{"as_of":"2026-08-19T09:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6b87eee4a6ea371f96bfa2429b56903c0c694741e54a8f4de8c79ee07ee1d25e","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T04:50:41.467985Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-17T02:36:16.437850Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-17T02:38:53.929427Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"cited_work":{"arxiv_id":"2508.02987","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.02987","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adversarial attention perturbations for large object de- tection transformers.ArXiv, abs/2508.02987","venue":null,"work_id":"0033062d-20ad-4468-a939-1661e539f7a4","year":2025},"citing_paper":{"arxiv_id":"2512.03730","last_updated":"2026-04-10T13:02:39Z","snapshot_observed_at":"2026-08-09T09:17:50.128906Z","submitted_at":"2025-12-03T12:17:35Z","title":"Out-of-the-box: Black-box Causal Attacks on Object Detectors","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-17T02:36:16.437850Z"},"links":{"cited_paper":"/paper/2508.02987","citing_paper":"/paper/2512.03730"},"observation_digest":"sha256:41d1c01f3dc499fe42c7ab88cdd5fb2d533e657e3e1fadd4886bc74a114adb49","observation_id":"54a19a12-eb9e-4dcd-92a7-88ce5ffa8497","resolution":{"observed_at":"2026-05-17T02:38:53.931560Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.02987/citation-record","integrity":"/paper/2508.02987/integrity","json":"/paper/2508.02987/citation-record.json","paper":"/paper/2508.02987"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T04:50:41.295390Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.295390Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:3c4dfa948ffe4510d2971063280c5c6a8cd9658de0f1b822b6cd3f7929a044f4","observation_id":"4b512809-7824-4cba-8227-2d70708eac34","resolution":{"observed_at":"2026-08-06T04:50:41.295390Z","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":"2026-08-06T04:50:41.897490Z","title":"Align-detr: Improving detr with sim- ple iou-aware bce loss, 2023","venue":null,"work_id":"eaceeeb4-2531-4137-9433-c566fc76dfbe","year":2023},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.299246Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:c57a9fe5792a054ff5b0f13675561b82ef5b942cbfd54428ad031203c9386998","observation_id":"511110d8-fc30-40a9-99b6-10e507bc1d3b","resolution":{"observed_at":"2026-08-06T04:50:41.900325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.888301Z","title":"Salman Asif","venue":null,"work_id":"f1b6c7ac-c38e-443a-aa5f-e4694a6e3acb","year":2023},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.302497Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:90d229357db02ff59850a876372a0adaa554f94ed3e9c39f9905f0caf82ca581","observation_id":"706a60d7-a672-4a27-b86b-914200431043","resolution":{"observed_at":"2026-08-06T04:50:41.891174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.878744Z","title":"End-to-end object detection with transformers","venue":null,"work_id":"86e5dbda-563d-4020-96dc-1d247e478e94","year":2020},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.305678Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:22214fc3e9b9d8f317aa90d3c30497e3f36c0d6b25de7ec6c372b02c24727a6c","observation_id":"c64cb791-32d1-445d-ad95-55c04478c62a","resolution":{"observed_at":"2026-08-06T04:50:41.881917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.868572Z","title":"Rele- vance attack on detectors","venue":null,"work_id":"1c442497-8359-4099-af88-8799a81103e4","year":null},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.312091Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:3e0add91735615936e31d23049ec5a83526f46202005ff49aa8d958ca8634d43","observation_id":"b4d9f301-eda8-4957-a773-f9ace99a2477","resolution":{"observed_at":"2026-08-06T04:50:41.872409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.859380Z","title":"Understanding ob- ject detection through an adversarial lens","venue":null,"work_id":"2bf572ee-7519-42a9-bd91-c144bee94dec","year":2020},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.314941Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:080f7904519792eed6e4c1755ed88f1c04856c1ffb4c8eef6d2cd3a6c5f264a4","observation_id":"e6b48724-7185-45b3-a9d3-6c06b7aa6db4","resolution":{"observed_at":"2026-08-06T04:50:41.862632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.849568Z","title":"Adversarial objectness gradient attacks in real- time object detection systems","venue":null,"work_id":"0b85e131-c158-4801-870e-1b1d4d77cf41","year":2020},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.317916Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:7419e4097c71dc4ccc0c3b09c2982aeaa918416b93c8858660f588d595df7d83","observation_id":"b28ffc3a-282b-4ddc-952e-d2625587bdee","resolution":{"observed_at":"2026-08-06T04:50:41.852845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.840618Z","title":"Object detection on coco test- dev","venue":null,"work_id":"99eb9b1c-b51d-43b8-950c-801db48b8fc0","year":null},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.320938Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:101a987780637636dab9dc8229d29978a1fd4ffda9e1f73f0eb4abb7ca45dc2d","observation_id":"f3257702-bb6d-4f78-81de-80c38bc5b48f","resolution":{"observed_at":"2026-08-06T04:50:41.843837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.831514Z","title":null,"venue":null,"work_id":"e7463379-5d42-4cf6-aece-963d6c23ab5c","year":2010},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.323917Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:e7570bd0a6a6f3dee460a3a06dba8c42a4a2ed781bb88688253edce708f5f482","observation_id":"a148af88-ac3d-4b12-b2ff-a6725219fe15","resolution":{"observed_at":"2026-08-06T04:50:41.834243Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.07636","last_updated":"2022-12-05T13:53:51Z","snapshot_observed_at":"2026-08-16T16:16:16.267082Z","submitted_at":"2022-11-14T18:59:52Z","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.07636","snapshot_observed_at":"2026-08-06T04:50:41.326740Z","title":"Eva: Exploring the limits of masked visual represen- tation learning at scale","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.326740Z"},"links":{"cited_paper":"/paper/2211.07636","citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:a80c3b7351b826a9fe5a23d417d6dd6cd11bffe76c03b8af373887995c0c3ac7","observation_id":"3ba9e894-b14d-4fae-87cd-88aa7c59178f","resolution":{"observed_at":"2026-08-06T04:50:41.326740Z","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":"2026-08-06T04:50:41.821878Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"386d98fd-9d96-4b8c-8dcb-114843b3b64f","year":2016},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.330173Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:2f4704224e04f403f9be94a9a92431366e1057e221be698e5792e14e6067f810","observation_id":"96e0d3b4-bb09-4216-bbb9-f22931c60d60","resolution":{"observed_at":"2026-08-06T04:50:41.825190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.812931Z","title":"Object-aware transfer-based black-box adversarial attack on object detector","venue":null,"work_id":"bdef34f6-e51b-4291-bc1f-3675e33ab596","year":2024},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.333116Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:a22c2097e18e9009893765227d0b25d1e95423ff195d812c6030ac45a9754ec8","observation_id":"f0568a9a-0176-40c8-9cbc-8fec4b0bacf3","resolution":{"observed_at":"2026-08-06T04:50:41.816047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.803387Z","title":"Improving transferable adversarial attack for vision transformers via global attention and local drop","venue":null,"work_id":"119505ab-713f-4212-92b4-21bfdac4b2f5","year":2023},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.335853Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:1bfe0883dfc451bac5e3139e6b0af034d8b10a208a9c2f449077a1cf5e3ae44f","observation_id":"ecc5d21c-107e-4d4e-8962-b091c120cc69","resolution":{"observed_at":"2026-08-06T04:50:41.806679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.794023Z","title":"Exploring plain vision transformer backbones for object de- tection, 2022","venue":null,"work_id":"3656fa26-97b6-4ab1-88f9-5396e180b5a7","year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.338507Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:19328a672033d517e434fb498a487587d06003ddf81662dee3197eccdb176488","observation_id":"f44b9244-c065-4ccc-ac3b-76c79219b6a0","resolution":{"observed_at":"2026-08-06T04:50:41.797511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.785346Z","title":"Robust adversarial perturbation on deep proposal-based models","venue":null,"work_id":"c60ec9c6-974d-4a6d-b7e2-e89728898a2a","year":2018},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.341195Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:4449ce4dd7b37642747ae0501d801e498a51c8db997bde6c264ed10670bdb967","observation_id":"78621324-8e7c-46fd-807d-59a135413a55","resolution":{"observed_at":"2026-08-06T04:50:41.788252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.775972Z","title":"Attack anything: Blind dnns via universal background adversarial attack, 2024","venue":null,"work_id":"4754f976-868c-4d0b-a705-07745a0dc49c","year":2024},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.344036Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:082da04a6d23d516a01cba449ea4fe2f618ff9c33ee72eba85a7f270dea00b37","observation_id":"74b0d3fd-47aa-42f0-ae68-8e0f614fbf48","resolution":{"observed_at":"2026-08-06T04:50:41.779417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.766652Z","title":"A large-scale multiple-objective method for black-box attack against object detection","venue":null,"work_id":"b2455292-eac4-4f27-8837-5b69efeebf20","year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.346831Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:247c61cacb682d538408a991e767677ce94b74be927783c857edfdb2df5b39d6","observation_id":"06a2774f-b34e-4a03-8253-9245e9695ee9","resolution":{"observed_at":"2026-08-06T04:50:41.769553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.757643Z","title":"Lawrence Zitnick","venue":null,"work_id":"5d93711c-b1a0-45b3-a701-619604a84b45","year":2014},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.349575Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:d5fadb053e644b86c153264feca0656303ffeb2700401f504870d9390f660009","observation_id":"02102c18-50bf-4723-8a86-e13fe6b184df","resolution":{"observed_at":"2026-08-06T04:50:41.760590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.748075Z","title":null,"venue":null,"work_id":"07ecddae-e802-4e7a-a5df-65ffe2132e5d","year":2016},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.352675Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:0531de1a15bf2dda2c2a704a3c07039529a9b43949109d7bc00865ca59dadcbe","observation_id":"0c5873ae-89b4-49eb-94cb-87b3858abf8f","resolution":{"observed_at":"2026-08-06T04:50:41.751447Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.739317Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"114f905a-f989-40f3-a78c-4118338b73ae","year":2021},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.355631Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:993a949f6b0f0c0238ac785616c6e4f9467d042fad4c5fccd775c953f7b96d1f","observation_id":"1f029a17-f496-4938-8260-194c8604a055","resolution":{"observed_at":"2026-08-06T04:50:41.742360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.730622Z","title":"A convnet for the 2020s, 2022","venue":null,"work_id":"01ad0b94-0983-405d-8760-8288653ad146","year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.358790Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:d8b4f43a2294c72bcbc8a55d07b49b9fa8c8cef9acc2ca865e000f901d8ae6d0","observation_id":"d3d4d179-9997-4a0a-85e7-350e0045cdfc","resolution":{"observed_at":"2026-08-06T04:50:41.733568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.721170Z","title":"Give me your attention: Dot-product attention considered harmful for adversarial patch robustness","venue":null,"work_id":"edf8b534-1a6a-4e9b-af1f-123b8be5504f","year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.361784Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:9b177fdee024b0062eeca881c1096dfbdd94b19762c63a735faf5971a3ab2806","observation_id":"da185219-98da-48b5-844d-4564a3f7fcbe","resolution":{"observed_at":"2026-08-06T04:50:41.724542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.711824Z","title":"Towards deep learn- ing models resistant to adversarial attacks","venue":null,"work_id":"de91f460-2bbc-4165-a7da-dbaa211f950e","year":2018},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.365285Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:10866bc41a2c6dff53316323d25f1cebfc0d7c4cf1989c9cf74e843228560e70","observation_id":"fca71beb-a15c-4fc4-b21a-6c95d6d74ca3","resolution":{"observed_at":"2026-08-06T04:50:41.714832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.01934","last_updated":"2025-04-17T15:52:09Z","snapshot_observed_at":"2026-08-16T13:28:42.795226Z","submitted_at":"2024-08-04T05:22:08Z","title":"A Survey and Evaluation of Adversarial Attacks for Object Detection","version":5},"cited_work":{"arxiv_id":"2408.01934","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.01934","snapshot_observed_at":"2026-08-06T04:50:41.526910Z","title":"A Survey and Evaluation of Adversarial Attacks for Object Detection","venue":"cs.CV","work_id":"402d66c5-af3a-4a77-94fb-85ee0c3bbb33","year":2024},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.369344Z"},"links":{"cited_paper":"/paper/2408.01934","citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:a11d509d38f8d553e3353667f455132cc3570617fc4f948a8dd1c998b8eb87bb","observation_id":"863f7401-c90c-4160-aeb3-702d70b797f1","resolution":{"observed_at":"2026-08-06T04:50:41.532458Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06137","last_updated":"2022-12-12T18:59:58Z","snapshot_observed_at":"2026-08-16T16:09:12.679911Z","submitted_at":"2022-12-12T18:59:58Z","title":"NMS Strikes Back","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06137","snapshot_observed_at":"2026-08-06T04:50:41.374305Z","title":"Nms strikes back","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.374305Z"},"links":{"cited_paper":"/paper/2212.06137","citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:938410896dcf976c9c3a65bab3fa3363fcd8b0130c6264d4fe8d0f4328d26db3","observation_id":"5eec3291-ca72-402c-ab16-2de04b35f4e0","resolution":{"observed_at":"2026-08-06T04:50:41.374305Z","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":"2026-08-06T04:50:41.702754Z","title":"Pytorch: An im- perative style, high-performance deep learning library","venue":null,"work_id":"788ab104-3889-4991-9757-7cbdf3497f8a","year":2019},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.379345Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:54e243ffd0f0cfa8cd444027536a5030e20bdf4c60b0ce87fb83d596646a0274","observation_id":"7a760d4d-fbd0-4f04-ae50-cc199cbb9047","resolution":{"observed_at":"2026-08-06T04:50:41.705848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.693710Z","title":"Yolov3: An incremental improvement, 2018","venue":null,"work_id":"feae69f6-d340-4f98-80d7-45883cac1c7e","year":2018},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.387772Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:82f4aaa5aff744123accc2e5065422547502694697a486482a1afc74be433327","observation_id":"4aa7f4a7-fa79-4fdd-b17f-99693e9f37cf","resolution":{"observed_at":"2026-08-06T04:50:41.696460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.684137Z","title":"Faster r-cnn: Towards real-time object detection with region proposal networks, 2016","venue":null,"work_id":"485276a9-50eb-4454-b386-cc28009061ff","year":2016},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.400555Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:9cf64d5268da32ed97d14d3dd6963ad92fd701f90882485c2524189851460d30","observation_id":"b2d35e48-6ecf-4007-8715-d6c5220f46e5","resolution":{"observed_at":"2026-08-06T04:50:41.687885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.674445Z","title":"detrex: Benchmarking de- tection transformers, 2023","venue":null,"work_id":"fc3f1cf7-f759-421f-a530-70068de52946","year":2023},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.409179Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:6490edd49eb4730fdc9038151d3d8b48a4178995e4c70d3b61c2da371284cdff","observation_id":"a18c4129-8942-4c19-97be-2eba6877ef32","resolution":{"observed_at":"2026-08-06T04:50:41.677820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.665853Z","title":"Attention is all you need","venue":null,"work_id":"2df21d58-11e8-4aaf-93e6-e8cc9958a34e","year":2017},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.419715Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:90234c5cd4c2165134faef9076300fd504c4649aff27c961d2174b144cfb81d1","observation_id":"d1ef4f24-3daa-4326-aa26-737a68f2e8bb","resolution":{"observed_at":"2026-08-06T04:50:41.668752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.05778","last_updated":"2023-04-17T11:51:12Z","snapshot_observed_at":"2026-08-16T16:17:06.045278Z","submitted_at":"2022-11-10T18:59:04Z","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.05778","snapshot_observed_at":"2026-08-06T04:50:41.428702Z","title":"Internimage: Exploring large-scale vi- sion foundation models with deformable convolutions.arXiv preprint arXiv:2211.05778, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.428702Z"},"links":{"cited_paper":"/paper/2211.05778","citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:1d55ce392855d984cacc65efb2d79344c346b66900d0848123c0d41e137a9302","observation_id":"55c4d454-7b08-46f4-8b37-487d1a93f090","resolution":{"observed_at":"2026-08-06T04:50:41.428702Z","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":"2026-08-06T04:50:41.655675Z","title":"Gradient-guided hierarchical feature attack for object detector","venue":null,"work_id":"c47221fe-ca76-41ec-8144-95c12842493c","year":2024},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.431896Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:cb2b455cb95290719f77e18f2b422e506ad5172b9670e3fc9dd6561a4d9dac2f","observation_id":"750ef739-9c5f-46c9-9105-9b367dc56f11","resolution":{"observed_at":"2026-08-06T04:50:41.659224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.646565Z","title":"Transferable adversarial attacks for image and video object detection","venue":null,"work_id":"7bc334bf-c757-487e-939d-689f0212502d","year":2019},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.435045Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:4fb1837dac0adc5dc0b1245dca07cf199c4fed3252a0de783704bbf97c5c72b7","observation_id":"9d605d2f-4e8f-43b9-8c2e-53a23f58b558","resolution":{"observed_at":"2026-08-06T04:50:41.649795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.637247Z","title":"Detectron2","venue":null,"work_id":"1caa3cfd-2dbd-4421-8a8c-18d247f83101","year":2019},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.438003Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:748e20a4785b449ca50aa1c3fbfbb21d1424b51cf1237dded887874255dcd420","observation_id":"d91d781d-e4d0-4732-8f1a-3763f85c5879","resolution":{"observed_at":"2026-08-06T04:50:41.640209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.627343Z","title":"Adversarial examples for se- mantic segmentation and object detection","venue":null,"work_id":"8ee6c50d-e954-43bb-bb07-4b4a46146e3c","year":2017},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.440971Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:e2658d288a190011df3c32f2011c8556178c0307bc6254f916e96a311717b956","observation_id":"4b530210-21f0-451a-a029-520e843de572","resolution":{"observed_at":"2026-08-06T04:50:41.630701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.618565Z","title":"Focal modulation networks, 2022","venue":null,"work_id":"6f38ecc4-398a-4607-845f-cc5ba52fd30e","year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.443689Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:871f2d47bc48d8817ba8c8f8e68d4296c4a4e0841c0e46ad5ecb8893792f682d","observation_id":"5bba6505-4b89-47b4-b060-f2ad1e239b4f","resolution":{"observed_at":"2026-08-06T04:50:41.621481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.608735Z","title":"Ni, and Heung-Yeung Shum","venue":null,"work_id":"4ca1c8e9-5003-435f-b012-00558a46553d","year":2022},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.446733Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:c14984ba7605a48a853e70de6994880abb01705777d3173ce1f641f46ca384c7","observation_id":"15a99c6d-f561-467b-918a-dcbd65956df3","resolution":{"observed_at":"2026-08-06T04:50:41.611776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-06T04:50:41.449475Z","title":"Deformable detr: Deformable trans- formers for end-to-end object detection","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.449475Z"},"links":{"cited_paper":"/paper/2010.04159","citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:6f70771798854148f8ebb55d40a67af59d77883e8c6364a9f831bf3fa9c10d07","observation_id":"42d23715-e3a9-46c3-a683-585d2972483a","resolution":{"observed_at":"2026-08-06T04:50:41.449475Z","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":"2026-08-06T04:50:41.598759Z","title":"• For AFOG’s implementation a link to an anonymous downloadable source repository is included in our ab- stract","venue":null,"work_id":"7570d463-0b0d-4c0c-8b6a-36af7f6493a6","year":null},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.452732Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:f36f9bf5f508215f78fd01dba67ec0e084b494208c3e9fd396b8d5b34b5ae72b","observation_id":"d06082ba-0864-4956-a4ac-7e4795c9f281","resolution":{"observed_at":"2026-08-06T04:50:41.602073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.589252Z","title":null,"venue":null,"work_id":"5fa213a4-ceb2-4a07-a845-1c1b183397d8","year":2017},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.455656Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:a09d9999e0a072de97c499a29accf7b442db0c997551cf4aaaf8d24c46663336","observation_id":"83526d91-e760-438e-93b6-0a5e6ef5cbe0","resolution":{"observed_at":"2026-08-06T04:50:41.592101Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.569443Z","title":"A larger version of InternImage is also cur- rently one of the strongest models on the COCO ob- ject detection leaderboard [9]","venue":null,"work_id":"406ddb70-f2ce-4c25-ad69-33063b845451","year":2017},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.461528Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:c075eae2c518fd62a93ca6bc8db9cf95bf274fb07a604413062b2c858ebba7cd","observation_id":"313b3f1b-e7a1-4bcf-b8ec-a315d8f5c391","resolution":{"observed_at":"2026-08-06T04:50:41.572754Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.560254Z","title":"The key difference between AFOG and AFOG-V is the replacement of Ox with a set of zero predictions ∅ instead of forward propagating image Ox ← fD(x; ϑ)","venue":null,"work_id":"006de6dd-8df3-4e08-93da-a97640cd40a2","year":null},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.464492Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:d2a3d5232f42518b496035468622e8f3944fb585069939d55771ccd81053408d","observation_id":"0a2a757e-dc4f-4e43-856a-2c76c73275c1","resolution":{"observed_at":"2026-08-06T04:50:41.563389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.549401Z","title":"Couch” prediction in both models by disrupting both class and bounding box losses. Similarly, AFOG induces several small “Cat","venue":null,"work_id":"44f2fd5c-40a1-410e-a37a-ea4d33defb6c","year":null},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.467985Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:6210b37abf39ecef2d5d495e7df11e9f9093dc8d6a852978d1743f16d03a4b12","observation_id":"734b680c-9d11-448f-bf75-dadb7965eb06","resolution":{"observed_at":"2026-08-06T04:50:41.552576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-06T04:50:41.579040Z","title":"We choose ViTDet for our experiments to investigate AFOG’s potential applicability to all ViT-based models","venue":null,"work_id":"787267e7-b400-4f39-a743-c81406596e71","year":2017},"citing_paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T04:50:41.458718Z"},"links":{"citing_paper":"/paper/2508.02987"},"observation_digest":"sha256:49fae6a79f02986210c756e4e3d02ccaeb89e640339dff6ea4c456e67e090226","observation_id":"3e2dfd36-a394-4637-9854-ebdc06f28cc6","resolution":{"observed_at":"2026-08-06T04:50:41.582447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.02987","last_updated":"2025-08-05T01:31:10Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T02:57:23.719882Z","submitted_at":"2025-08-05T01:31:10Z","title":"Adversarial Attention Perturbations for Large Object Detection Transformers"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":35},"total_outbound_references":44},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2508.02987."}