{"as_of":"2026-08-09T11:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2c3788dcfa1a2ad9166f01c6a6073817c064e04f99fea3e579ec0e608dc121fa","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T23:06:14.759570Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2608.03231/citation-record","integrity":"/paper/2608.03231/integrity","json":"/paper/2608.03231/citation-record.json","paper":"/paper/2608.03231"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T23:06:15.417923Z","title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control,","venue":null,"work_id":"48a8969a-7c78-42e0-8af8-baed942a60aa","year":2023},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.686176Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:af0b4a7e19a2282d6b838e60847df5f25c6577c6ae819baa32e7ca57b428732d","observation_id":"a39f8970-2279-4ac0-88d7-1dc642e30583","resolution":{"observed_at":"2026-08-05T23:06:15.420535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09246","last_updated":"2024-09-05T19:46:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-13T15:46:55Z","title":"OpenVLA: An Open-Source Vision-Language-Action Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09246","snapshot_observed_at":"2026-08-05T23:06:14.689326Z","title":"Openvla: An open-source vision-language-action model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.689326Z"},"links":{"cited_paper":"/paper/2406.09246","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:9b4bc7a9af4601f035cc182338bf6c250f0411e7c25154c9e4df28a998f60e98","observation_id":"998d6341-7a24-4fa0-b90d-22e3db3156df","resolution":{"observed_at":"2026-08-05T23:06:14.689326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12213","last_updated":"2024-05-26T19:55:26Z","snapshot_observed_at":"2026-07-06T18:16:51.116432Z","submitted_at":"2024-05-20T17:57:01Z","title":"Octo: An Open-Source Generalist Robot Policy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.12213","snapshot_observed_at":"2026-08-05T23:06:14.692364Z","title":"Octo: An open-source generalist robot policy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.692364Z"},"links":{"cited_paper":"/paper/2405.12213","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:b7441af562192905030c0cffb9ce27861ab5f2ae48812631ac23595917b0b067","observation_id":"393e0d5c-73d9-480f-9eff-4f5853cb0402","resolution":{"observed_at":"2026-08-05T23:06:14.692364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.24164","last_updated":"2026-01-08T17:01:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-31T17:22:30Z","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.24164","snapshot_observed_at":"2026-08-05T23:06:14.695292Z","title":"π 0: A vision-language-action flow model for general robot control,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.695292Z"},"links":{"cited_paper":"/paper/2410.24164","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:9a1ea37f72cf10b66fa8c54f5d77d37e001263ffbe68a054212d1e69ea91cbdd","observation_id":"6e8d5955-b9a4-442f-9860-0194f51174a7","resolution":{"observed_at":"2026-08-05T23:06:14.695292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.09665","last_updated":"2018-05-17T01:44:59Z","snapshot_observed_at":"2026-07-06T06:16:16.225385Z","submitted_at":"2017-12-27T20:03:51Z","title":"Adversarial Patch","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.09665","snapshot_observed_at":"2026-08-05T23:06:14.698236Z","title":"Adversarial patch,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.698236Z"},"links":{"cited_paper":"/paper/1712.09665","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:d0b66779bf848afc51a1197518447f9f8451b4872be54bcfd095a07332f5e349","observation_id":"feee247a-bdd0-4aa3-9b6a-493696c6891a","resolution":{"observed_at":"2026-08-05T23:06:14.698236Z","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":"2026-08-05T23:06:15.410477Z","title":"Synthesizing robust adversar- ial examples,","venue":null,"work_id":"eb62bc2d-676e-45e2-a765-09be90863a65","year":2018},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.700973Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:b539d344efbc5a3ea7ccfc9ef88e0ffb677acaa839f115d72a77767f0b72ba99","observation_id":"19b1536e-87ef-4e5c-b3da-a120db88d505","resolution":{"observed_at":"2026-08-05T23:06:15.413009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:14.703646Z","title":"Manipulation facing threats: Evaluating physical vulnerabilities in end-to-end vision language action models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.703646Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:7896b8d6da6e4af2bcf75e42acc2cff38410a614fd1b647daaf3cfe44e68aa79","observation_id":"e97eb49e-5296-4fc2-844f-6a5f943a21bf","resolution":{"observed_at":"2026-08-05T23:06:14.703646Z","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":"2026-08-05T23:06:14.706033Z","title":"Eva-vla: Evaluating vision-language- action models’ robustness under real-world physical variations,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.706033Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:0790c24ef31ad751b20f1af0247a8323b5102d37aedeb21bfe33eceed6eb737e","observation_id":"84f5fcfe-1e54-483a-a82b-c0e5f696e2dc","resolution":{"observed_at":"2026-08-05T23:06:14.706033Z","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":"2026-08-05T23:06:15.402963Z","title":"Exploring the adversarial vulnera- bilities of vision-language-action models in robotics,","venue":null,"work_id":"8a8d2bcc-069b-4a6c-86ac-2ade13a466b3","year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.708393Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:278fc47d7041ec4597fb9fc3dceb282837e84957dd47553cef6588fcc5e153f0","observation_id":"48426eb5-ee36-4468-84b0-a80486a00611","resolution":{"observed_at":"2026-08-05T23:06:15.405547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:14.710688Z","title":"Model-agnostic adversarial attack and defense for vision-language-action models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.710688Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:40a24285942c8f9b2c74a7fe6f44a30182e1b96885b10a9a0d102daca7fe6ef9","observation_id":"807f5217-a23e-487b-a2ab-25ecb6b9fe89","resolution":{"observed_at":"2026-08-05T23:06:14.710688Z","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":"2026-08-05T23:06:15.395183Z","title":"Libero: Benchmarking knowledge transfer for lifelong robot learning,","venue":null,"work_id":"b2229b0c-b6cc-4c67-8c34-6568eed3e8b8","year":2023},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.712967Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:72efba42dcc43d97cb0b2b31408c782af2c0a1fbd13db6d2a1d72d7a16300dd7","observation_id":"767a8bfc-1281-4899-bc4d-cf22ffa671d7","resolution":{"observed_at":"2026-08-05T23:06:15.398053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:15.387929Z","title":"Diffusion policy: Visuomotor policy learning via action diffusion,","venue":null,"work_id":"20374f68-35a7-4afb-b5c0-a72c3bf0005d","year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.715441Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:d550b508e4c7c459e6e478a7de4c3d2942fdb0c9042d33229e88090bb07eeb42","observation_id":"a5a8ebe4-eecb-4940-a540-487cff11fba4","resolution":{"observed_at":"2026-08-05T23:06:15.390459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:15.380555Z","title":"Mft: Modal fusion transformer for cross- modal fusion in 3d object detection,","venue":null,"work_id":"ec84995d-09e5-4088-8321-f8408b49a9a4","year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.717800Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:40279131eb6292ea5005c825d98b831ad97b16b3631dac339792b7c70a77cf5c","observation_id":"284defe1-7ffa-4eb0-a72c-761eb9a53b6c","resolution":{"observed_at":"2026-08-05T23:06:15.383088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:15.373163Z","title":"Dstr: Dual scenes transformer for cross-modal fusion in 3d object detection,","venue":null,"work_id":"e18f9672-11da-46da-bfd3-b4328551bed4","year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.720082Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:c079562774068a7205e3110444713e68e47860505a2671669ca1410493457be9","observation_id":"afc7abe0-8fef-4768-ae24-61d97a120988","resolution":{"observed_at":"2026-08-05T23:06:15.375780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:14.722301Z","title":"When robots obey the patch: Universal transferable patch attacks on vision-language-action models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.722301Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:c6b7359d03e78acaba738751bf4d53707f580f810e4138c108d1f1c7fda5c3b4","observation_id":"8ba9e4b6-88b7-46fc-becf-7f9867d48c38","resolution":{"observed_at":"2026-08-05T23:06:14.722301Z","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":"2026-08-05T23:06:14.724813Z","title":"Attention-guided patch-wise sparse adversarial attacks on vision-language-action models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.724813Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:1e7ed7822ee3c13ea8a80268403599f1b124da3b991473a3097931bdf22a44b3","observation_id":"0b3525f3-c5d2-4f4f-91fa-a6e4f217afe1","resolution":{"observed_at":"2026-08-05T23:06:14.724813Z","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":"2026-08-05T23:06:14.727346Z","title":"Attackvla: Benchmarking adversarial and backdoor attacks on vision-language-action models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.727346Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:08a30c2e3efb3b5e25011f14aee9fdbbdaee55158ca5f3c8088d697ed926080a","observation_id":"49d8984b-36cb-4172-baf8-0950d6a21ae8","resolution":{"observed_at":"2026-08-05T23:06:14.727346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-05T23:06:14.729891Z","title":"Towards deep learning mod- els resistant to adversarial attacks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.729891Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:60e8cf9e18aef794d6244c6d93eb00d4d47697419ed7e769fad1ce90b57a848d","observation_id":"d8f99bcd-fea5-4bf4-b756-0e9d0583d466","resolution":{"observed_at":"2026-08-05T23:06:14.729891Z","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":"2026-08-05T23:06:15.364714Z","title":"Theoretically principled trade-off be- tween robustness and accuracy,","venue":null,"work_id":"1b73b15c-d7bf-410e-898a-6710bb2db7b3","year":2019},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.732865Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:e6674a81e3a6d6314cfd38ac5a5e26055b9860e3e72a8dad099622a21349064a","observation_id":"0ea06ddf-7872-4150-9c24-17e0baa8b7cc","resolution":{"observed_at":"2026-08-05T23:06:15.368012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:15.356513Z","title":"Domain randomization for transferring deep neural networks from simulation to the real world,","venue":null,"work_id":"13892ab6-8a0d-4a30-b586-3690b9cf7fd2","year":2017},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.735473Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:d9e78bdfafc7be0ff5da8b3e511776d021009de3012c11284cf96cf05f7043c4","observation_id":"9a1ced44-9188-45e3-bd27-43a297ea07ab","resolution":{"observed_at":"2026-08-05T23:06:15.359352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.07460","last_updated":"2022-05-16T06:03:00Z","snapshot_observed_at":"2026-08-04T18:06:26.992880Z","submitted_at":"2022-05-16T06:03:00Z","title":"Diffusion Models for Adversarial Purification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.07460","snapshot_observed_at":"2026-08-05T23:06:14.738049Z","title":"Diffusion models for adversarial purification,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.738049Z"},"links":{"cited_paper":"/paper/2205.07460","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:0afefaa5bf63fd0f3c54f48932cd6b84c02a806b48215c71a2646420eb4f7a7e","observation_id":"6c8ae63e-61ba-4009-9244-e7d4e2947e81","resolution":{"observed_at":"2026-08-05T23:06:14.738049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06605","last_updated":"2018-05-18T00:20:52Z","snapshot_observed_at":"2026-08-02T06:44:56.184651Z","submitted_at":"2018-05-17T05:38:55Z","title":"Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06605","snapshot_observed_at":"2026-08-05T23:06:14.740820Z","title":"Defense-gan: Protecting classifiers against adversarial attacks using generative models,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.740820Z"},"links":{"cited_paper":"/paper/1805.06605","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:b18c448d6386d66ccc8e2c84552b732145818eb1e835cf3efea3741fd9d5f060","observation_id":"bc99b205-cf3f-4840-bf59-05acb970b94a","resolution":{"observed_at":"2026-08-05T23:06:14.740820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10766","last_updated":"2018-05-21T05:26:01Z","snapshot_observed_at":"2026-08-04T05:51:55.347332Z","submitted_at":"2017-10-30T04:21:23Z","title":"PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10766","snapshot_observed_at":"2026-08-05T23:06:14.743502Z","title":"Pixeldefend: Leveraging generative models to understand and defend against adversarial examples,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.743502Z"},"links":{"cited_paper":"/paper/1710.10766","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:50b5f6e10dfe64cf56bc12d16e76809e5c5b3303e1f9daffedd159d554aea4b5","observation_id":"ae3302a1-186a-4f09-a8ce-412f7a986002","resolution":{"observed_at":"2026-08-05T23:06:14.743502Z","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":"2026-08-05T23:06:15.348940Z","title":"{PatchGuard}: A provably robust defense against adversarial patches via small receptive fields and masking,","venue":null,"work_id":"b6be2e5e-86c9-4e6d-a30e-09603eb3e8ac","year":2021},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.746180Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:b69f9834fe9d08a420b21d4167057a5bd2d7f396c20dcb6c43499dff8fe1e6fb","observation_id":"5bc0a4bd-5d3a-4a00-9995-de5d41b1131d","resolution":{"observed_at":"2026-08-05T23:06:15.351567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:15.341255Z","title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples,","venue":null,"work_id":"26774863-967f-44d1-999b-1347f27824ed","year":2018},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.748858Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:b63b9ee84af95c903894d3c96a9596ee3b7d94626f615b806591af2441d599b3","observation_id":"57c8423d-e9ca-4fa9-a846-a72f802c3c1e","resolution":{"observed_at":"2026-08-05T23:06:15.343797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:15.332668Z","title":"Overcoming catas- trophic forgetting in neural networks,","venue":null,"work_id":"d3ccf480-56a4-4c90-9c01-4c3088763e87","year":2017},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.751347Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:8f79c6c217a0efc9ff2dd8e332c89f3caefa6fd1983d20dd849682905949f824","observation_id":"e5709ec9-7152-43a4-a1d5-2762132b9330","resolution":{"observed_at":"2026-08-05T23:06:15.336236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-05T23:06:15.323251Z","title":"Learning without forgetting,","venue":null,"work_id":"c24844e6-047a-47a8-83c5-059245ee6812","year":2018},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.754003Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:dc64a2175d8452499315e351e67fa79b6d2f2badadd0272537a67587c17d047d","observation_id":"c5b97522-3c4f-4842-9b6a-4a4c77fb37d9","resolution":{"observed_at":"2026-08-05T23:06:15.326827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1612.03928","last_updated":"2017-02-12T22:05:47Z","snapshot_observed_at":"2026-07-06T05:22:25.273447Z","submitted_at":"2016-12-12T21:15:57Z","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.03928","snapshot_observed_at":"2026-08-05T23:06:14.756828Z","title":"Paying more attention to attention: Improving the performance of convolutional neural networks via atten- tion transfer,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.756828Z"},"links":{"cited_paper":"/paper/1612.03928","citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:652424139e9b116f15c5c8ebdf7bfa8b45775e0f3b276d3b09a14efbd51c5688","observation_id":"9d766829-16c6-49ec-a2eb-a53a516646af","resolution":{"observed_at":"2026-08-05T23:06:14.756828Z","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":"2026-08-05T23:06:14.759570Z","title":"Robust finetuning of vision- language-action robot policies via parameter merging,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T23:06:14.759570Z"},"links":{"citing_paper":"/paper/2608.03231"},"observation_digest":"sha256:66406dc90fe50ccb8c098fb22d5e52bc42b8ee9575f7fdb1a7a151b61b6c37c3","observation_id":"8be20555-9bce-4205-b18b-922824e007bb","resolution":{"observed_at":"2026-08-05T23:06:14.759570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.03231","last_updated":"2026-08-04T07:03:05Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-09T09:53:14.297976Z","submitted_at":"2026-08-04T07:03:05Z","title":"Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":13},"total_outbound_references":29},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2608.03231."}