{"as_of":"2026-08-16T13:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b723324535d8437400be06e646786b7297d4b62b1c61d8c271d94b3b47c4471","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T00:21:38.485958Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2608.07770/citation-record","integrity":"/paper/2608.07770/integrity","json":"/paper/2608.07770/citation-record.json","paper":"/paper/2608.07770"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:39.590470Z","title":"Oceans 11 Data Repository","venue":null,"work_id":"9ecb8eb4-faba-4653-9771-faa96f3c7301","year":2026},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.342933Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:02edc18d5a74187b4629490291c0e455a7ff0ec10acef248fdfab80512f110bf","observation_id":"d2076e6d-864c-47fe-bd19-fc925d8b07e0","resolution":{"observed_at":"2026-08-11T00:21:39.594814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:39.577541Z","title":"Annomate with microsentryai: Human-in-the-loop aiml-powered inspection tools","venue":null,"work_id":"e005018c-a336-4b2b-86c1-029194d6e8a4","year":2026},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.347224Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:dea3056146fa83fd5f1955096e4c56413168ecaa1acbe7a480b671df26b29b7a","observation_id":"eb5887f1-11d0-41b7-9d88-e4b37ba0f0ba","resolution":{"observed_at":"2026-08-11T00:21:39.581982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:38.351978Z","title":"Anomaly detection in laser powder bed fusion using machine learning: A review,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.351978Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:fbd7be22c92cc273e37e41e6dc717e2be0173628526e80be1672261331dcc8d3","observation_id":"ba8ebd6d-3f23-4938-b6dd-fa95c9d5b4b9","resolution":{"observed_at":"2026-08-11T00:21:38.351978Z","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":"10.1016/j.infrared.2013.07.007","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:38.609698Z","title":"Automatic metal parts inspection: Use of thermographic images and anomaly detection algorithms,","venue":null,"work_id":"f66f5787-06d2-456f-a958-59bc8c310674","year":2013},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.355873Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:f59f390adc06bef3cefedecdd5279b79858939b6bc697bbd61a130ed5c036d71","observation_id":"a5a622b1-c792-4853-872c-99858f429428","resolution":{"observed_at":"2026-08-11T00:21:38.614006Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-11T00:38:06.108413+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-11T00:38:06.108413+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.jmapro.2022.06.046","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:38.597466Z","title":"A deep-learning-based in-situ surface anomaly detection methodology for laser directed energy deposition via powder feeding,","venue":null,"work_id":"61867e30-71f9-43e3-94b6-d86d8081ee53","year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.360328Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:f079ae9656c888f55d2a0fa4296216a0fc3464cdf77b9502692737ee611e0993","observation_id":"e8ec180c-9af6-4f3c-948a-5a45d38aa01d","resolution":{"observed_at":"2026-08-11T00:21:38.601758Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-11T00:38:06.207773+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-11T00:38:06.207773+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:38.364410Z","title":"The via annotation software for images, audio and video,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.364410Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:cee76fc855824d5a4e7d8f624af60d5bf0515e887cdf5d852930f7d8f08e006d","observation_id":"f332ea5c-9890-4cfb-86a7-1338b75b463b","resolution":{"observed_at":"2026-08-11T00:21:38.364410Z","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":"2026-08-11T00:21:38.368731Z","title":"Labelme: A database and web-based tool for image annotation,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.368731Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:9611c7d97ee8c5d0c343f467523f91e9b0dbcc40cb782acb095708834c7d22c7","observation_id":"684fc48f-ae7c-484c-add3-784079f9ff73","resolution":{"observed_at":"2026-08-11T00:21:38.368731Z","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":"2026-08-11T00:21:38.372912Z","title":"Anomaly detection: A survey,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.372912Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:6ff5d2485d93bf6e61bb836b0d2ca9385e2bc55687f4be3145133f7fed1627dc","observation_id":"0ba3b262-c81b-4f9a-9cb5-25d722680939","resolution":{"observed_at":"2026-08-11T00:21:38.372912Z","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":"2026-08-11T00:21:38.376839Z","title":"Deep Learning for Anomaly Detection: A Review doi: 10.1145/3439950,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.376839Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:6d449df6c4f7240c7e71f64b5d58cbeba5e9b1ab40e945cd193002e35beeaa1f","observation_id":"2d681ef9-0599-485c-bf26-1d03f3f43540","resolution":{"observed_at":"2026-08-11T00:21:38.376839Z","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":"2026-08-11T00:21:38.381861Z","title":"Anomalib: A Deep Learning Library for Anomaly Detection doi: 10.1109/ICIP46576.2022.9897283,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.381861Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:cf4b4d223d0e94c82dca3a0c1393d3458b219072ae65db1aad5ba9ed3f27a073","observation_id":"2d3c66eb-7df6-4e5e-aa85-20636c9503f9","resolution":{"observed_at":"2026-08-11T00:21:38.381861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03294","last_updated":"2023-04-21T03:00:18Z","snapshot_observed_at":"2026-08-16T09:38:33.087660Z","submitted_at":"2023-04-06T07:05:59Z","title":"What makes a good data augmentation for few-shot unsupervised image anomaly detection?","version":3},"cited_work":{"arxiv_id":"2304.03294","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.03294","snapshot_observed_at":"2026-08-11T00:21:39.159678Z","title":"What makes a good data augmentation for few-shot unsupervised image anomaly detection?","venue":"cs.CV","work_id":"f213fae6-0db0-40cb-9378-144694412082","year":2023},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.386506Z"},"links":{"cited_paper":"/paper/2304.03294","citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:19979ce5f930be3b85510a3bad1f61f615754fd406a5effcc3700123e820fa1b","observation_id":"2d2c9c90-6750-4e51-8abf-fd075f3f5212","resolution":{"observed_at":"2026-08-11T00:21:39.164235Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:38.392009Z","title":"The MVTec anomaly detection dataset: A comprehensive real-world dataset for unsupervised anomaly detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.392009Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:6506f46d4e7ab0c16dfdf6e4d9f09f17344a0ef548f3fa13616358a80884f25f","observation_id":"9429da1f-307f-4614-8810-ba8d03b8a22c","resolution":{"observed_at":"2026-08-11T00:21:38.392009Z","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":"10.1007/s11633-023-","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:38.563217Z","title":"Deep industrial image anomaly detection: A survey,","venue":null,"work_id":"cb8f1de0-d532-490e-bdab-d851965acf29","year":2024},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.396225Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:fbb0cd7a3f64584ee7b4e900736e3265ae084c93e448917cf0beed41fd2f4cbd","observation_id":"8dce2351-e3a9-4314-9bf0-61bd5bec4776","resolution":{"observed_at":"2026-08-11T00:21:38.567411Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13359","last_updated":"2024-01-28T02:20:41Z","snapshot_observed_at":"2026-08-15T20:14:32.301762Z","submitted_at":"2023-01-31T01:24:45Z","title":"IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing","version":5},"cited_work":{"arxiv_id":"2301.13359","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.13359","snapshot_observed_at":"2026-08-11T00:21:39.141864Z","title":"IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing","venue":"cs.CV","work_id":"28258b43-7c70-4c95-b6b3-3625d05afebf","year":2023},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.403071Z"},"links":{"cited_paper":"/paper/2301.13359","citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:7eb7aec7e8141725e3ba447186796e109e448ff72a15d5b8a11014640e897ece","observation_id":"95bfa6c1-9df4-4a7e-87a3-a453c6bec353","resolution":{"observed_at":"2026-08-11T00:21:39.146987Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:38.406706Z","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.406706Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:64c3890f4dc722c226ae02ec0ef2903a13cdbadc4e5ad0de43dc9602c770ef1e","observation_id":"5f921e49-73d6-4dcc-9b2b-db00e981e006","resolution":{"observed_at":"2026-08-11T00:21:38.406706Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5244/c.35.349","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:38.550523Z","title":"Student-teacher feature pyramid matching for anomaly detection,","venue":null,"work_id":"5d1b6edf-264f-4e67-acba-18edb083cae2","year":2021},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.416717Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:43b2be6eef3b2d7f0b01c1c57f95c6c36814e2570c76eaf6fb2a03d03601ae61","observation_id":"722057b0-7ee8-425c-8ff6-62d04c985f23","resolution":{"observed_at":"2026-08-11T00:21:38.555278Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-11T00:38:06.536149+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-11T00:38:06.536149+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:38.420983Z","title":"Towards Total Recall in Industrial Anomaly Detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.420983Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:21dc7bd3f48a73f67a1d1a1db47998b42d0f73d7e26b4aa5a51af686fd1a298a","observation_id":"b99d8bbb-af4d-4079-a7f3-6b27e6947933","resolution":{"observed_at":"2026-08-11T00:21:38.420983Z","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":"10.1007/978-3-030-68799-","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:21:38.534615Z","title":"PaDiM: A patch dis- tribution modeling framework for anomaly detection and localization,","venue":null,"work_id":"86066445-5f99-415b-926b-cce681b862ff","year":2021},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.425104Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:512fc3168f1162a35d56d96fa133a032d55abe8cca8cb309e724e3ed64ea61e7","observation_id":"ebe099f2-9054-4ee9-8562-1bd3de994452","resolution":{"observed_at":"2026-08-11T00:21:38.541539Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:38.429113Z","title":"CFA: Coupled-hypersphere-based fea- ture adaptation for target-oriented anomaly localization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.429113Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:e5d3cdbe3046cc9a80983ba8f480800edfc43c0bbf6f5f894df3eaf6b5305daa","observation_id":"32ec5883-0a7a-45b7-a743-8d3f70d5942d","resolution":{"observed_at":"2026-08-11T00:21:38.429113Z","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":"2026-08-11T00:21:38.433567Z","title":"AnomalyDINO: Boosting Patch-based Few-Shot Anomaly Detection with DINOv2,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.433567Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:5b24a595647af863c4fec4d4f2f90fcc19b0d17ad8d9142bef8451d96d649717","observation_id":"7bd3ac05-fa37-490e-ace2-47ed8c511f4c","resolution":{"observed_at":"2026-08-11T00:21:38.433567Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03143","last_updated":"2024-08-22T15:38:28Z","snapshot_observed_at":"2026-08-15T14:30:05.310765Z","submitted_at":"2024-08-06T12:37:47Z","title":"SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection","version":2},"cited_work":{"arxiv_id":"2408.03143","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.03143","snapshot_observed_at":"2026-08-11T00:21:38.821402Z","title":"SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection","venue":"cs.CV","work_id":"c29ccbc9-8029-4195-8178-ca0346ce9578","year":2024},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.437744Z"},"links":{"cited_paper":"/paper/2408.03143","citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:ed6e0424a65b0fa4dd2b3d2788fbccd8447075edc6b339b53bf81c50afb265af","observation_id":"96d4b774-2c04-4d3f-9e98-1b9289d919c2","resolution":{"observed_at":"2026-08-11T00:21:38.826220Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07677","last_updated":"2021-11-16T06:33:39Z","snapshot_observed_at":"2026-08-13T17:34:01.767269Z","submitted_at":"2021-11-15T11:15:02Z","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07677","snapshot_observed_at":"2026-08-11T00:21:38.442041Z","title":"FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.442041Z"},"links":{"cited_paper":"/paper/2111.07677","citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:80f89b970ded0d7509d2a808b350052080c52f9e669b74351b93db7a0b863ab6","observation_id":"e3294870-ba0c-4a78-ad19-ba8851e9ab11","resolution":{"observed_at":"2026-08-11T00:21:38.442041Z","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":"2026-08-11T00:21:38.449566Z","title":"Fully Convolu- tional Cross-Scale-Flows for Image-based Defect Detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.449566Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:6a25a1c3e1c80e74b1f5931bfd1c7bf07fe9e75cb019358969c0745b6926304f","observation_id":"237cd5db-f1fc-48c5-a24f-f307a1e79e5d","resolution":{"observed_at":"2026-08-11T00:21:38.449566Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-11T00:21:38.453160Z","title":"U-Flow: A u-shaped normalizing flow for anomaly detection with unsupervised threshold,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.453160Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:0c75f8de7d36dd497fe22b4956f137d8681975232a299e29012f9399ab6cf0c9","observation_id":"61cb56cb-5a1b-4f52-a7b8-9f4ce4b413e6","resolution":{"observed_at":"2026-08-11T00:21:38.453160Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-11T00:21:39.565466Z","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection,","venue":null,"work_id":"4924c6d0-37c1-4617-93d3-d0b5d35753ac","year":2025},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.456928Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:f9f298a0c28ea3daa874da0fa3c1b22b4712acad614ade431e902240c6782293","observation_id":"71b1f222-e5e1-4cdc-bd56-0ae4d225c9e5","resolution":{"observed_at":"2026-08-11T00:21:39.569741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:38.460646Z","title":"DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.460646Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:a3ab7c57e2b469bab7a0e9c139de374eb069d5fa7025076e46470031e04e54db","observation_id":"4aa0824f-7429-4193-9fe6-865abd51f548","resolution":{"observed_at":"2026-08-11T00:21:38.460646Z","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":"2026-08-11T00:21:38.465333Z","title":"DSR – a dual subspace re- projection network for surface anomaly detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.465333Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:b18f3e63d25c7b574aa1be9b36a1945ef3fd712957d32cb28fca4af1a39d4e4d","observation_id":"f8f34c0d-a924-40c1-8431-19e7ef61899d","resolution":{"observed_at":"2026-08-11T00:21:38.465333Z","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":"2026-08-11T00:21:39.552801Z","title":"GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training [arXiv],","venue":null,"work_id":"60f0cea4-1f47-4ab4-8f25-82f7b77579c4","year":2018},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.469072Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:5c14310b504c646ca5872b1f996e06a3ce98d377eb9dc5c8b1353882aa8d3ef5","observation_id":"2ea92b06-060c-40ba-94e5-b8b47d44274c","resolution":{"observed_at":"2026-08-11T00:21:39.557524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:39.540439Z","title":"FRE: A Fast Method For Anomaly Detection And Segmentation [arXiv],","venue":null,"work_id":"a816f77e-00d4-4a93-ab93-1cb40d239781","year":2022},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.472902Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:6bf385325560dd66779fb5b8caa27e7184d686773d108394121f9b81e44c1079","observation_id":"5c3c13d9-8e86-4dd8-a28e-b88c355b6438","resolution":{"observed_at":"2026-08-11T00:21:39.544696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11786","last_updated":"2019-09-25T21:41:56Z","snapshot_observed_at":"2026-08-10T22:12:16.636212Z","submitted_at":"2019-09-25T21:41:56Z","title":"Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11786","snapshot_observed_at":"2026-08-11T00:21:38.476849Z","title":"Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.476849Z"},"links":{"cited_paper":"/paper/1909.11786","citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:1be10792388a5696fdd9bab040ee9a8d764397f063652d572ffdc9bad38663ae","observation_id":"91e1ef83-66d3-40be-af3d-d850feda3042","resolution":{"observed_at":"2026-08-11T00:21:38.476849Z","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":"2026-08-11T00:21:39.526219Z","title":"Repository for reproducibility for ICMLA 2026","venue":null,"work_id":"40391073-ee94-4487-bb3e-ffebcfc9df60","year":2026},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.481954Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:789fe2977256db825bd571bafd12372a241590edcabb62a50f5d2dd64b62d445","observation_id":"e447f304-8dba-41e0-8e1d-0105f9dc0287","resolution":{"observed_at":"2026-08-11T00:21:39.532088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T00:21:39.507254Z","title":"SAM 2: Segment Anything in Images and Videos,","venue":null,"work_id":"8594771c-4db8-4f55-b0d6-e7e882ed0002","year":2025},"citing_paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T00:21:38.485958Z"},"links":{"citing_paper":"/paper/2608.07770"},"observation_digest":"sha256:00625c2868539ec1ec96ffafad719002eca9b644526121cd69bb1c898ca33f69","observation_id":"8ee87fa6-6de1-4dc5-8af1-4720a7cddee7","resolution":{"observed_at":"2026-08-11T00:21:39.512888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.07770","last_updated":"2026-08-07T21:31:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T23:21:06.523504Z","submitted_at":"2026-08-07T21:31:20Z","title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":6,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":6,"verified_fuzzy":7},"total_outbound_references":32},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2608.07770."}