":"14540eac-4ca5-4da8-b075-ba36272e0e82","year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.667749Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:564325bada411b2c3f05ce43e2da4d30c66384a1fd617ab8f9dae494150b8d11","observation_id":"2bdcb882-d38a-464b-b3d9-75c6cb922543","resolution":{"observed_at":"2026-08-06T15:06:26.501823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-06T15:06:24.671346Z","title":"LLaMA: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.671346Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:6d205a4cbfc09999aec9fe4e10796e6e78672563f61f10f8f69f22e12c9541e0","observation_id":"bed54cc2-5684-4b32-a7ef-9a9cb5685342","resolution":{"observed_at":"2026-08-06T15:06:24.671346Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.485402Z","title":"Neural discrete representation learning","venue":null,"work_id":"c429de3f-8d1b-4598-9561-795dfde5af6b","year":2017},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.675497Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:3bae482de1379abafef442ab3d577ba70a97edec5898534f0e57b8413f489557","observation_id":"811b869b-d90b-4ae0-993c-ee82341552ea","resolution":{"observed_at":"2026-08-06T15:06:26.489366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.473354Z","title":"A comprehensive survey of continual learning: theory, method and application","venue":null,"work_id":"bdf5fcbb-5b5d-4793-bb11-9cd5519edaf4","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.679442Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:0dff40c71468019a288bb9eb53424857684b4f6707998be8c966dc7b2a2e5297","observation_id":"e9ce8263-a7af-412a-8c49-c28f0b45b219","resolution":{"observed_at":"2026-08-06T15:06:26.477211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.461640Z","title":"Few-shot online anomaly detection and segmentation","venue":null,"work_id":"d23d08d5-096e-4391-926b-bb934b17dc68","year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.683179Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:915da9ed6889bfcb242570acb71ad6c438fe64ed6eb204120943f0cb0fad5aa3","observation_id":"63b25924-bbfe-4f5f-8394-97ba11b82302","resolution":{"observed_at":"2026-08-06T15:06:26.465306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.449598Z","title":"Weakly supervised learning for industrial optical inspection","venue":null,"work_id":"827035e3-3829-406f-975f-08790a11a500","year":2007},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.686992Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:853e7dc47d1b1518a42f6682b0f2a4abce8d6f758d570bce6c01005fe8dea542","observation_id":"387660d0-de35-400e-9294-1be207535855","resolution":{"observed_at":"2026-08-06T15:06:26.453472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.437475Z","title":"Defect spectrum: A granular look of large-scale defect datasets with rich seman- tics","venue":null,"work_id":"61dd3d9e-62ec-4fd7-a009-0b64febadfd3","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.690809Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:87298dba645ccd12b7f4a410c3c9a59c35f8c9bf8f397b73033d9c866c608d7c","observation_id":"46641ebb-fe93-4154-aa2b-6473ba5b20fb","resolution":{"observed_at":"2026-08-06T15:06:26.441392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.425366Z","title":"GLAD: Towards better reconstruction with global and local adaptive diffu- sion models for unsupervised anomaly detection","venue":null,"work_id":"e99a9558-6471-466f-a8da-5a211631b133","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.694848Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:70af34f7a78a9497991d893d6107cd6fbc3806dcfd2dddd3cd4165db10416190","observation_id":"e312f0fc-6f39-4cb2-88f1-37c271146609","resolution":{"observed_at":"2026-08-06T15:06:26.429362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.412810Z","title":"Hierarchical gaussian mixture normal- izing flow modeling for unified anomaly detection","venue":null,"work_id":"92125e6b-5e17-42ac-a39e-af24b26330f7","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.698371Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:2d74bbdb4d10a48d2dae05161ef482d7b48fa611d501ea50499fc007c56c88d2","observation_id":"1c3d783f-68a1-4360-8be6-27942f5cfa21","resolution":{"observed_at":"2026-08-06T15:06:26.416664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.400578Z","title":"A unified model for multi-class anomaly detection","venue":null,"work_id":"1ff52bf7-cf5f-41ae-a242-bb77f6bb084c","year":2022},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.702520Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:64e7b2f05e55f59d274041ba077f6c943a1def94789f93cd0aed5837bf14e2d0","observation_id":"703c86b2-e0be-4eae-8bbb-a732184f2cca","resolution":{"observed_at":"2026-08-06T15:06:26.404415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07677","last_updated":"2021-11-16T06:33:39Z","snapshot_observed_at":"2026-07-06T12:08:32.226011Z","submitted_at":"2021-11-15T11:15:02Z","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07677","snapshot_observed_at":"2026-08-06T15:06:24.706782Z","title":"FastFlow: Unsupervised anomaly detection and localization via 2D normalizing flows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.706782Z"},"links":{"cited_paper":"/paper/2111.07677","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:d6d7207d01b1657e67343c17a919d60d6c51dad8785eb96bb6b93e56119374cb","observation_id":"061896e5-9e47-4e27-89b5-f950a7bb6271","resolution":{"observed_at":"2026-08-06T15:06:24.706782Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.387599Z","title":"DRAEM-a discriminatively trained reconstruction embed- ding for surface anomaly detection","venue":null,"work_id":"aa98f126-45df-4e23-aa53-92b200674655","year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.710922Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:11d38293daa288cf6b22c87edbd155f035446b9b91b4aac67203801208e22105","observation_id":"6f0d3926-16bd-455f-9885-cfe50a27a3bb","resolution":{"observed_at":"2026-08-06T15:06:26.392444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00483","last_updated":"2024-08-01T11:39:45Z","snapshot_observed_at":"2026-07-06T18:55:32.910650Z","submitted_at":"2024-08-01T11:39:45Z","title":"A Systematic Review on Long-Tailed Learning","version":1},"cited_work":{"arxiv_id":"2408.00483","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.00483","snapshot_observed_at":"2026-08-06T15:06:25.585263Z","title":"A Systematic Review on Long-Tailed Learning","venue":"cs.LG","work_id":"9ceec99b-1e58-42b5-9e8c-6e769aa2d343","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.714627Z"},"links":{"cited_paper":"/paper/2408.00483","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:3c98a6096c1ef490d7be17bcc451a72e4a039dd7fa5f783167fd9855ef33008d","observation_id":"4e9f144e-9b86-4abb-944c-756f8b44e15e","resolution":{"observed_at":"2026-08-06T15:06:25.589547Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.375070Z","title":"Defect-GAN: High-fidelity defect synthesis for automated defect inspection","venue":null,"work_id":"d647a749-ae20-4daa-a32f-9399e15e9d5d","year":2021},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.718635Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:d1101b8227ac31b32c9c249add8000b44003c9ce4b087308e1fa87bfbf333609","observation_id":"3dac0a2e-8d31-41ba-a71f-d72372582570","resolution":{"observed_at":"2026-08-06T15:06:26.379292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.02612","last_updated":"2024-04-16T11:35:37Z","snapshot_observed_at":"2026-07-06T16:43:13.809278Z","submitted_at":"2023-11-05T10:01:18Z","title":"GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.02612","snapshot_observed_at":"2026-08-06T15:06:24.722351Z","title":"Exploring grounding poten- tial of VQA-oriented GPT-4V for zero-shot anomaly detec- tion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.722351Z"},"links":{"cited_paper":"/paper/2311.02612","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:74e12661d192b2b58339321795726e1c3c5b76f5c0abdca5a89d199478e1b23e","observation_id":"a4eb71bd-a62d-4ee2-b4c5-b66959740f73","resolution":{"observed_at":"2026-08-06T15:06:24.722351Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.362656Z","title":"Exploring plain ViT reconstruction for multi- class unsupervised anomaly detection","venue":null,"work_id":"1657cda0-922e-4f81-b89f-ce035e078a0a","year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.726117Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:22fe8daafafa2c175a3b038c1dc6a474eb60011aaf5b4b8f086a61be9e32e391","observation_id":"4a689aea-0531-400c-9e58-ac0bfbec23b2","resolution":{"observed_at":"2026-08-06T15:06:26.366583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"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":"2026-08-06T15:06:24.729744Z","title":"ADer: A comprehensive benchmark for multi-class visual anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.729744Z"},"links":{"cited_paper":"/paper/2406.03262","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:a7e4a38658e9b74032104fd03893e9e79b27e0dd66c037c43b126f5f610b4522","observation_id":"b45fcf4b-96d8-45ff-aeb4-f6812680cb62","resolution":{"observed_at":"2026-08-06T15:06:24.729744Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.350443Z","title":"DeSTSeg: Segmentation guided denois- ing student-teacher for anomaly detection","venue":null,"work_id":"2646a9bd-5f44-43fe-95f7-45d8ed195328","year":null},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.733439Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:7ef878dcdbd4595e0a34816fa0c56d694a2a4e01f5a75ce865b5040fa1ab235d","observation_id":"efbe44d8-c251-4902-b2c0-be0848f55ff9","resolution":{"observed_at":"2026-08-06T15:06:26.354201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10802","last_updated":"2023-07-20T12:10:29Z","snapshot_observed_at":"2026-08-09T15:42:33.894056Z","submitted_at":"2023-07-20T12:10:29Z","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10802","snapshot_observed_at":"2026-08-06T15:06:24.737211Z","title":"Meta- Transformer: A unified framework for multimodal learn- ing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.737211Z"},"links":{"cited_paper":"/paper/2307.10802","citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:5a24966ed258ac1075a931bf3508890cf28b2714d62a3f5f5b34e9d830af3d32","observation_id":"a81cb44e-c014-4261-ba5b-b64825c1889b","resolution":{"observed_at":"2026-08-06T15:06:24.737211Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.338290Z","title":"OmniAL: A unified cnn framework for unsu- pervised anomaly localization","venue":null,"work_id":"84ce13c9-04b0-4b88-a547-0f448a0a2139","year":2023},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.740958Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:494cf1d33813410d0460c07df63b697d762b87da296284bb8e0b6fdc61311477","observation_id":"1f8eba74-3889-4dc3-8fde-eda6fc48f0c3","resolution":{"observed_at":"2026-08-06T15:06:26.342179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:06:26.325548Z","title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","venue":null,"work_id":"00e2e893-52ed-4197-8edf-865741ae0cac","year":2024},"citing_paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-06T15:06:24.744696Z"},"links":{"citing_paper":"/paper/2507.16946"},"observation_digest":"sha256:01ee49c95881829bc01e56072f7cb3b168b882508e51bed511f120dd748812e7","observation_id":"da5e308c-ffc4-48de-98ab-0d3bf8da8314","resolution":{"observed_at":"2026-08-06T15:06:26.330123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.16946","last_updated":"2025-07-22T18:35:50Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T12:05:57.381919Z","submitted_at":"2025-07-22T18:35:50Z","title":"Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":78,"verified_exact":5,"verified_fuzzy":17},"total_outbound_references":149},"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 100 of 149 outbound references and 0 inbound Pith citation observations for arXiv:2507.16946."}