{"as_of":"2026-08-08T12:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:74178b8ce4f5872076bd865e0447542299beb4a610dfaef747de4bf0ce760629","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T13:07:09.539291Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2605.28428/citation-record","integrity":"/paper/2605.28428/integrity","json":"/paper/2605.28428/citation-record.json","paper":"/paper/2605.28428"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T13:07:09.539291Z","title":"Graph based anomaly detection and description: a survey.Data mining and knowledge discovery, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:299f18f10e48a3218823376247693db6e3e6178344e1925393f32e410fba6d06","observation_id":"1aea8058-6720-4dd9-8c50-b16f9d9598c6","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Pni: industrial anomaly detection using position and neighborhood infor- mation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:a80a5fda973977ee964a0fccf2e3a584e9da5f0cdfc41adf52e5c4b9d5b62ee1","observation_id":"d477c3e7-0df1-44f5-aa4d-d93c4e835987","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Man- ifold regularization: A geometric framework for learning from labeled and unlabeled examples.Journal of machine learning research, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:27889668d19f099f56775af881e0012984a1333ae22199367113f08b2b26fc45","observation_id":"8a9cc63c-ff40-4b76-834f-f3c2073ea038","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:b69e8c101dc8103d0ea5bf0939ee45a17bf75e89d7dfbe111dce8502ca422efc","observation_id":"4d64a8ec-bc83-4502-847e-909983e196e6","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-07-06T09:17:53.298286Z","submitted_at":"2020-05-05T17:43:35Z","title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","version":3},"cited_work":{"arxiv_id":"2005.02357","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.02357","snapshot_observed_at":"2026-07-04T19:40:06.738342Z","title":"arXiv preprint arXiv:2005.02357 , year=","venue":null,"work_id":"46f059fe-3ba7-4f4f-9103-1e90c9a6f472","year":2005},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"cited_paper":"/paper/2005.02357","citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:c0c9d008cf77c162825ce3272ae4f091dc531c312744669b2b06d60549a3ef94","observation_id":"1a4e88c2-8689-466c-a0a4-d454444686c9","resolution":{"observed_at":"2026-06-29T13:13:27.454389Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-06-29T13:07:09.539291Z","title":"Vision transformers need registers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:48137da72cd03b109dc5074ab3ec29434f02623c3dddfdbc624f5df62078ed1c","observation_id":"e4f54506-f9f9-494b-b9c1-0d71b2e27a53","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Padim: a patch distribution modeling framework for anomaly detection and localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:5d054c968424ced3e65f641cf89118407e15733f01529dccea007855816aedbf","observation_id":"56c9fa7c-f19d-450d-9232-78d6575a16fa","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Deep anomaly detection on attributed networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:04f660a87d03f40ae1d6bc6f400ac3487d7362ea971dc5c56060e910932ee3ac","observation_id":"20c52ad8-84d0-4d60-8c45-53ba46298d84","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":"2010.11929","doi":"10.1175/jcli-d-22-0357.1","metadata_source":"pith","pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","venue":"cs.CV","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","year":2020},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:4a16304bf8561b0bd676ebaf33a183c3e8bb3f2079111c4bd74ab6c5e196f24d","observation_id":"db03bea2-7963-409d-a0b1-627aebf9824f","resolution":{"observed_at":"2026-06-29T13:13:27.457033Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-06-29T13:07:09.539291Z","title":"Graph random neural networks for semi-supervised learning on graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:27d9d6bcba4a0ae095eff30bb9c6c0568158b20a52a22a8927766d4afa63d8fc","observation_id":"652731c1-bfd2-4b49-aa30-b663882fadf5","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Registration based few-shot anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:00ef03fc23bc3e336b2aa75ec13e87185f3ab694615b1f4ebf2bd4eedb699795","observation_id":"4d648e7a-ed8f-46c3-bf4c-f4c12ff33592","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Winclip: Zero- /few-shot anomaly classification and segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:ab0f775e001a150ff3d7379dfc12aa6b42c91a4b5e5bc788eea5fb92c6c7376c","observation_id":"4056df33-a01d-4a2a-8754-9b6a6acf8d94","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Identifying medical diagnoses and treatable diseases by image-based deep learning.cell, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:0a25c44fa2c7e91310d095dc93c6cb52ffa40fbfd4260c482ed0f93a94e9557b","observation_id":"945c77f0-a17e-48a2-a476-7a3efa5c953a","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Graph anomaly detection with graph neural networks: Current status and challenges.IEEe Access, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:e2b2a9120c50c4779a2a35ceb6cf3d3f006f7b0626480a9fb135bb9207d4cd86","observation_id":"4c243d60-04b7-4011-9eb3-3ef8e2043996","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Semi-supervised classification with graph convo- lutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:936430db68bf111a835bfaa6d7f3dd620ef475aac9e3029b2c621d719b411f13","observation_id":"efc18cee-5566-40ba-ac50-d63f8de36b8b","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Continuous memory representation for anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:4ea5f9f69f5f879a69f99919a4196eed2314c0485ad6367c02190fea373f662e","observation_id":"774cdbab-2e94-4702-ac69-719080cb4de8","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Deeper insights into graph convolutional networks for semi-supervised learn- ing","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:e63b5caba985d2992029fd62166f9c18136c6c3121c8528a0adc28b4b93aa60c","observation_id":"436bfc71-a0f0-499c-9b38-0dae723c2233","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Promptad: Learn- ing prompts with only normal samples for few-shot anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:e3ba92e625e572fc8a5034a584054b5604da69e67ccb8205c1198cc78b41f95c","observation_id":"2a28af20-73c7-4910-a025-f6fcfcee8409","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Exploring intrinsic normal prototypes within a single image for universal anomaly detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:44a1496a258dfe2348d76ef0322051075238d83032c498a042ed79c1fa809a96","observation_id":"9aba8abf-5611-40d1-a921-fbed4f2fda9b","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Deep generative model us- ing unregularized score for anomaly detection with hetero- geneous complexity.IEEETCYB","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:03686b1f372138d8368f40a48ebe8aaf17210ac039074ff726c49766b0caf83e","observation_id":"02384ddf-b6a0-44a5-8dc5-3fb60431a883","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"k-nnn: nearest neighbors of neighbors for anomaly detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:ca3a0463623526ff2d48980da7ad64e161b02c44996d49fd8c1a59f25dc603dc","observation_id":"22fa7718-ef24-4440-bbaa-a4ab584a11b1","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Anomalous: A joint modeling approach for anomaly detection on attributed networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:20f399689b99240b7674d81d5eea6e75605b70ac059ce41f24c5e7a3ab786a01","observation_id":"a5bbf4e5-f9be-4c24-92ac-7b2f73d29a04","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:2265c1a99dbd805a29d0ab0d26f502842e8e1af52e6047e6aae80a77939522d8","observation_id":"89d3399b-25d6-44d6-9ab8-37288bdeeed3","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Towards total recall in industrial anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:3aa695c0b5fc0e0bff710b67f7f16374415ba455e9536941e11e589309f4d06d","observation_id":"55c57d17-4347-4139-b5fd-4a72e500d1df","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10104","last_updated":"2025-08-13T18:00:55Z","snapshot_observed_at":"2026-07-06T22:12:35.584339Z","submitted_at":"2025-08-13T18:00:55Z","title":"DINOv3","version":1},"cited_work":{"arxiv_id":"2508.10104","doi":"10.1055/a-2487-1252","metadata_source":"pith","pith_arxiv_id":"2508.10104","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DINOv3","venue":"cs.CV","work_id":"c8b07deb-8fe7-4e18-9620-f3569d3529ce","year":2025},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"cited_paper":"/paper/2508.10104","citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:e1507bba4258490a54252d00009a70ec606ce620196028ae18dcf1e7da1cf7b3","observation_id":"1405c41b-5a2b-456a-b6a1-6409a78ee581","resolution":{"observed_at":"2026-06-29T13:13:27.462524Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-06-29T13:07:09.539291Z","title":"Rethink- ing graph neural networks for anomaly detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:484fac62d26fda62d4ef921f8b94d8ed353a8244d67def11878a5c193b1c6439","observation_id":"ec4e29fa-1b0a-4f70-851d-17880523c616","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Kernel-aware graph prompt learning for few-shot anomaly detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:7124fe8e35b0095fa8a885290bd2d9a93273ee50adf6431d428666fe93f194bf","observation_id":"80491375-e3ad-4b84-a460-f8ef1903458e","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Graph laplacian for image anomaly detection.Machine Vision and Applications,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:4b800343e40d4d474ce8ff6201ec657e2881f2039352fd5ba844abeb0fa37bcb","observation_id":"cdd15927-197f-4731-9ddf-6696bc11d619","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Real-iad: A real-world multi-view dataset for benchmarking versatile industrial anomaly detec- tion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:0d10a24a1556a533078798c08ca5846067fb227e3a674dcc979c1973a14d6010","observation_id":"1c8d2b94-08af-4b98-87ed-e77ba6d051f3","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Pushing the limits of fewshot anomaly detec- tion in industry vision: Graphcore","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:560c557eb5943532a1b62eb82e843b54c6504a6ea0ebdd168eec1fa299e4cdd9","observation_id":"e544423a-2188-469c-9ccb-7edb70b3fbec","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2509.14084","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T13:13:27.458180Z","title":"Ad-dinov3: Enhancing dinov3 for zero-shot anomaly detection with anomaly-aware calibration.arXiv preprint arXiv:2509.14084, 2025","venue":null,"work_id":"63beb4f1-e463-432f-80a7-71e3850ad1fd","year":2025},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:d90e775601a5f490e5a8a78f247aaba21814f7cd8c495ad543429c63deb20982","observation_id":"0ac88359-95af-4118-b9e1-067c9d40a7d5","resolution":{"observed_at":"2026-06-29T13:13:27.459893Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-06-29T13:07:09.539291Z","title":"Wide residual net- works","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:a451d28b1f8d761c755850cc9869b9c82817249ff7b1f7d3ca5f526db2164b05","observation_id":"cd23cb7e-18ce-4db0-b082-46f4bb717033","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Error-bounded graph anomaly loss for gnns","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:3b4a1f715ca135cbefbaeefc28ced69b8b362c48e9ca1dcf2ef3d751d7a1ce1d","observation_id":"11f9f4a6-60a1-48eb-a69f-66d7d0a89a5f","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Graph neural networks: A review of methods and applications.AI open, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:f54e4204a3ade542f7f47ef60d7506aebda5bf19940d41f020b88a6a1dc93eed","observation_id":"ebb7bc7b-ae2e-4058-8ead-57663d8fcc94","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Toward generalist anomaly detection via in-context residual learning with few-shot sam- ple prompts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:f3cb5797acf8208072fac297764a20240685e9bd2d0e00ea2cdc19e86f657895","observation_id":"f6408d0e-4fc0-4609-b3f0-039e418f9521","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:844e5710e61117d83d3833b54be77ed8edbb5b4a4fd2b6e2ffd76da97d37a18d","observation_id":"c3e7fdf1-ee30-42d9-92d0-a0a13549a10e","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"Spot-the-difference self-supervised pre- training for anomaly detection and segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:acef5a07a4fd74976069269badb641587651b21d75aff28a58f2b44db1387697","observation_id":"bc6ed3ca-251f-43f7-816a-4aac0934b4a1","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","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":"2026-06-29T13:07:09.539291Z","title":"11 S2.Ablation on the query feature stabilization coeffi- cientΛ q","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-29T13:07:09.539291Z"},"links":{"citing_paper":"/paper/2605.28428"},"observation_digest":"sha256:5a1bc10ccc0aa7dfec350badeb003398b6b6f9babce5e689b49caec3ca941985","observation_id":"161e551c-d75f-4840-b473-63bc363e79dc","resolution":{"observed_at":"2026-06-29T13:07:09.539291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.28428","last_updated":"2026-05-27T12:58:56Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-01T15:19:39.591589Z","submitted_at":"2026-05-27T12:58:56Z","title":"Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":34,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":38},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2605.28428."}