{"as_of":"2026-08-14T03:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6fcf90f1ca5d7d406b1b6c16470f6ead131059213c407c82b21c694822d2aceb","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:22:39.318312Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2412.00560/citation-record","integrity":"/paper/2412.00560/integrity","json":"/paper/2412.00560/citation-record.json","paper":"/paper/2412.00560"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:22:39.131968Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.131968Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:733d5984d58455eeaf8e8f119124b748e19da10ce68f54f4081c548004278007","observation_id":"abbf8788-2068-4d85-ae2e-d6ec9fbe57a7","resolution":{"observed_at":"2026-08-12T05:22:39.131968Z","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":"2026-08-12T05:22:40.075830Z","title":null,"venue":null,"work_id":"c31219a8-078b-4841-ba27-1e1cfe09acf6","year":2020},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.138362Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:4371389ac9e60cf496c6bfd45a5adad6f2110140b0e12c2c435709c30a44ca02","observation_id":"7f822a05-5b43-428d-8bc3-62133da77f11","resolution":{"observed_at":"2026-08-12T05:22:40.080225Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:40.061238Z","title":null,"venue":null,"work_id":"654f3a86-3da2-4313-82ab-dc6ff460da99","year":2006},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.143563Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:3f4de71167ea08014cb695d5e12b362d4aee6380ebf90f4a70d8b87c266f6f6a","observation_id":"fcc0e3cc-66e0-4098-bfb1-8cbc8b2e45d3","resolution":{"observed_at":"2026-08-12T05:22:40.065948Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09359","last_updated":"2024-07-12T15:33:37Z","snapshot_observed_at":"2026-08-12T23:23:19.507551Z","submitted_at":"2024-07-12T15:33:37Z","title":"A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09359","snapshot_observed_at":"2026-08-12T05:22:39.149508Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.149508Z"},"links":{"cited_paper":"/paper/2407.09359","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:71e024d712f0db759df8a69f68fe9422922ab932b30457bae84f7d13b6e00eeb","observation_id":"e58aa9d1-dbbd-4238-945f-379f9033d73b","resolution":{"observed_at":"2026-08-12T05:22:39.149508Z","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":"2026-08-12T05:22:40.046980Z","title":null,"venue":null,"work_id":"d724a0d1-be20-4246-a8e6-b6d9f1db84b9","year":2021},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.155962Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:b28baebf7a69b581d8153d8d42ab8e26b082edd755710f18e44ca2c6975e9c6e","observation_id":"58b2b7e6-8683-431b-8266-d32476f7b849","resolution":{"observed_at":"2026-08-12T05:22:40.051756Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:40.032265Z","title":null,"venue":null,"work_id":"65485b1b-8341-4aef-828b-dcb20cf7b4c5","year":2022},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.161044Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:7fda9810d20b17b2e715944ce11083a1b05dc5923564fc1b6077bafa82513e06","observation_id":"1285062f-998b-4af9-a85e-8c1556c82efb","resolution":{"observed_at":"2026-08-12T05:22:40.036740Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:40.017690Z","title":null,"venue":null,"work_id":"8fbfe2a7-40fa-43c6-98c0-ddd8406b8413","year":2024},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.167117Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:e07500be6dac5ca5ac4a029b0db843e3b9c000cf6c5558bff79134b650fa17be","observation_id":"47888532-b009-4c04-8c8e-5e584a9adc98","resolution":{"observed_at":"2026-08-12T05:22:40.022379Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.171805Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.171805Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:ce4ef6cba8b6ec55f0f377276d5d598de3aa58f882595acab7826847075e32dc","observation_id":"3d6980a2-91f3-4ce4-9075-187e0101808c","resolution":{"observed_at":"2026-08-12T05:22:39.171805Z","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":"2026-08-12T05:22:39.993079Z","title":null,"venue":null,"work_id":"7463b0e3-decc-42ea-ac8e-a2381a207a4f","year":2014},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.176790Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:0380f5963151a5a62e80711fd91a34e9e0dba0be532c2b4c3a1774b32b802a84","observation_id":"10b5a6d9-11de-466e-8ae5-8791cd4116ae","resolution":{"observed_at":"2026-08-12T05:22:39.997985Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.12571","last_updated":"2021-07-27T03:10:38Z","snapshot_observed_at":"2026-08-11T16:14:31.801084Z","submitted_at":"2021-07-27T03:10:38Z","title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.12571","snapshot_observed_at":"2026-08-12T05:22:39.181420Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.181420Z"},"links":{"cited_paper":"/paper/2107.12571","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:6f3ad87d957fcaa016b5ac66dacf61378cc055af4d15268340cdc5f6a53bb9f0","observation_id":"935ec20a-6d13-4ecd-9450-e2f0485f5c3e","resolution":{"observed_at":"2026-08-12T05:22:39.181420Z","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":"2026-08-12T05:22:39.186660Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.186660Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:67c33a1f19b07f78504dd8ef133727e6384178fdb6a751ab7bac241e9ea2c8d0","observation_id":"d0bb4103-4118-4219-a58e-8d7851ad4904","resolution":{"observed_at":"2026-08-12T05:22:39.186660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.06607","last_updated":"2023-12-11T18:38:28Z","snapshot_observed_at":"2026-08-13T05:04:52.138777Z","submitted_at":"2023-12-11T18:38:28Z","title":"DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.06607","snapshot_observed_at":"2026-08-12T05:22:39.191699Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.191699Z"},"links":{"cited_paper":"/paper/2312.06607","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:618cc904d5a0a70faa943b1180ae3367b310216a2e0b45574632996727c25308","observation_id":"2f758fd5-bdc7-4aa9-850d-da93cb91b4f6","resolution":{"observed_at":"2026-08-12T05:22:39.191699Z","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":"2026-08-12T05:22:39.197798Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.197798Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:bb3173fd1636648233261532a9dd6d8977abb0ed17ae4433b9a3d43732728a92","observation_id":"281ad357-4f88-42a1-acf7-685d66992f2c","resolution":{"observed_at":"2026-08-12T05:22:39.197798Z","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":"2026-08-12T05:22:39.965674Z","title":null,"venue":null,"work_id":"f53ac7af-d637-42f4-8ba2-7f8d6e4526e7","year":2024},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.202904Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:22fcb54b1ef8bdcf6125e2348b97efae1f31b87c35c85d1f706b64eb2aeae96e","observation_id":"ea8c7369-1f9e-47b9-b4ba-ac52c8df4767","resolution":{"observed_at":"2026-08-12T05:22:39.971679Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02595","last_updated":"2023-03-05T07:37:28Z","snapshot_observed_at":"2026-08-14T01:09:54.187105Z","submitted_at":"2023-03-05T07:37:28Z","title":"PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow","version":1},"cited_work":{"arxiv_id":"2303.02595","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.02595","snapshot_observed_at":"2026-08-12T05:22:39.636207Z","title":"PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow","venue":"cs.CV","work_id":"2df48be5-3e9b-4120-8b31-769362386857","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.207432Z"},"links":{"cited_paper":"/paper/2303.02595","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:81f0a796644eb2050ee5bd53f708038deba27601c5a1950152b875636cade170","observation_id":"3d6b1ea2-1862-4015-aeb4-368c563e0d6a","resolution":{"observed_at":"2026-08-12T05:22:39.641373Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.950215Z","title":null,"venue":null,"work_id":"6c8505d7-2659-43da-983b-7ff18a300037","year":2021},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.212040Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:4a7783ee654da7fa315b9bd29a8aabe7f1c09acf23967eb775ab922f1d2f1354","observation_id":"65c4bf09-a4f2-4006-a120-a169044ddf6e","resolution":{"observed_at":"2026-08-12T05:22:39.955389Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2023.32937","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:22:39.608295Z","title":null,"venue":null,"work_id":"bfc71a35-30f4-4b0b-90c9-c1835a06b4a1","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.216260Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:6bf9904800b6375c9421ab81dae8c575ada87cca38e593a0c048a8d84b9a4a2a","observation_id":"1db62f83-f85c-49f2-a3b1-dc715687dcc9","resolution":{"observed_at":"2026-08-12T05:22:39.616590Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03888","last_updated":"2024-10-15T05:51:38Z","snapshot_observed_at":"2026-08-12T23:07:08.590334Z","submitted_at":"2024-08-07T16:39:16Z","title":"Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03888","snapshot_observed_at":"2026-08-12T05:22:39.220413Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.220413Z"},"links":{"cited_paper":"/paper/2408.03888","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:2a97b312f5606fee1200d00340a62925aa279b68f02a86168277c7f224d53b5a","observation_id":"ba3d5015-a279-4df8-91eb-ef732f33f1cd","resolution":{"observed_at":"2026-08-12T05:22:39.220413Z","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":"2026-08-12T05:22:39.934417Z","title":null,"venue":null,"work_id":"4ad5172f-9f98-492a-85c0-42f8861d3f21","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.225361Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:a9c94c7b899fbc78d613ef6a44a1f9db8363066f1d4a68543462a0ae7d298d25","observation_id":"7da0a1ec-0b5f-48c1-97dd-269d8aa5be5d","resolution":{"observed_at":"2026-08-12T05:22:39.939639Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.919537Z","title":null,"venue":null,"work_id":"4da9f99e-2974-4a9e-a710-2859183d7fb7","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.230122Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:e91d898adffc5b332aa2a2012337dc60fea5ec49d0c7a18f73c682c748f6f621","observation_id":"ba7692a6-9545-4c51-a10e-3bdff239606a","resolution":{"observed_at":"2026-08-12T05:22:39.924214Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.234336Z","title":null,"venue":null,"work_id":null,"year":1947},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.234336Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:ad5f43a3cc9f5a9fde5bef0d8a28e2d07d14af2bebf18f6428420e3e80de2a49","observation_id":"f1d77f94-7e6b-400d-9baa-20b5e3f8daf6","resolution":{"observed_at":"2026-08-12T05:22:39.234336Z","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":"2026-08-12T05:22:39.893519Z","title":null,"venue":null,"work_id":"31017aa7-60af-4478-be8e-e4477c81b66d","year":2012},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.238841Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:b4789b91d4788e5a239a884464cfcf73b4f12f1224065e423fdb0cc7532782c5","observation_id":"ad2a3ec9-417c-4964-8073-48801ca44d06","resolution":{"observed_at":"2026-08-12T05:22:39.898162Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.878271Z","title":null,"venue":null,"work_id":"4e4ba463-2ee3-49c3-a6a0-dfa93e64d450","year":2022},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.243333Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:ab70d1a7e83d0b99c902ec0cf7d6dad18b2d2551a851cee7a2840a8a7187ec24","observation_id":"345907b5-38e4-4144-a8e1-30cde1cba430","resolution":{"observed_at":"2026-08-12T05:22:39.883658Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.858092Z","title":"Rohban, and Hamid R","venue":null,"work_id":"9f8f19ae-efaf-4743-aae0-d14c41cf625d","year":2021},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.247628Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:350af07853518239ce4eab235b7c86d6d366be4b220911b87f79b9347d4f741a","observation_id":"280f8245-1372-4b05-922d-3382a571ebb6","resolution":{"observed_at":"2026-08-12T05:22:39.862868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.844265Z","title":"Duong, Chanh D","venue":null,"work_id":"f315b151-788d-4089-95bd-60020d1c6eb5","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.252150Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:ad1e3846024b2370873e523e7142dc8285fdea64bcc2e335d19881f986ada45f","observation_id":"180d4f93-10d1-4d8e-aa62-6fcacfefdaa8","resolution":{"observed_at":"2026-08-12T05:22:39.848763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.829420Z","title":null,"venue":null,"work_id":"ff84447d-a118-4ef4-8741-a211cc026511","year":1992},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.256449Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:6464994fe3af7d0695fff020bafc7cb6f7d12e534ba07f32492980239fb275fc","observation_id":"f2d51342-32ff-452a-8ed9-21cde738e52d","resolution":{"observed_at":"2026-08-12T05:22:39.834126Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04097","last_updated":"2023-07-09T04:59:10Z","snapshot_observed_at":"2026-08-13T10:59:38.625433Z","submitted_at":"2023-07-09T04:59:10Z","title":"Restricted Generative Projection for One-Class Classification and Anomaly Detection","version":1},"cited_work":{"arxiv_id":"2307.04097","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.04097","snapshot_observed_at":"2026-08-12T05:22:39.426340Z","title":"Restricted Generative Projection for One-Class Classification and Anomaly Detection","venue":"cs.LG","work_id":"39bd51e3-19b6-4730-8b3d-022bd8ff0bad","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.260919Z"},"links":{"cited_paper":"/paper/2307.04097","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:c5788308abd9628fb9e3542b05b9ca3a75e43bfda41e21fb5bb18f34300408a4","observation_id":"a0b95697-3f65-4bbd-9221-1d8cffb9ab4c","resolution":{"observed_at":"2026-08-12T05:22:39.433329Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07487","last_updated":"2024-09-09T07:23:36Z","snapshot_observed_at":"2026-08-12T23:45:19.178112Z","submitted_at":"2024-06-11T17:27:23Z","title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07487","snapshot_observed_at":"2026-08-12T05:22:39.265863Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.265863Z"},"links":{"cited_paper":"/paper/2406.07487","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:8b973da233d495c8af8ae688d89bcbfd3f4074571ad35e617a711376d7dda7cd","observation_id":"f7ec1741-86d7-4c93-9b10-33b2340b87ae","resolution":{"observed_at":"2026-08-12T05:22:39.265863Z","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":"2026-08-12T05:22:39.815252Z","title":null,"venue":null,"work_id":"62f441ad-9ed0-4569-9e70-5d4f4eafafef","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.270945Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:e6dce601efc6d5953c4070b5dc95ff85c0c373529a1659d37d1febecc8764f7c","observation_id":"42fddb78-fe4b-4c1a-8283-4e0a84e57ea0","resolution":{"observed_at":"2026-08-12T05:22:39.820135Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.797257Z","title":null,"venue":null,"work_id":"0672c803-60a8-415b-a745-9db2d4125e2d","year":2020},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.275491Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:898524cc4d1032db29b54e2ef6aef80f18339c10aa57fc57ae12f83bb90e423a","observation_id":"2c228643-c5a1-438e-ad43-3f7cf387bf6f","resolution":{"observed_at":"2026-08-12T05:22:39.803767Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.03687","last_updated":"2022-10-25T08:37:08Z","snapshot_observed_at":"2026-08-13T15:28:16.156439Z","submitted_at":"2022-06-08T06:05:09Z","title":"A Unified Model for Multi-class Anomaly Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.03687","snapshot_observed_at":"2026-08-12T05:22:39.280180Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.280180Z"},"links":{"cited_paper":"/paper/2206.03687","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:8f01aa16142e7c48a7b0ec30d3f9fbed4e0d393d57776932e92b8cfd4d961ad5","observation_id":"acaee972-e839-4898-988f-803cf1004f19","resolution":{"observed_at":"2026-08-12T05:22:39.280180Z","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":"2026-08-12T05:22:39.779702Z","title":null,"venue":null,"work_id":"5e9a9026-d41e-45ec-baee-10c6fd8667a6","year":2021},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.284811Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:103604448ff781d466a81ecffb5dccb45acf9cbc4dc92e83a382c1eaa33e2f79","observation_id":"c9069d92-a1ef-4e85-97ab-9a1370441f4c","resolution":{"observed_at":"2026-08-12T05:22:39.784664Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.762083Z","title":null,"venue":null,"work_id":"90540239-c1e5-4ead-911d-a414f978c566","year":2022},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.289463Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:7525e2a380c9586f2ca8cddc5fc1f7f9ce39fbbabf34ec9740ab9fe05f95e47d","observation_id":"2c8f1119-a47e-4068-a154-f0bd6d2381a2","resolution":{"observed_at":"2026-08-12T05:22:39.767014Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.745661Z","title":null,"venue":null,"work_id":"4a5d28e7-e92b-48ba-8324-e8f559d0952b","year":2021},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.294590Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:272a4b35e33efd659b0eb438c897290b6db78327cee5319451ee4bd98143f218","observation_id":"c5418cad-d317-4f12-a713-b35e5f74dee6","resolution":{"observed_at":"2026-08-12T05:22:39.750601Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05897","last_updated":"2024-03-09T12:25:01Z","snapshot_observed_at":"2026-08-13T00:58:46.505557Z","submitted_at":"2024-03-09T12:25:01Z","title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05897","snapshot_observed_at":"2026-08-12T05:22:39.299225Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.299225Z"},"links":{"cited_paper":"/paper/2403.05897","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:4d57748b2a605aaaf547f10f7a8f88a8da4353d96acec6f99c9fd73d5232f14a","observation_id":"56404d13-facc-4790-8131-50ccde887817","resolution":{"observed_at":"2026-08-12T05:22:39.299225Z","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":"2026-08-12T05:22:39.727720Z","title":null,"venue":null,"work_id":"5b8f3251-df68-4eed-b547-154703a1f52d","year":2023},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.304165Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:1b92e03717500bca6cde817306c45a4cd892e03802b5910677a92bb7cd115062","observation_id":"56a29636-9e3f-418d-9b82-819c9cfbe3a8","resolution":{"observed_at":"2026-08-12T05:22:39.733565Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.712403Z","title":null,"venue":null,"work_id":"29f22caa-5cbd-4186-bb3a-8812cdf327d7","year":2022},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.308994Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:3dd67783690fe76f6cb121db982bc6f178b19feba92233839131a9b7312ea2c2","observation_id":"b97774f5-644b-4554-bf74-631c80689664","resolution":{"observed_at":"2026-08-12T05:22:39.717052Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T05:22:39.313590Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.313590Z"},"links":{"citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:750fb1d53fdb7fdbe7f0933abbcaf6eb4cdc7ef95fc060b477032a4c33dbd08e","observation_id":"675bf530-1d6f-477c-a7db-407d92798c0c","resolution":{"observed_at":"2026-08-12T05:22:39.313590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.14315","last_updated":"2022-07-28T18:00:03Z","snapshot_observed_at":"2026-08-13T14:54:47.952168Z","submitted_at":"2022-07-28T18:00:03Z","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.14315","snapshot_observed_at":"2026-08-12T05:22:39.318312Z","title":"arXiv preprint arXiv:2207.14315 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-12T05:22:39.318312Z"},"links":{"cited_paper":"/paper/2207.14315","citing_paper":"/paper/2412.00560"},"observation_digest":"sha256:e675c55947afc4bb0b59256a2ec30ff9c96ef04cc0dea4f11040275bc2b658b3","observation_id":"18ced5d4-b37f-4629-91bb-9e9573cd3949","resolution":{"observed_at":"2026-08-12T05:22:39.318312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.00560","last_updated":"2025-08-04T14:13:34Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T18:04:25.854745Z","submitted_at":"2024-11-30T19:07:16Z","title":"Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":34,"verified_exact":2,"verified_fuzzy":2},"total_outbound_references":39},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2412.00560."}