{"as_of":"2026-08-23T16:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6a72e789577114ee7c59af2cf03908a3d9e062737a6627fe362db4d948e36459","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:46:06.914961Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2608.06674/citation-record","integrity":"/paper/2608.06674/integrity","json":"/paper/2608.06674/citation-record.json","paper":"/paper/2608.06674"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T22:46:06.802812Z","title":"A survey of modern deep learning based object detection models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.802812Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:c0172f22c7bcb9718ea4ea30f5522e027861de236662152e23961cbb88179059","observation_id":"cb0b9b4d-dac7-4c85-aef1-ec8994ae7c37","resolution":{"observed_at":"2026-08-10T22:46:06.802812Z","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":"2026-08-10T22:46:07.180985Z","title":"A survey: object detection methods from cnn to transformer,","venue":null,"work_id":"e3544ee2-e8bf-4fa5-a599-e05a2cd856c2","year":2023},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.806265Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:1a5fa76f651a7cdc1816c142c9da6eecd4813745c12d5ccff21eac81dc0738f4","observation_id":"aeeddf61-a801-4cb6-a239-da7a68dd1d8a","resolution":{"observed_at":"2026-08-10T22:46:07.184851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:06.809125Z","title":"End-to-end object detection with transformers,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.809125Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:5a3804c42de7355fc2ca6fc6ad3457e5c721c485eb8bba8315736c52be2e1d74","observation_id":"de40e37e-0a84-416a-b2c0-f03a22617e22","resolution":{"observed_at":"2026-08-10T22:46:06.809125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.04159","last_updated":"2021-03-18T03:14:26Z","snapshot_observed_at":"2026-08-13T17:54:01.724774Z","submitted_at":"2020-10-08T17:59:21Z","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.04159","snapshot_observed_at":"2026-08-10T22:46:06.812442Z","title":"Deformable detr: Deformable transformers for end-to-end object detection,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.812442Z"},"links":{"cited_paper":"/paper/2010.04159","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:304e1751f7f15871e73534ee47a0f7b8363952c8c6817bcbaef4ebb05e3679f0","observation_id":"ab4d05f6-4a47-48ca-bc0b-c9901bb4a7a1","resolution":{"observed_at":"2026-08-10T22:46:06.812442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.03605","last_updated":"2022-07-11T10:30:29Z","snapshot_observed_at":"2026-08-18T07:50:02.322273Z","submitted_at":"2022-03-07T18:55:26Z","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.03605","snapshot_observed_at":"2026-08-10T22:46:06.817063Z","title":"Dino: Detr with improved denoising anchor boxes for end-to- end object detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.817063Z"},"links":{"cited_paper":"/paper/2203.03605","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:474bb8fe695afc4d8ba31c87a8f836dd1131fee635d89685770b00a287fa681b","observation_id":"ba459870-ec33-4da8-a043-cce0157967f4","resolution":{"observed_at":"2026-08-10T22:46:06.817063Z","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":"2026-08-10T22:46:07.168805Z","title":"Evaluating the adversarial robustness of detection transformers,","venue":null,"work_id":"0fcc87e0-3a57-4119-bdbd-21436b208080","year":2026},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.820271Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:52cf2eb8e24f96826a3015802e85a9a2010ef2b026079ac0df3047b22b7589d2","observation_id":"fc3da679-a7f8-4fe4-b666-3517224b9354","resolution":{"observed_at":"2026-08-10T22:46:07.171633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.160824Z","title":"Adversarial attention perturbations for large object detection transformers,","venue":null,"work_id":"ff8f4f52-3e10-4684-8350-63772c874da1","year":2025},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.823456Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:cc291ba2c0565b2fe404566cf78336044b99224f4b297354fd991e01748749f5","observation_id":"047b7e77-d803-4eb6-817a-1e7ac126e897","resolution":{"observed_at":"2026-08-10T22:46:07.164041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.152042Z","title":"Lite detr: An interleaved multi-scale encoder for efficient detr,","venue":null,"work_id":"b519b466-70ae-4305-b615-a8b73519bb8b","year":2023},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.827088Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:5d3254d76d0cdb2d9625c30cd2ba901aead8a7a36b9e05858cc79d8fe5437237","observation_id":"dea52e30-93ba-4703-98d6-6c5af47a1ca0","resolution":{"observed_at":"2026-08-10T22:46:07.155102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.144057Z","title":"Give me your attention: Dot-product attention considered harmful for adversarial patch robustness,","venue":null,"work_id":"d25fa173-377c-47c9-819d-b8d1d280aeb9","year":2022},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.829939Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:c011534cdf704f338b8f5e147f6e2aa90c6f1c3286f8f4b23a8250ab9a5f7dc4","observation_id":"ad484536-eb0d-44bd-b40e-46dc0316c947","resolution":{"observed_at":"2026-08-10T22:46:07.146811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.08392","last_updated":"2025-01-04T03:37:30Z","snapshot_observed_at":"2026-08-19T00:19:02.176712Z","submitted_at":"2022-03-16T04:45:59Z","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.08392","snapshot_observed_at":"2026-08-10T22:46:06.832506Z","title":"Patch-fool: Are vision transformers always robust against adversarial perturbations?","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.832506Z"},"links":{"cited_paper":"/paper/2203.08392","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:a7c76cc0bf7e817c22343c1a045842e1c51a4723c579d134be4985c0cc0d67b9","observation_id":"89c56a5b-918b-40c6-b59f-b49749706a81","resolution":{"observed_at":"2026-08-10T22:46:06.832506Z","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":"2026-08-10T22:46:07.135439Z","title":"Adversarial examples for semantic segmentation and object detection,","venue":null,"work_id":"47441d08-459e-4a15-a2f5-12a00b67ac55","year":2017},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.835333Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:4855a27f6be3ae378ce8cf2ce523db770573e7f83453977520c225dfcd1d5c73","observation_id":"0a1edbbd-3136-4df8-aa5d-bd9a4a5cdd06","resolution":{"observed_at":"2026-08-10T22:46:07.138986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12641","last_updated":"2019-05-13T07:22:16Z","snapshot_observed_at":"2026-08-20T09:09:47.669293Z","submitted_at":"2018-11-30T06:55:22Z","title":"Transferable Adversarial Attacks for Image and Video Object Detection","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.12641","snapshot_observed_at":"2026-08-10T22:46:06.838424Z","title":"Transferable adversarial attacks for image and video object detection,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.838424Z"},"links":{"cited_paper":"/paper/1811.12641","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:2888abb31e2a708d3dfe2c47ecfaf12ca3bdd6ec2250d48e1498d5d1420ae6db","observation_id":"538ec394-0bf5-4507-b41b-de297eaca26e","resolution":{"observed_at":"2026-08-10T22:46:06.838424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.05962","last_updated":"2019-11-03T15:18:03Z","snapshot_observed_at":"2026-08-18T02:21:30.845277Z","submitted_at":"2018-09-16T21:49:14Z","title":"Robust Adversarial Perturbation on Deep Proposal-based Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.05962","snapshot_observed_at":"2026-08-10T22:46:06.842568Z","title":"Robust ad- versarial perturbation on deep proposal-based models,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.842568Z"},"links":{"cited_paper":"/paper/1809.05962","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:5ff25cd22dcc0b312250505662f08332df981eff86c7f61a5e0ca1665bcca4d8","observation_id":"3af7cc6b-d1c7-44d0-9a68-a3a9bd8c272a","resolution":{"observed_at":"2026-08-10T22:46:06.842568Z","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":"2026-08-10T22:46:07.127282Z","title":"Adversarial objectness gradient attacks in real-time object detection systems,","venue":null,"work_id":"44be31b9-ddad-428d-b947-cdb0ae871ae7","year":2020},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.845596Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:eab66b77830bba5fe4d8c199fc7cfcd453b8c84e7897d07b10119b5192f8e2b9","observation_id":"7a6962a0-141a-4ef8-98a5-973fafc60baa","resolution":{"observed_at":"2026-08-10T22:46:07.130282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-19T07:17:20.004918Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-10T22:46:06.848186Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.848186Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:82008134b9a9a2e9ef2e4d6beac58d3aa9276fd4e7b97d5089308a9ce71929fb","observation_id":"bd6fc859-4134-4356-8945-661a6559995b","resolution":{"observed_at":"2026-08-10T22:46:06.848186Z","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":"2026-08-10T22:46:07.119077Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":"e40b8274-785f-4219-aeb4-f1b4b5702fd1","year":2018},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.851556Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:994dec79ce3ef5b2d4220901f279de2e7a9ea3b7c54e46963f1aeee33736bb6b","observation_id":"45240bc9-5937-4cc3-a52a-34c3adec218e","resolution":{"observed_at":"2026-08-10T22:46:07.122031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:06.854213Z","title":"Towards evaluating the robustness of neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.854213Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:db04075015e273fabe060f5fea65784d6f4cc10e9e0e432bca54d207c289fe22","observation_id":"986df3e9-8503-4883-b9f4-9b9eec4e69a3","resolution":{"observed_at":"2026-08-10T22:46:06.854213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-10T22:46:06.857020Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.857020Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:fc9307ccc58db121de4c395add80cf9bb67055c33a53898f7da7c40266b1b402","observation_id":"59e12877-6905-4cdb-a9a8-909a90ad306d","resolution":{"observed_at":"2026-08-10T22:46:06.857020Z","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":"2026-08-10T22:46:06.859942Z","title":"Training data-efficient image transformers & distillation through attention,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.859942Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:ff949e624a8f3f851c7feb1674e134a18680c8769f95913462daacaa7d7eaa29","observation_id":"5ba27241-4bd3-4020-9e2c-3120804b3de1","resolution":{"observed_at":"2026-08-10T22:46:06.859942Z","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":"2026-08-10T22:46:07.102291Z","title":"Localized query attack toward transformer-based visible object detectors,","venue":null,"work_id":"7f4b99ce-184a-4ca9-9aca-3ce523eb234c","year":1987},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.866814Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:46e22237f2c785c40795bf884d6a5ff61c5d08d21c119ba10ea9b8b9b6611a34","observation_id":"c7a0c03b-e3ac-46e6-b868-bfd05a87b2ab","resolution":{"observed_at":"2026-08-10T22:46:07.105643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.093370Z","title":"Ad- versarial attention deficit: Fooling deformable vision transformers with collaborative adversarial patches,","venue":null,"work_id":"ea119e22-d37f-42ae-8458-2cbb6970ad90","year":2025},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.870449Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:3791ea3f349cf921d434c74f335e9542aa9e21edb9e52f2a5b716cf8b7e5e7d9","observation_id":"eecb2152-75d8-4913-87a7-97fed269214a","resolution":{"observed_at":"2026-08-10T22:46:07.096419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.085314Z","title":"The lipschitz constant of self- attention,","venue":null,"work_id":"479859c6-9fa9-430f-a596-97c109b136af","year":2021},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.873018Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:22d64a8d16bc43ca91467e5c10da371743a8422fcfff87888717639e234aea06","observation_id":"2deb2707-32dd-4b3f-8809-4a2bd689f766","resolution":{"observed_at":"2026-08-10T22:46:07.088090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:06.875645Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.875645Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:9ad398bd41372d26db43be4734c2135c04203918d9bf75024a5ffe3c3bdf5642","observation_id":"571aa0f0-4369-4236-a45a-acf4432815e1","resolution":{"observed_at":"2026-08-10T22:46:06.875645Z","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":"2026-08-10T22:46:06.878857Z","title":"Microsoft coco: Common objects in context,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.878857Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:70da6f33accd5b91b0cb53e596104a514c97ce4f22bf39a4b35bd8e4d00ab143","observation_id":"ae92e26f-41f5-438e-8b82-4af2367ddeb8","resolution":{"observed_at":"2026-08-10T22:46:06.878857Z","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":"2026-08-10T22:46:06.881469Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.881469Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:32a9316600755589bb4fd45d3a48ef321827d86a10122491f25d5eeee9ea5bf2","observation_id":"dfbc8305-d812-4ec8-8ad3-5af93bfbc3d6","resolution":{"observed_at":"2026-08-10T22:46:06.881469Z","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":"2026-08-10T22:46:07.063266Z","title":"A large-scale multiple-objective method for black-box attack against object detection,","venue":null,"work_id":"29d65729-bfb7-423f-801f-5f881cff4f0f","year":2022},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.884042Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:b48018ce0cd70ea1ace827121771dbf41ddfc05ea3910855dfc7626d13ef62cc","observation_id":"d3c7ec68-418e-44fa-a5f7-9232368c6e49","resolution":{"observed_at":"2026-08-10T22:46:07.066266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.054751Z","title":"Improving transferable adversarial attack for vision transformers via global attention and local drop,","venue":null,"work_id":"8de68382-6a6f-417e-9954-6bf85f2a993d","year":2023},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.887547Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:3ee29467a06d9a5e92c580217cf99a0a7d89e713992e06aa2d3feb614a1975a2","observation_id":"a35bed58-a041-42e7-a314-f355e43c95dc","resolution":{"observed_at":"2026-08-10T22:46:07.057788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.06822","last_updated":"2021-11-23T14:15:34Z","snapshot_observed_at":"2026-08-21T02:09:29.904579Z","submitted_at":"2020-08-16T02:44:25Z","title":"Relevance Attack on Detectors","version":4},"cited_work":{"arxiv_id":"2008.06822","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.06822","snapshot_observed_at":"2026-08-10T22:46:06.935369Z","title":"Relevance Attack on Detectors","venue":"cs.CV","work_id":"1e99286b-417b-4a64-9122-f673fe7e90b8","year":2020},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.890373Z"},"links":{"cited_paper":"/paper/2008.06822","citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:8e8746f46ab89a6e8ec03a117d61cb45f209b3310c167fa2eeab4eff907ba395","observation_id":"94a4d4f2-4da7-4722-b633-b1aa3e57da4e","resolution":{"observed_at":"2026-08-10T22:46:06.939996Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.046202Z","title":"Gradient- guided hierarchical feature attack for object detector,","venue":null,"work_id":"8fada956-e972-48a6-8f01-b8d5cbe50875","year":2024},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.893366Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:1e786934e0f954d7f3674154a99208253b3510db243e884ef85b669276773224","observation_id":"e145be79-6761-4890-8bd1-77e13599c1fe","resolution":{"observed_at":"2026-08-10T22:46:07.049432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.036531Z","title":"Ensemble-based blackbox attacks on dense prediction,","venue":null,"work_id":"17f7fb4f-b6a0-4fc9-bbcd-0fd18fc74fbb","year":2023},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.896298Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:28f18d68f796ce16ca2a823242193ffe4fe3a2df60c7dc59e9ed13b745d4fb7e","observation_id":"40068108-d616-42e0-946f-97a8d5f4d7b1","resolution":{"observed_at":"2026-08-10T22:46:07.039734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:07.027502Z","title":"Object-aware transfer-based black-box adversarial attack on object detector,","venue":null,"work_id":"a540db5b-0339-47a4-903e-1042bc8332df","year":2023},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.899008Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:6fe85c936a22cd2d7dabf7c3aece61c24d87abf2513fb93375c1422857a30f90","observation_id":"af4b86ac-ae67-4188-b640-84e97e158e74","resolution":{"observed_at":"2026-08-10T22:46:07.031047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:06.901676Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.901676Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:5b6a662645dd5ae8d7641d66e8fde5928d7ef7fa818624b0df79700b1c8b8639","observation_id":"fb487fc1-44bf-4d32-97d7-4a4ba26abb3e","resolution":{"observed_at":"2026-08-10T22:46:06.901676Z","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":"2026-08-10T22:46:06.904284Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.904284Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:c0403f7ec5636f933e95b4f63e9f792ac3bf9efe6545d8fffe8b960c22fe9fde","observation_id":"c31c02ad-9d25-411c-8d9f-987961647a41","resolution":{"observed_at":"2026-08-10T22:46:06.904284Z","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":"2026-08-10T22:46:06.906852Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.906852Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:8acd7f03eb23d9feaa24bb39518f8f9fbcda9526e53ddd3ec7a352130ef7d24c","observation_id":"82d57557-cb15-4554-8909-54d48162d6f6","resolution":{"observed_at":"2026-08-10T22:46:06.906852Z","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":"2026-08-10T22:46:07.006242Z","title":"Internimage: Exploring large-scale vision foundation models with deformable convolutions,","venue":null,"work_id":"acd96b5d-2253-4d9f-9142-f109c0b03b63","year":2023},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.909409Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:82da772aee043311844c1cf4875bdb318105586da6c4eebe327048df0d33ce90","observation_id":"6986e513-9ab0-49d2-a0db-d987acd87d29","resolution":{"observed_at":"2026-08-10T22:46:07.009386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-10T22:46:06.911998Z","title":"Focal modulation networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.911998Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:4e245673e193637279e9652de167dbf41a39cf925a0c0afe800238439ac55f6f","observation_id":"0c0e8b4e-5ac2-4d4e-ad0a-d71188eda6fa","resolution":{"observed_at":"2026-08-10T22:46:06.911998Z","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":"2026-08-10T22:46:06.991487Z","title":"Eva: Exploring the limits of masked visual representation learning at scale,","venue":null,"work_id":"d87504d9-08ce-46f1-a123-07cfd2f6930e","year":2023},"citing_paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T22:46:06.914961Z"},"links":{"citing_paper":"/paper/2608.06674"},"observation_digest":"sha256:146a845dc7064b347d5b7d2512de95affa3fc232deb19bee6062bdbbec499d4d","observation_id":"ff466371-215b-4221-bb6f-e6e59ad05d31","resolution":{"observed_at":"2026-08-10T22:46:06.995733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.06674","last_updated":"2026-08-07T00:42:25Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T20:19:07.405423Z","submitted_at":"2026-08-07T00:42:25Z","title":"Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":1,"verified_fuzzy":18},"total_outbound_references":37},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2608.06674."}